AI Model Catalog

Spesifikasi, Harga & Fitur Model AI

Bandingkan 636 model AI dari 324 provider. Context window, pricing, reasoning, tool calling, dan multimodal — semua di satu tempat.

alibaba

Qwen3 235B-A22B Thinking 2507

alibaba · qwen

Updated large open Qwen3 MoE thinking model for reasoning, math, coding, and tool use

Text→Text
262K ctx · 82K outReasoningToolsOpen
alibaba

Qwen3 30B A3B

alibaba · qwen

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Text→Text
131K ctx · 16K outReasoningToolsOpen
alibaba

Qwen2.5-VL 72B Instruct

alibaba · qwen-vl

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImage→Text
131K ctx · 8K outToolsAttachmentsOpen
alibaba

Qwen3.6 27B

alibaba · qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImageVideo→Text
262K ctx · 66K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 10.898/1M•Output Rp 65.387/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.5 9B Base

alibaba · qwen

Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning

TextImageVideo→Text
262K ctx · 66K outAttachmentsOpen
alibaba

Qwen Max

alibaba · qwen-max

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Text→Text
33K ctx · 8K outTools
💰Harga:
Input Rp 20.343/1M•Output Rp 81.371/1M
🏷️ Termurah: AI/ML API
alibaba

Qwen3 Reranker 8B

alibaba · qwen-reranker

Multilingual query-document reranking model supporting more than 100 languages

Text→Text
33K ctx · 0 outOpen
alibaba

Qwen3.5 122B-A10B

alibaba · qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImageVideo→Text
262K ctx · 66K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 7.266/1M•Output Rp 58.122/1M
🏷️ Termurah: LLM Gateway
alibaba

Qwen-Image-2.1

alibaba · qwen-image

Unified text-to-image generation and image editing model with native RGBA transparency and reference-image editing

TextImage→Image
8K ctx · 0 outAttachmentsOpen
alibaba

Qwen-VL Max

alibaba · qwen-vl-max

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImage→Text
131K ctx · 8K outToolsAttachments
alibaba

Qwen 3.8 Max Prime

alibaba · qwen-max

High-throughput edition of Qwen3.8 Max for coding, professional work, multimodal understanding, and long-running agent workflows

TextImageVideo→Text
1M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 72.653/1M•Output Rp 217.957/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.5 4B

alibaba · qwen

Small Qwen3.5 multimodal model for low-cost chat, reasoning, and tool use

TextImageVideo→Text
262K ctx · 82K outReasoningToolsAttachmentsOpen
alibaba

Qwen3.5 Plus

alibaba · qwen-plus

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImageVideo→Text
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 7.266/1M•Output Rp 43.592/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3 Max Preview

alibaba · qwen-max

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Text→Text
262K ctx · 33K outTools
alibaba

Qwen3.6 Flash

alibaba · qwen-flash

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImageVideo→Text
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 4.541/1M•Output Rp 27.245/1M
🏷️ Termurah: LLM Gateway
alibaba

Qwen3.5 Flash

alibaba · qwen-flash

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImageVideo→Text
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 1.817/1M•Output Rp 7.266/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.8 Max 0902

alibaba · qwen-max

2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding

TextImageVideoPDF→Text
1M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 108.979/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen2.5-Coder-0.5B

alibaba · qwen-coder

Tiny open Qwen code model for lightweight completion and on-device coding

Text→Text
33K ctx · 8K outOpen
alibaba

Qwen3 Coder Flash

alibaba · qwen-coder-flash

Qwen coding model for software agents, repository edits, and code reasoning

Text→Text
1M ctx · 66K outTools
💰Harga:
Input Rp 5.449/1M•Output Rp 27.245/1M
🏷️ Termurah: LLM Gateway
alibaba

Qwen3 Omni 30B A3B Thinking

alibaba · qwen-omni

Multimodal reasoning model accepting text, images, video, and audio with text output

TextImageVideoAudio→Text
66K ctx · 16K outReasoningToolsAttachmentsOpen
alibaba

Qwen Plus

alibaba · qwen-plus

Qwen instruction model for multilingual chat, reasoning, and tool use

Text→Text
1M ctx · 33K outReasoningTools
💰Harga:
Input Rp 5.086/1M•Output Rp 15.257/1M
🏷️ Termurah: AI/ML API
alibaba

Qwen3 30B-A3B Instruct 2507

alibaba · qwen

Updated compact Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Text→Text
262K ctx · 16K outToolsOpen
alibaba

Qwen3.8 Flash

alibaba · qwen-flash

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImageVideo→Text
1M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 2.725/1M•Output Rp 8.537/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

QwQ 32B

alibaba · qwq

Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving

Text→Text
131K ctx · 8K outReasoningToolsOpen
alibaba

Qwen3-Next 80B-A3B (Thinking)

alibaba · qwen

Efficient Qwen thinking model for local reasoning, math, and coding agents

Text→Text
262K ctx · 33K outReasoningToolsOpen
alibaba

Qwen3.5 35B-A3B Base

alibaba · qwen

Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning

TextImageVideo→Text
262K ctx · 66K outAttachmentsOpen
alibaba

Qwen3.5 35B-A3B

alibaba · qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImageVideo→Text
262K ctx · 66K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 4.541/1M•Output Rp 36.327/1M
🏷️ Termurah: LLM Gateway
alibaba

Qwen-VL Plus

alibaba · qwen-vl-plus

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImage→Text
131K ctx · 8K outToolsAttachments
alibaba

Qwen3.5 2B

alibaba · qwen

Compact Qwen3.5 multimodal model for fast chat, reasoning, and tool use

TextImageVideo→Text
262K ctx · 82K outReasoningToolsAttachmentsOpen
alibaba

Qwen3.8 Max

alibaba · qwen-max

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

TextImageVideoPDF→Text
1M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 108.979/1M
🏷️ Termurah: AI/ML API
alibaba

Qwen3.8 Max Preview

alibaba · qwen-max

Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows

TextImageVideo→Text
1M ctx · 131K outReasoningToolsAttachments
alibaba

Qwen3.5 27B

alibaba · qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImageVideo→Text
262K ctx · 66K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 43.592/1M
🏷️ Termurah: LLM Gateway
alibaba

Qwen3.5 9B

alibaba · qwen

Qwen instruction model for multilingual chat, reasoning, and tool use

TextImageVideo→Text
262K ctx · 66K outReasoningToolsAttachmentsOpen
alibaba

Qwen3 Coder Next

alibaba · qwen-coder

Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use

Text→Text
262K ctx · 66K outToolsOpen
💰Harga:
Input Rp 9.082/1M•Output Rp 21.796/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3 Coder Plus

alibaba · qwen-coder-plus

Hosted Qwen coder for software agents, repo edits, and long-context code

Text→Text
1.0M ctx · 66K outTools
alibaba

Qwen3.8 Omni Flash

alibaba · qwen-omni-flash

Qwen omni model for text, vision, audio, and multimodal agent tasks

TextImageAudioVideo→Text
1M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 2.725/1M•Output Rp 8.537/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

QwQ Plus

alibaba · qwq

Qwen reasoning model for deliberate problem solving, math, and coding

Text→Text
131K ctx · 8K outReasoningTools
alibaba

Qwen3 VL 30B A3B Instruct

alibaba · qwen-vl

Open vision-language MoE model for image and video understanding, documents, and visual agents

TextImageVideo→Text
262K ctx · 33K outToolsAttachmentsOpen
alibaba

Qwen2.5 7B Instruct

alibaba · qwen

Small open Qwen2.5 instruction model for chat, structured output, and tool use

Text→Text
131K ctx · 8K outToolsOpen
alibaba

Qwen3-VL Plus

alibaba · qwen-vl-plus

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImageVideo→Text
262K ctx · 33K outReasoningToolsAttachments
💰Harga:
Input Rp 3.633/1M•Output Rp 29.061/1M
🏷️ Termurah: LLM Gateway
alibaba

Qwen3.8 Flash Next

alibaba · qwen-flash

Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding

TextImageVideo→Text
262K ctx · 131K outReasoningToolsAttachmentsOpen
alibaba

Qwen3.5 0.8B

alibaba · qwen

Smallest Qwen3.5 multimodal model for on-device chat, reasoning, and tool use

TextImageVideo→Text
262K ctx · 82K outReasoningToolsAttachmentsOpen
alibaba

Qwen3.5 397B-A17B

alibaba · qwen

Large open Qwen multimodal MoE for visual agents and long technical tasks

TextImageVideo→Text
262K ctx · 66K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 10.898/1M•Output Rp 65.387/1M
🏷️ Termurah: Cloudflare AI Gateway
alibaba

Qwen3 Max

alibaba · qwen-max

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

Text→Text
262K ctx · 66K outTools
💰Harga:
Input Rp 21.796/1M•Output Rp 108.979/1M
🏷️ Termurah: Cloudflare AI Gateway
alibaba

Qwen3-Next 80B-A3B Instruct

alibaba · qwen

Qwen instruction model for multilingual chat, reasoning, and tool use

Text→Text
262K ctx · 33K outToolsOpen
💰Harga:
Input Rp 1.635/1M•Output Rp 19.980/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen4 Max

alibaba · qwen-max

Flagship multimodal model for coding, office productivity, frontend design, and complex agentic tasks

TextImageVideoPDF→Text
1M ctx · 262K outReasoningToolsAttachments
💰Harga:
Input Rp 27.245/1M•Output Rp 81.734/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3-Coder 480B-A35B Instruct

alibaba · qwen-coder

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Text→Text
262K ctx · 66K outToolsOpen
💰Harga:
Input Rp 19.217/1M•Output Rp 93.681/1M
🏷️ Termurah: AI/ML API
alibaba

Qwen3-Coder 30B-A3B Instruct

alibaba · qwen-coder

Smaller Qwen coder for efficient local agents and repo-level fixes

Text→Text
262K ctx · 66K outToolsOpen
alibaba

Qwen3.8 2.4T A95B

alibaba · qwen

Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows

Text→Text
262K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 36.327/1M•Output Rp 108.979/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3 VL 235B A22B Instruct

alibaba · qwen-vl

Qwen vision-language instruct model for visual reasoning, documents, and agent tasks

TextImage→Text
131K ctx · 33K outToolsAttachmentsOpen
alibaba

Qwen3 235B-A22B Instruct 2507

alibaba · qwen

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Text→Text
262K ctx · 16K outToolsOpen
alibaba

Qwen3 32B

alibaba · qwen

Dense open Qwen model for self-hosted chat, reasoning, and coding

Text→Text
131K ctx · 16K outReasoningToolsOpen
alibaba

Qwen3.7 Max

alibaba · qwen-max

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

Text→Text
1M ctx · 131K outReasoningTools
💰Harga:
Input Rp 22.704/1M•Output Rp 68.112/1M
🏷️ Termurah: Cloudflare AI Gateway
alibaba

Qwen3.8 27B

alibaba · qwen

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

TextImageVideo→Text
262K ctx · 33K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 1.090/1M•Output Rp 35.600/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3 VL Flash (Alibaba Cloud)

alibaba · qwen-vl-flash

Qwen vision-language model for visual reasoning, documents, and agent tasks

TextImage→Text
262K ctx · 33K outToolsAttachments
alibaba

Qwen3.6 35B-A3B

alibaba · qwen

Open multimodal Qwen MoE for local agents that need vision, audio, and code

TextImageVideo→Text
262K ctx · 66K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 6.812/1M•Output Rp 40.867/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen-Omni Turbo

alibaba · qwen-omni

Qwen omni model for text, vision, audio, and multimodal agent tasks

TextImageAudioVideo→TextAudio
33K ctx · 2K outToolsAttachments
alibaba

Qwen Turbo

alibaba · qwen-turbo

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Text→Text
1M ctx · 16K outReasoningTools
alibaba

Qwen Flash

alibaba · qwen-flash

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Text→Text
1M ctx · 33K outReasoningTools
💰Harga:
Input Rp 909/1M•Output Rp 7.266/1M
🏷️ Termurah: LLM Gateway
alibaba

Qwen3 8B

alibaba · qwen

Dense 8B Qwen3 model with switchable thinking for chat, reasoning, and tool use

Text→Text
33K ctx · 33K outReasoningToolsOpen
alibaba

Qwen3 VL 235B A22B Thinking

alibaba · qwen-vl

Qwen vision-language thinking model for visual reasoning, documents, and agent tasks

TextImage→Text
131K ctx · 33K outReasoningToolsAttachmentsOpen
alibaba

Qwen3 Embedding 8B

alibaba · qwen-embedding

Multilingual text embedding model for retrieval, code search, classification, and clustering

Text→Text
33K ctx · 0 outOpen
alibaba

Qwen3 235B-A22B

alibaba · qwen

Large open Qwen MoE for multilingual reasoning, coding, and tool use

Text→Text
131K ctx · 16K outReasoningToolsOpen
alibaba

Qwen3.7 Flash

alibaba · qwen-flash

Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

TextImageVideo→Text
1M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 545/1M•Output Rp 2.362/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.7 Plus

alibaba · qwen-plus

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

TextImageVideo→Text
1M ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 5.813/1M•Output Rp 23.249/1M
🏷️ Termurah: Cloudflare AI Gateway
alibaba

Qwen3.6 Max Preview

alibaba · qwen-max

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Text→Text
262K ctx · 66K outReasoningTools
alibaba

Qwen MT Plus

alibaba · qwen-mt-plus

Flagship Qwen translation model with terminology control and support for 92 languages

Text→Text
16K ctx · 8K out
alibaba

Qwen3.6 Plus

alibaba · qwen-plus

Earlier Qwen multimodal workhorse for million-token agent and document tasks

TextImageVideo→Text
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 9.082/1M•Output Rp 54.490/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen2.5-Coder-32B-Instruct

alibaba · qwen-coder

Open coding-focused Qwen model for code generation, repair, and repository reasoning

Text→Text
131K ctx · 8K outToolsOpen
microsoft

Phi-4-mini

microsoft · phi-mini

Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks

Text→Text
128K ctx · 4K outToolsOpen
microsoft

WizardLM 2 8x22B

microsoft · wizardlm

Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks

Text→Text
66K ctx · 8K outOpen
💰Harga:
Input Rp 8.955/1M•Output Rp 8.955/1M
🏷️ Termurah: NanoGPT
microsoft

MAI-Code-1.1-Flash

microsoft · mai-code-flash

Microsoft coding model with native vision support, optimized for fast and efficient software development

TextImage→Text
256K ctx · 128K outReasoningToolsAttachments
microsoft

MAI Code 2 Flash

microsoft · mai-code-flash

Microsoft's lightweight coding model for explanations, targeted edits and routine fixes at high volume

TextImage→Text
1.1M ctx · 128K outReasoningToolsAttachments
microsoft

MAI-Code-1-Flash

microsoft · mai-code-flash

Microsoft coding model built for fast, efficient assistance in everyday developer workflows

Text→Text
256K ctx · 128K outReasoningTools
microsoft

Phi-4-multimodal-instruct

microsoft · phi

Compact Microsoft multimodal model for text, image, and speech understanding

TextImageAudio→Text
131K ctx · 131K outToolsAttachmentsOpen
microsoft

MAI Code 2

microsoft · mai-code

Microsoft's larger agentic coding model for debugging, multi-file changes and repository-wide reasoning

TextImage→Text
1.1M ctx · 128K outReasoningToolsAttachments
sarvam

Sarvam-M

sarvam · sarvam

Hybrid-reasoning multilingual model for Indian languages built on Mistral Small

Text→Text
33K ctx · 33K outReasoningOpen
sarvam

Sarvam 30B

sarvam · sarvam

Efficient Indian-language reasoning model for chat, coding, and multilingual work

Text→Text
128K ctx · 128K outReasoningToolsOpen
sarvam

Sarvam 105B

sarvam · sarvam

Flagship Indian-language reasoning model for enterprise multilingual applications

Text→Text
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 727/1M•Output Rp 2.907/1M
🏷️ Termurah: FastRouter
aion-labs

Aion-3.0-Mini

aion-labs · aion-mini

Efficient model for low-latency assistance, extraction, and routine automation

Text→Text
131K ctx · 33K outReasoningTools
💰Harga:
Input Rp 12.715/1M•Output Rp 25.429/1M
🏷️ Termurah: NanoGPT
aion-labs

Aion-3.0

aion-labs · aion

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Text→Text
131K ctx · 33K outReasoningTools
💰Harga:
Input Rp 54.490/1M•Output Rp 108.979/1M
🏷️ Termurah: NanoGPT
aion-labs

Aion-2.0

aion-labs · aion

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Text→Text
131K ctx · 33K outReasoningTools
💰Harga:
Input Rp 14.531/1M•Output Rp 29.061/1M
🏷️ Termurah: NanoGPT
aion-labs

Aion-RP 1.0 (8B)

aion-labs · aion-rp

Open Llama instruction model for multilingual chat, reasoning, and coding

Text→Text
33K ctx · 29K outOpen
💰Harga:
Input Rp 14.531/1M•Output Rp 29.061/1M
🏷️ Termurah: NanoGPT
xiaomi

MiMo-V2.5-TTS

xiaomi · mimo-tts

Speech generation model for controllable voice, narration, and audio delivery

Text→Audio
8K ctx · 8K out
xiaomi

MiMo-V2.5-Pro-UltraSpeed

xiaomi · mimo-pro

MiMo pro model for strong multimodal reasoning and agent execution

Text→Text
1.0M ctx · 131K outReasoningToolsOpen
xiaomi

MiMo-V2-TTS

xiaomi · mimo-tts

Speech generation model for controllable voice, narration, and audio delivery

Text→Audio
8K ctx · 8K out
xiaomi

MiMo-V2.6-Pro-UltraSpeed

xiaomi · mimo-pro

MiMo pro model for strong multimodal reasoning and agent execution

TextImageAudioVideo→Text
1.0M ctx · 131K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 79.010/1M•Output Rp 158.019/1M
🏷️ Termurah: NanoGPT
xiaomi

MiMo-V2.5-TTS-VoiceClone

xiaomi · mimo-tts

Speech generation model for controllable voice, narration, and audio delivery

Text→Audio
8K ctx · 8K out
xiaomi

MiMo-V2.5-TTS-VoiceDesign

xiaomi · mimo-tts

Speech generation model for controllable voice, narration, and audio delivery

Text→Audio
8K ctx · 8K out
xiaomi

MiMo-V2.6-Pro

xiaomi · mimo-pro

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

TextImageAudioVideo→Text
1.0M ctx · 131K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 7.811/1M•Output Rp 15.802/1M
🏷️ Termurah: Kilo Gateway
xiaomi

MiMo-V2-Omni

xiaomi · mimo-omni

MiMo omni model for text, image, video, audio, and agents

TextImageAudioVideoPDF→Text
262K ctx · 131K outReasoningToolsAttachments
xiaomi

MiMo-V2.6-Flash

xiaomi · mimo-flash

MiMo Flash model for multimodal coding agents and long-context automation

TextImageAudioVideo→Text
1.0M ctx · 131K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 2.289/1M•Output Rp 4.578/1M
🏷️ Termurah: Pareto Inference
xiaomi

MiMo-V2.5

xiaomi · mimo

Open MiMo model for multimodal coding agents and long-context automation

TextImageAudioVideo→Text
1.0M ctx · 131K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 2.543/1M•Output Rp 5.086/1M
🏷️ Termurah: Impossibl
xiaomi

MiMo-V2-Pro

xiaomi · mimo-pro

Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks

Text→Text
1.0M ctx · 131K outReasoningTools
xiaomi

MiMo-V2-Flash

xiaomi · mimo-flash

MiMo flash model for fast multimodal assistance and agent workflows

Text→Text
262K ctx · 66K outReasoningToolsOpen
xiaomi

MiMo-V2.5-Pro

xiaomi · mimo-pro

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

Text→Text
1.0M ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 7.901/1M•Output Rp 15.802/1M
🏷️ Termurah: Standard Compute
abacusai

Dracarys Llama 3.1 70B Instruct

abacusai · dracarys

Abacus.AI coding fine-tune of Llama 3.1 70B Instruct

Text→Text
131K ctx · 131K outOpen
anthracite-org

Magnum v4 72B

anthracite-org · magnum

Open-weight instruction model for adaptable chat and self-hosted production workloads

Text→Text
33K ctx · 4K outOpen
💰Harga:
Input Rp 45.408/1M•Output Rp 90.816/1M
🏷️ Termurah: Kilo Gateway
perplexity

Sonar Reasoning Pro

perplexity · sonar-reasoning-pro

Web-grounded Sonar for multi-step research questions that need cited reasoning

TextImage→Text
128K ctx · 4K outReasoningAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 145.305/1M
🏷️ Termurah: Kilo Gateway
perplexity

Sonar Deep Research

perplexity · sonar-deep-research

Sonar search model for autonomous research and citation-backed long-form reports

Text→Text
128K ctx · 33K outReasoning
💰Harga:
Input Rp 36.327/1M•Output Rp 145.305/1M
🏷️ Termurah: LLMTR
perplexity

Sonar

perplexity · sonar

Fast web-grounded Sonar for current answers, citations, and lightweight retrieval

Text→Text
128K ctx · 4K out
💰Harga:
Input Rp 18.164/1M•Output Rp 18.164/1M
🏷️ Termurah: AI/ML API
perplexity

Sonar Pro

perplexity · sonar-pro

Deeper Sonar search model with broader retrieval and stronger synthesis

TextImage→Text
200K ctx · 8K outAttachments
💰Harga:
Input Rp 54.490/1M•Output Rp 272.446/1M
🏷️ Termurah: AI/ML API
gryphe

MythoMax L2 13B

gryphe · mythomax

Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay

Text→Text
4K ctx · 3K outOpen
💰Harga:
Input Rp 1.635/1M•Output Rp 1.635/1M
🏷️ Termurah: Novita AI
arcee-ai

Trinity Large Thinking

arcee-ai · trinity-large

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

Text→Text
524K ctx · 262K outReasoningToolsOpen
arcee-ai

Trinity Nano Preview

arcee-ai · trinity-nano

Experimental chat-tuned 6B MoE model with 1B active parameters for low-resource chat and instruction following

Text→Text
131K ctx · 131K outToolsOpen
arcee-ai

Trinity Mini

arcee-ai · trinity-mini

Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads

Text→Text
131K ctx · 131K outReasoningToolsOpen
arcee-ai

Trinity Large Preview

arcee-ai · trinity-large

Lightly post-trained 398B MoE chat model for creative work, long-context prompts, and tool-using agents

Text→Text
524K ctx · 262K outToolsOpen
inception

Mercury Edit 2

inception · mercury-edit

Code editing dLLM for autocomplete (FIM) and next-edit suggestions

Text→Text
32K ctx · 8K out
inception

Mercury 2.5

inception · mercury

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Text→Text
260K ctx · 66K outReasoningTools
inception

Mercury 2

inception · mercury

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Text→Text
128K ctx · 50K outReasoningTools
inception

Mercury 3

inception · mercury

Inception's diffusion reasoning model for chat, multi-step problem solving, and tool use

Text→Text
1M ctx · 131K outReasoningTools
💰Harga:
Input Rp 1.817/1M•Output Rp 6.358/1M
🏷️ Termurah: NanoGPT
apodex

Apodex 1.1 Mini

apodex · apodex-mini

Open-weight 35B MoE model for long-horizon research, forecasting, and tool-assisted work

Text→Text
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Novita AI
inclusionai

Ling 3.0 Tiny

inclusionai · ling-tiny

Lightweight hybrid-linear MoE reasoning model with 7.9B total and 1.3B active parameters for on-device deployment and offline agents

Text→Text
131K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Rp 273/1M•Output Rp 818/1M
🏷️ Termurah: NanoGPT
inclusionai

Ling 3.0 Flash VL

inclusionai · ling-flash

Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents

TextImageVideo→Text
262K ctx · 33K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 1.090/1M•Output Rp 3.270/1M
🏷️ Termurah: NanoGPT
inclusionai

Ling 3.2 Flash

inclusionai · ling-flash

Native multimodal MoE model with 560B total and 25B active parameters for complex visual understanding, multimodal agents, 3D interaction, and medical imaging

TextImageVideo→Text
1M ctx · 33K outReasoningToolsAttachments
inclusionai

Ling 3.0 Flash

inclusionai · ling-flash

Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents

Text→Text
262K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Rp 382/1M•Output Rp 1.145/1M
🏷️ Termurah: OpenRouter
inclusionai

Ling 3.1 Flash

inclusionai · ling-flash

Efficient model for low-latency assistance, extraction, and routine automation

Text→Text
262K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Rp 1.090/1M•Output Rp 3.270/1M
🏷️ Termurah: OpenRouter
inclusionai

Ling 3.0 Flash Sante

inclusionai · ling-flash

Health and medicine specialization of Ling 3.0 Flash for medical reasoning and evidence-based retrieval

Text→Text
262K ctx · 33K outReasoningTools
💰Harga:
Input Rp 1.363/1M•Output Rp 3.996/1M
🏷️ Termurah: Novita AI
inclusionai

Ling 3.0 Flash Fin

inclusionai · ling-flash

Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution

Text→Text
262K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Rp 1.363/1M•Output Rp 3.996/1M
🏷️ Termurah: Novita AI
perceptron

Perceptron Mk1.5

perceptron · perceptron-mk

Image, video, and audio understanding with visual grounding, reasoning, and function calling

TextImageVideoAudio→Text
37K ctx · 8K outReasoningToolsAttachments
💰Harga:
Input Rp 2.725/1M•Output Rp 27.245/1M
🏷️ Termurah: NanoGPT
perceptron

Perceptron Mk1

perceptron · perceptron-mk

Multimodal reasoning model for visual analysis, planning, and tool use

TextImageVideo→Text
33K ctx · 8K outReasoningAttachments
💰Harga:
Input Rp 2.725/1M•Output Rp 27.245/1M
🏷️ Termurah: NanoGPT
nousresearch

Hermes 3 70B Instruct

nousresearch · hermes

Open Llama instruction model for multilingual chat, reasoning, and coding

Text→Text
131K ctx · 16K outOpen
nousresearch

Hermes 2 Pro Llama 3 8B

nousresearch · hermes

Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue

Text→Text
8K ctx · 8K outToolsOpen
💰Harga:
Input Rp 2.543/1M•Output Rp 2.543/1M
🏷️ Termurah: Novita AI
nousresearch

Hermes 3 405B Instruct

nousresearch · hermes

Open Llama instruction model for multilingual chat, reasoning, and coding

Text→Text
131K ctx · 16K outOpen
nousresearch

Hermes 4 405B

nousresearch · hermes

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Text→Text
131K ctx · 118K outReasoningToolsOpen
💰Harga:
Input Rp 18.164/1M•Output Rp 54.490/1M
🏷️ Termurah: Kilo Gateway
fireworks

Ember-1

fireworks · ember

Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality

TextImage→Text
1.0M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 54.490/1M•Output Rp 272.446/1M
🏷️ Termurah: NanoGPT
nvidia

Nemotron 3.5 Content Safety

nvidia · nemotron-safety

Safety model for policy screening, moderation, and risk-aware routing workflows

TextImage→Text
128K ctx · 8K outReasoningAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron Nano 12B v2 VL

nvidia · nemotron-nano

Nemotron multimodal model for visual reasoning and agentic AI workflows

TextImageVideo→Text
128K ctx · 128K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 3.633/1M•Output Rp 10.898/1M
🏷️ Termurah: Kilo Gateway
nvidia

Nemotron 3 Nano 30B A3B

nvidia · nemotron-nano

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Text→Text
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Rp 909/1M•Output Rp 3.633/1M
🏷️ Termurah: NanoGPT
nvidia

Nemotron 3 Super 120B A12B

nvidia · nemotron-super

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

Text→Text
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Rp 909/1M•Output Rp 4.541/1M
🏷️ Termurah: NanoGPT
nvidia

Nemotron Content Safety Reasoning 4B

nvidia · nemotron-safety

Safety model for policy screening, moderation, and risk-aware routing workflows

Text→Text
128K ctx · 4K outReasoningOpen
nvidia

Nemotron 3 Ultra 550B A55B

nvidia · nemotron-ultra

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Text→Text
1M ctx · 128K outReasoningToolsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: InferAll
nvidia

Llama 3.1 Nemotron 70B Instruct

nvidia · nemotron

Nemotron model for efficient reasoning, coding, and specialized AI agents

Text→Text
128K ctx · 8K outToolsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron 3.5 Lightning 30B A3B

nvidia · nemotron-lightning

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

Text→Text
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Rp 364/1M•Output Rp 1.744/1M
🏷️ Termurah: Kilo Gateway
nvidia

Llama Nemotron Embed 1B v2

nvidia · nemotron-embed

Multilingual text embedding model for retrieval and question answering pipelines

Text→Text
8K ctx · 2K outOpen
nvidia

Llama 3.3 Nemotron Super 49B v1

nvidia · nemotron-super

Nemotron model for efficient reasoning, coding, and specialized AI agents

Text→Text
131K ctx · 131K outReasoningToolsOpen
nvidia

Nemotron VoiceChat

nvidia · nemotron-voice

Nemotron multimodal model for visual reasoning and agentic AI workflows

TextAudio→Text
128K ctx · 8K outToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron Nano 9B v2

nvidia · nemotron-nano

Compact Nemotron model for efficient reasoning and deployable AI agents

Text→Text
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 1.090/1M•Output Rp 4.178/1M
🏷️ Termurah: Kilo Gateway
nvidia

Llama Nemotron Embed VL 1B v2

nvidia · nemotron-embed

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

TextImage→Text
10K ctx · 2K outAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Llama 3.1 Nemotron Safety Guard 8B v3

nvidia · nemotron-safety

Safety model for policy screening, moderation, and risk-aware routing workflows

Text→Text
128K ctx · 4K outOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron 3.5 Super 120B A12B

nvidia · nemotron-super

NVIDIA Nemotron 3.5 Super reasoning model (120B total, 12B active) served with text-only input

Text→Text
1.0M ctx · 131K outReasoningToolsOpen
nvidia

Llama 3.1 Nemotron Ultra 253B

nvidia · nemotron-ultra

Flagship Nemotron model for high-throughput reasoning and complex agents

Text→Text
128K ctx · 8K outReasoningToolsOpen
nvidia

Nemotron Cascade 2 30B A3B

nvidia · nemotron-cascade

Nemotron model for efficient reasoning, coding, and specialized AI agents

Text→Text
256K ctx · 33K outReasoningToolsOpen
nvidia

Llama 3.3 Nemotron Super 49B v1.5

nvidia · nemotron-super

Nemotron model for efficient reasoning, coding, and specialized AI agents

Text→Text
131K ctx · 131K outReasoningToolsOpen
nvidia

Nemotron 3.5 Super VL 120B A12B

nvidia · nemotron-super

NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use

TextImageVideo→Text
1.0M ctx · 8K outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: InferAll
nvidia

Llama Nemotron Rerank VL 1B v2

nvidia · nemotron-rerank

Reranking model for improving retrieval quality in search and recommendation systems

TextImage→Text
10K ctx · 4K outAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron 3 Nano Omni 30B A3B Reasoning

nvidia · nemotron-nano

Open Nemotron omni model combining reasoning with text, vision, and audio

TextImageVideoAudio→Text
256K ctx · 66K outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Mistral Nemotron

nvidia · nemotron

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Text→Text
128K ctx · 8K outTools
nvidia

Nemotron Mini 4B Instruct

nvidia · nemotron-mini

Compact Nemotron model for efficient reasoning and deployable AI agents

Text→Text
128K ctx · 8K outToolsOpen
nvidia

Nemotron 3 Content Safety

nvidia · nemotron-safety

Safety model for policy screening, moderation, and risk-aware routing workflows

Text→Text
128K ctx · 4K outOpen
morph

Morph V3 Fast

morph · morph-fast

Efficient model for low-latency assistance, extraction, and routine automation

Text→Text
262K ctx · 131K out
💰Harga:
Input Rp 14.531/1M•Output Rp 21.796/1M
🏷️ Termurah: Kilo Gateway
morph

Morph V3 Large

morph · morph-large

Flagship model for demanding analysis, coding, and production agent workflows

Text→Text
262K ctx · 131K out
💰Harga:
Input Rp 16.347/1M•Output Rp 34.510/1M
🏷️ Termurah: Kilo Gateway
sao10k

Llama 3 8B Lunaris

sao10k · lunaris

Open Llama instruction model for multilingual chat, reasoning, and coding

Text→Text
8K ctx · 7K outOpen
💰Harga:
Input Rp 727/1M•Output Rp 909/1M
🏷️ Termurah: Kilo Gateway
sao10k

Llama 3.1 Euryale 70B v2.2

sao10k · euryale

Open Llama instruction model for multilingual chat, reasoning, and coding

Text→Text
131K ctx · 16K outToolsOpen
💰Harga:
Input Rp 12.351/1M•Output Rp 12.351/1M
🏷️ Termurah: Kilo Gateway
sao10k

Llama 3.3 Euryale 70B

sao10k · euryale

Open Llama instruction model for multilingual chat, reasoning, and coding

Text→Text
131K ctx · 16K outOpen
meituan

LongCat-2.0

meituan · longcat

Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window

Text→Text
1M ctx · 131K outReasoningToolsOpen
meituan

LongCat-2.5-Preview

meituan · longcat

Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window

TextImage→Text
1M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 14.304/1M•Output Rp 56.260/1M
🏷️ Termurah: NanoGPT
meituan

LongCat-2.5

meituan · longcat

Meituan's multimodal reasoning model for long-horizon coding and agent tasks, with visual understanding and a 1M-token context window

TextImage→Text
1M ctx · 262K outReasoningToolsAttachments
💰Harga:
Input Rp 5.449/1M•Output Rp 21.796/1M
🏷️ Termurah: Kilo Gateway
particle-ai

Particle-1

particle-ai · particle

Token-efficient agentic coding model post-trained on DeepSeek V4.1 Flash to finish software engineering tasks with fewer reasoning and tool-call tokens

TextImage→Text
1.0M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 636/1M•Output Rp 4.541/1M
🏷️ Termurah: Kilo Gateway
mixedbread

Toast 1

mixedbread · toast

Specialized search model for knowledge-intensive questions, multi-step retrieval, and evidence synthesis

Text→Text
131K ctx · 4K outTools
💰Harga:
Input Rp 5.449/1M•Output Rp 13.078/1M
🏷️ Termurah: Kilo Gateway
upstage

SOLAR 10.7B Instruct v1.0

upstage · solar

Upstage depth-upscaled 10.7B instruction model for single-turn chat

Text→Text
4K ctx · 4K outOpen
upstage

Solar Pro 3

upstage · solar-pro

Flagship model for demanding analysis, coding, and production agent workflows

Text→Text
131K ctx · 8K outReasoningTools
💰Harga:
Input Rp 2.725/1M•Output Rp 10.898/1M
🏷️ Termurah: LLMTR
upstage

Solar Pro 2

upstage · solar-pro

Flagship model for demanding analysis, coding, and production agent workflows

Text→Text
66K ctx · 8K outReasoningTools
💰Harga:
Input Rp 2.725/1M•Output Rp 10.898/1M
🏷️ Termurah: LLMTR
upstage

Solar Mini 4

upstage · solar-mini

Upstage's compact, cost-efficient model for agentic use

Text→Text
524K ctx · 131K outReasoningTools
💰Harga:
Input Rp 909/1M•Output Rp 3.633/1M
🏷️ Termurah: NanoGPT
upstage

Solar Pro 4

upstage · solar-pro

Upstage's flagship model, specialized for agentic use

Text→Text
524K ctx · 131K outReasoningTools
💰Harga:
Input Rp 2.725/1M•Output Rp 10.898/1M
🏷️ Termurah: NanoGPT
essentialai

Rnj-1 Instruct

essentialai · rnj

Open 8B Essential AI model for code, STEM reasoning, and agentic tool use

Text→Text
33K ctx · 33K outToolsOpen
thinkingmachines

Inkling Small

thinkingmachines · inkling-small

Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio

TextImageAudio→Text
1.0M ctx · 1.0M outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 8.174/1M•Output Rp 21.796/1M
🏷️ Termurah: Kilo Gateway
thinkingmachines

Inkling

thinkingmachines · inkling

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

TextImageAudio→Text
1.0M ctx · 1.0M outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 18.164/1M•Output Rp 73.561/1M
🏷️ Termurah: NanoGPT
thinkingmachines

Inkling 2 Small

thinkingmachines · inkling-small

Multimodal MoE reasoning model (594B total, 17B active) for agentic coding, vision, and knowledge work

TextImage→Text
1.0M ctx · 131K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 2.725/1M•Output Rp 9.082/1M
🏷️ Termurah: Prime Inference
bytedance-seed

Seed 1.6 Vision

bytedance-seed · seed

ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks

TextImage→Text
256K ctx · 32K outToolsAttachments
bytedance-seed

Seed Evolving

bytedance-seed · seed

Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities

TextImageVideo→Text
1.0M ctx · 256K outReasoningToolsAttachments
bytedance-seed

Seed 1.6

bytedance-seed · seed

ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks

TextImageVideo→Text
256K ctx · 64K outReasoningToolsAttachments
bytedance-seed

Seed 2.1 Pro

bytedance-seed · seed-pro

Flagship ByteDance Seed 2.1 model for complex multimodal reasoning, coding, and agents

TextImageVideo→Text
1.0M ctx · 256K outReasoningToolsAttachments
bytedance-seed

Seed 2.0 Pro

bytedance-seed · seed-pro

Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows

TextImageVideo→Text
256K ctx · 128K outReasoningToolsAttachments
bytedance-seed

Seed 2.1 Lite

bytedance-seed · seed-lite

Omnimodal ByteDance Seed 2.1 model with native text, vision, and audio understanding, 1M context, and improved coding and agent task completion

TextImageAudioVideo→Text
1.0M ctx · 256K outReasoningToolsAttachments
bytedance-seed

Seed 1.6 Flash

bytedance-seed · seed-flash

Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use

TextImageVideo→Text
256K ctx · 32K outToolsAttachments
bytedance-seed

Seed 2.0 Lite

bytedance-seed · seed-lite

Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation

TextImageVideo→Text
256K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Rp 4.541/1M•Output Rp 36.327/1M
🏷️ Termurah: NanoGPT
bytedance-seed

Seedance 2.0

bytedance-seed · seedance

ByteDance unified multimodal audio-video model supporting text, image, video and audio references, editing, extension and synchronized stereo sound.

TextImageVideoAudio→VideoAudio
0 ctx · 0 outAttachments
bytedance-seed

Seed 2.0 Mini

bytedance-seed · seed-mini

Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks

TextImageVideo→Text
256K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Rp 1.817/1M•Output Rp 7.266/1M
🏷️ Termurah: Kilo Gateway
bytedance-seed

Seed 2.0 Code

bytedance-seed · seed-code

ByteDance Seed coding model for multimodal software engineering and long-running agents

TextImageVideo→Text
262K ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 9.082/1M•Output Rp 54.490/1M
🏷️ Termurah: NanoGPT
bytedance-seed

Seedance 2.5

bytedance-seed · seedance

ByteDance multimodal audio-video model with up to 30-second single-pass generation, multi-round extension, reference inputs and timestamp-level editing.

TextImageVideoAudio→VideoAudio
0 ctx · 0 outAttachments
bytedance-seed

Seed Character

bytedance-seed · seed

ByteDance Seed model optimized for character-driven dialogue and consistent conversational behavior

TextImageVideo→Text
256K ctx · 256K outReasoningToolsAttachments
bytedance-seed

Seed 1.8

bytedance-seed · seed

ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows

TextImage→Text
256K ctx · 64K outReasoningToolsAttachments
bytedance-seed

Seed-OSS-36B-Instruct

bytedance-seed · seed-oss

Open ByteDance Seed model for long-context reasoning, tool use, and agents

Text→Text
524K ctx · 524K outReasoningToolsOpen
bytedance-seed

Seed 2.1 Turbo

bytedance-seed · seed-turbo

Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows

TextImageVideo→Text
256K ctx · 256K outReasoningToolsAttachments
motif-technologies

Motif 3

motif-technologies · motif

Motif 3 is a large-scale, decoder-only Mixture-of-Experts (MoE) language model with 314 billion total parameters and 13.2 billion parameters activated per token.

Text→Text
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 21.796/1M
🏷️ Termurah: Kilo Gateway
lightonai

LightOnOCR 2 1B

lightonai · lightonocr

End-to-end 1B-parameter vision-language OCR model from the French company LightOn that converts documents (PDFs, scans, images) into clean, naturally ordered text without a brittle OCR pipeline

TextImage→Text
16K ctx · undefined outAttachmentsOpen
lightonai

LightOnOCR-3 0.8B

lightonai · lightonocr

LightOnOCR-3-0.8B is the lightest model of LightOn's LightOnOCR-3 family, with the same layout and visual understanding features as its larger siblings.

TextImage→Text
262K ctx · 16K outAttachmentsOpen
mancer

Weaver (alpha)

mancer · weaver

General-purpose chat model for instruction following, writing, and analysis

Text→Text
8K ctx · 6K out
💰Harga:
Input Rp 5.449/1M•Output Rp 9.082/1M
🏷️ Termurah: Kilo Gateway
google

Gemma 4 31B IT

google · gemma

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

TextImage→Text
262K ctx · 33K outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
google

Nano Banana 2.1

google · nano-banana

Image model for prompt-driven generation, multi-turn editing, and visual design workflows

TextImageVideo→TextImage
131K ctx · 33K outReasoningAttachments
💰Harga:
Input Rp 27.245/1M•Output Rp 136.223/1M
🏷️ Termurah: Eden AI
google

Gemini 3 Flash Preview

google · gemini-flash

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 4.541/1M•Output Rp 27.245/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 4 Carbon

google · gemini

Google's most capable reasoning model for complex software engineering, deep math and science, high factual accuracy, and long-horizon autonomous agents

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 181.631/1M
🏷️ Termurah: NanoGPT
google

Gemma 2 2B IT

google · gemma

Small open Gemma 2 instruction model for lightweight chat and on-device use

Text→Text
8K ctx · 8K outOpen
google

Gemini Omni Flash Preview

google · gemini-omni-flash

Video generation and editing model for fast, conversational text- and image-to-video workflows

TextImageVideo→Video
1.0M ctx · 58K outReasoningAttachments
💰Harga:
Input Rp 27.245/1M•Output Rp 163.468/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 3.1 Flash Lite

google · gemini-flash-lite

Low-latency Gemini model for high-volume multimodal and agent workloads

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 4.541/1M•Output Rp 27.245/1M
🏷️ Termurah: NanoGPT
google

Gemini Robotics-ER 1.6 Preview

google · gemini-robotics-er

Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics

TextImageVideoAudio→Text
131K ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 18.164/1M•Output Rp 90.816/1M
🏷️ Termurah: OrcaRouter
google

Gemini 2.5 Flash

google · gemini-flash

Fast Gemini workhorse for multimodal apps where latency and price matter

TextImageAudioVideoPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 3.815/1M•Output Rp 32.694/1M
🏷️ Termurah: Poe
google

Deep Research Max Preview

google · gemini-deep-research-max

Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports

TextImageVideoAudioPDF→TextImage
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 217.957/1M
🏷️ Termurah: Eden AI
google

Gemini 3.6 Flash

google · gemini-flash

Fast Gemini model balancing multimodal reasoning, tool use, and cost

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 6.812/1M•Output Rp 34.056/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 3.7 Flash

google · gemini-flash

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 13.623/1M•Output Rp 68.112/1M
🏷️ Termurah: NanoGPT
google

Veo 3.1 Lite Preview

google · veo-lite

Video model for prompt-guided generation, editing, and motion workflows

TextImage→Video
1K ctx · 0 outAttachments
google

Gemini 4 Hydrogen

google · gemini

Google's Gemini 4 model for everyday coding and agentic workflows, with four thinking levels and a 1M-token context window

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 27.245/1M•Output Rp 136.223/1M
🏷️ Termurah: NanoGPT
google

Lyria 3 Clip Preview

google · lyria-clip

Music generation model for short 30-second clips, loops, and previews from text or image prompts

TextImage→TextAudio
131K ctx · 66K outAttachments
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Kilo Gateway
google

Nano Banana 2 Lite

google · nano-banana-lite

Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing

TextImage→TextImage
66K ctx · 4K outReasoningToolsAttachments
💰Harga:
Input Rp 4.541/1M•Output Rp 27.245/1M
🏷️ Termurah: Eden AI
google

Lyria 3 Pro Preview

google · lyria-pro

Music generation model for full-length songs from text or images with vocals and structure

TextImage→TextAudio
131K ctx · 8K outAttachments
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Kilo Gateway
google

Gemini Embedding 2

google · gemini-embedding

Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space

TextImageAudioVideoPDF→Text
8K ctx · 3K outAttachments
💰Harga:
Input Rp 3.633/1M•Output Gratis/1M
🏷️ Termurah: Merge Gateway
google

DiffusionGemma 26B A4B IT

google · gemma-diffusion

Gemma 4 based discrete text diffusion model for fast chat, reasoning, and tool use

TextImage→Text
262K ctx · 33K outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
google

Gemma 2 27B

google · gemma

Open Gemma instruction model for efficient chat and self-hosted deployments

Text→Text
8K ctx · 2K outOpen
💰Harga:
Input Rp 11.806/1M•Output Rp 11.806/1M
🏷️ Termurah: Kilo Gateway
google

Nano Banana 2

google · nano-banana

Image model for prompt-driven generation, editing, and visual design workflows

TextImageVideoPDF→TextImage
131K ctx · 33K outReasoningAttachments
💰Harga:
Input Rp 9.082/1M•Output Rp 54.490/1M
🏷️ Termurah: Eden AI
google

Gemini 2.5 Flash Preview 05-20

google · gemini-flash

Preview snapshot of Gemini 2.5 Flash with controllable thinking budgets

TextImageAudioVideoPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
google

Gemma 4 26B A4B IT

google · gemma

Open Gemma instruction model for efficient chat and self-hosted deployments

TextImage→Text
262K ctx · 33K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 643/1M•Output Rp 1.713/1M
🏷️ Termurah: NanoGPT
google

Gemini 3.5 Flash Lite

google · gemini-flash-lite

Fast Gemini model balancing multimodal reasoning, tool use, and cost

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 5.449/1M•Output Rp 45.408/1M
🏷️ Termurah: NanoGPT
google

Gemini 3.1 Flash TTS Preview

google · gemini-tts-flash

Low-latency speech generation with steerable prompts and expressive audio tags

Text→Audio
8K ctx · 16K out
google

Veo 3.1 Fast Preview

google · veo

Video model for prompt-guided generation, editing, and motion workflows

TextImageVideo→Video
1K ctx · 0 outAttachments
google

Nano Banana

google · nano-banana

Nano Banana image model for fast generation, edits, and character-consistent assets

TextImage→TextImage
33K ctx · 33K outAttachments
💰Harga:
Input Rp 5.449/1M•Output Rp 45.408/1M
🏷️ Termurah: Eden AI
google

Gemini 2.5 Flash TTS

google · gemini-tts-flash

Speech generation model for controllable voice, narration, and audio delivery

Text→Audio
33K ctx · 16K out
google

Gemini 3.5 Flash

google · gemini-flash

Fast Gemini model balancing multimodal reasoning, tool use, and cost

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 27.245/1M•Output Rp 163.468/1M
🏷️ Termurah: NanoGPT
google

Gemma 4 E2B IT

google · gemma

Open Gemma instruction model for efficient chat and self-hosted deployments

TextImageAudio→Text
131K ctx · 8K outReasoningToolsAttachmentsOpen
google

Gemini Omni 1.1 Flash

google · gemini-omni-flash

Video generation and editing model for scene extension, frame interpolation, and reference-guided multimodal control

TextImageVideo→Video
1.0M ctx · 58K outReasoningAttachments
💰Harga:
Input Rp 27.245/1M•Output Rp 163.468/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 2.5 Pro

google · gemini-pro

Google's proven reasoning model for coding, math, and multimodal analysis

TextImageAudioVideoPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 15.802/1M•Output Rp 127.142/1M
🏷️ Termurah: Poe
google

Gemini 2.5 Flash-Lite Preview 06-17

google · gemini-flash-lite

First preview of Gemini 2.5 Flash-Lite, the low-cost, low-latency 2.5 model

TextImageAudioVideoPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
google

Gemini 3.1 Flash Lite Preview

google · gemini-flash-lite

Low-latency Gemini model for high-volume multimodal and agent workloads

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 2.271/1M•Output Rp 13.623/1M
🏷️ Termurah: Kilo Gateway
google

Nano Banana Pro

google · nano-banana-pro

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

TextImage→TextImage
66K ctx · 33K outReasoningAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 217.957/1M
🏷️ Termurah: Eden AI
google

Gemini 3.1 Flash Live Preview

google · gemini-live

High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications

TextImageVideoAudio→TextAudio
131K ctx · 66K outReasoningToolsAttachments
google

Gemini 2.5 Pro TTS

google · gemini-tts-pro

Speech generation model for controllable voice, narration, and audio delivery

Text→Audio
33K ctx · 16K out
google

Gemini 2.0 Flash-Lite

google · gemini-flash-lite

Low-latency Gemini model for high-volume multimodal and agent workloads

TextImageAudioVideoPDF→Text
1.0M ctx · 8K outToolsAttachments
💰Harga:
Input Rp 945/1M•Output Rp 3.815/1M
🏷️ Termurah: Poe
google

Gemini 3.5 Transcribe Live

google · gemini-transcribe

Speech transcription model for accurate audio-to-text and captioning workflows

Audio→Text
0 ctx · 0 outAttachments
google

Gemini Embedding 001

google · gemini-embedding

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Text→Text
2K ctx · 1 out
💰Harga:
Input Rp 2.725/1M•Output Gratis/1M
🏷️ Termurah: Merge Gateway
google

Gemini 4 Argon

google · gemini

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 181.631/1M
🏷️ Termurah: NanoGPT
google

Gemini 2.5 Flash-Lite

google · gemini-flash-lite

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

TextImageAudioVideoPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 1.817/1M•Output Rp 1.817/1M
🏷️ Termurah: LLMTR
google

Gemini 3.1 Pro Preview

google · gemini-pro

Reasoning-first Gemini preview for agentic coding and complex problem solving

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 217.957/1M
🏷️ Termurah: NanoGPT
google

Gemma 3n E2B IT

google · gemma

Efficient on-device Gemma 3n model for text, image, and audio understanding

TextImageAudio→Text
33K ctx · 33K outAttachmentsOpen
google

Gemma 4 E4B IT

google · gemma

Open Gemma instruction model for efficient chat and self-hosted deployments

TextImageAudio→Text
131K ctx · 8K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 364/1M•Output Rp 1.817/1M
🏷️ Termurah: Deep Infra
google

Gemma 4 12B IT

google · gemma

Compact Gemma 4 instruction model for open, self-hosted chat and reasoning

TextImage→Text
262K ctx · 33K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 818/1M•Output Rp 4.178/1M
🏷️ Termurah: Kitani
google

Gemma 3n E4B IT

google · gemma

Efficient on-device Gemma 3n model for text, image, and audio understanding

TextImageAudio→Text
33K ctx · 33K outAttachmentsOpen
google

Gemini 3.1 Pro Preview Custom Tools

google · gemini-pro

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 217.957/1M
🏷️ Termurah: NanoGPT
google

Gemini Flash-Lite Latest

google · gemini-flash-lite

Fast Gemini model balancing multimodal reasoning, tool use, and cost

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 4.541/1M•Output Rp 27.245/1M
🏷️ Termurah: OrcaRouter
google

Gemini 3.8 Flash

google · gemini-flash

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 13.623/1M•Output Rp 68.112/1M
🏷️ Termurah: NanoGPT
google

Gemini Flash Latest

google · gemini-flash

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 9.082/1M•Output Rp 54.490/1M
🏷️ Termurah: OrcaRouter
google

Gemini 2.0 Flash

google · gemini-flash

Earlier Gemini Flash workhorse for responsive multimodal apps and tool use

TextImageAudioVideoPDF→Text
1.0M ctx · 8K outToolsAttachments
💰Harga:
Input Rp 1.817/1M•Output Rp 7.629/1M
🏷️ Termurah: Poe
google

Gemini 2.5 Flash-Lite Preview 09-2025

google · gemini-flash-lite

September 2025 preview of Gemini 2.5 Flash-Lite with better instruction following and multimodal quality

TextImageAudioVideoPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
google

Gemini 3.5 Live Translate Preview

google · gemini-live-translate

Low-latency audio-to-audio model for real-time speech translation across 70+ languages

Audio→AudioText
131K ctx · 66K outAttachments
google

Gemini 2.5 Computer Use Preview

google · gemini-computer-use

Specialized Gemini 2.5 model for browser-control agents that automate UI tasks

TextImage→Text
128K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 181.631/1M
🏷️ Termurah: Merge Gateway
google

Gemma 3 4B IT

google · gemma

Open multimodal Gemma instruction model for efficient text generation and image understanding

TextImage→Text
131K ctx · 131K outToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
google

Gemini 2.5 Pro Preview 06-05

google · gemini-pro

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

PDFImageTextAudio→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 11.352/1M•Output Rp 90.816/1M
🏷️ Termurah: Kilo Gateway
google

Nano Banana 2 Preview

google · nano-banana

Image model for prompt-driven generation, editing, and visual design workflows

TextImagePDF→TextImage
66K ctx · 66K outReasoningAttachments
💰Harga:
Input Rp 9.082/1M•Output Rp 54.490/1M
🏷️ Termurah: Eden AI
google

Gemini Deep Research Preview

google · gemini-deep-research

Agentic model for autonomous multi-step research, synthesis, and cited reports

TextImageVideoAudioPDF→TextImage
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 217.957/1M
🏷️ Termurah: Eden AI
google

Gemini 3 Pro Preview

google · gemini-pro

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
google

Nano Banana Pro Preview

google · nano-banana-pro

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

TextImage→TextImage
66K ctx · 33K outReasoningAttachments
💰Harga:
Input Rp 18.164/1M•Output Rp 108.979/1M
🏷️ Termurah: Kilo Gateway
google

Gemma 3 12B IT

google · gemma

Open multimodal Gemma instruction model for multilingual text generation and image understanding

TextImage→Text
131K ctx · 131K outToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
google

Veo 3.1 Preview

google · veo

Video model for prompt-guided generation, editing, and motion workflows

TextImage→Video
1K ctx · 1 outAttachments
google

Gemini 4 Neon

google · gemini

Google's Gemini 4 model for fast, frontier-level coding, knowledge work and science workflows, with four thinking levels and a 1M-token context window

TextImageVideoAudioPDF→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 54.490/1M•Output Rp 272.446/1M
🏷️ Termurah: NanoGPT
google

Gemma 3 27B IT

google · gemma

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

TextImage→Text
131K ctx · 131K outToolsAttachmentsOpen
💰Harga:
Input Rp 1.163/1M•Output Rp 2.325/1M
🏷️ Termurah: Kilo Gateway
opendatalab

MinerU2.5 2509 1.2B

opendatalab · mineru

1.2B-parameter vision-language model from OpenDataLab for two-step document parsing: global layout analysis on downsampled images, then fine-grained text, formula, and table recognition at native resolution

TextImage→Text
16K ctx · undefined outAttachmentsOpen
rekaai

Reka Flash 3

rekaai · reka

Efficient model for low-latency assistance, extraction, and routine automation

Text→Text
66K ctx · 59K outReasoningOpen
💰Harga:
Input Rp 1.817/1M•Output Rp 3.633/1M
🏷️ Termurah: Kilo Gateway
rekaai

Reka Edge

rekaai · reka

Multimodal model for analyzing text, images, documents, and rich media

ImageTextVideo→Text
16K ctx · 15K outToolsAttachmentsOpen
💰Harga:
Input Rp 1.817/1M•Output Rp 1.817/1M
🏷️ Termurah: Kilo Gateway
vispark

Vision Medium

vispark · vispark-vision-medium

Balanced multimodal model pairing a 1M-token context window with deeper reasoning for analysis, content creation, and tool use across text, image, audio, video, and PDF inputs.

TextImageAudioVideoPDF→Text
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 76.467/1M•Output Rp 229.399/1M
🏷️ Termurah: Vispark
vispark

Vision Small

vispark · vispark-vision-small

Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.

TextImageAudioVideoPDF→Text
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 19.072/1M•Output Rp 57.396/1M
🏷️ Termurah: Vispark
vispark

Vision Large

vispark · vispark-vision-large

Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.

TextImageAudioVideoPDF→Text
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 133.862/1M•Output Rp 401.584/1M
🏷️ Termurah: Vispark
mindlab

Macaron V1 Tall

mindlab · macaron-tall

Qwen3.6-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI

TextImage→Text
262K ctx · 33K outReasoningToolsAttachmentsOpen
mindlab

Macaron V1 Venti

mindlab · macaron-venti

GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI

Text→Text
1.0M ctx · 131K outReasoningToolsOpen
baai

BGE M3

baai · bge

Multilingual embedding model combining dense, sparse, and multi-vector retrieval

Text→Text
8K ctx · 0 outOpen
💰Harga:
Input Rp 182/1M•Output Gratis/1M
🏷️ Termurah: Novita AI
baai

BGE Multilingual Gemma2

baai · bge

Multilingual Gemma 2 based embedding model for retrieval and semantic search

Text→Text
8K ctx · 0 outOpen
baai

BGE Reranker V2 M3

baai · bge-reranker

Lightweight multilingual cross-encoder that scores query-document relevance

Text→Text
8K ctx · 0 outOpen
💰Harga:
Input Rp 182/1M•Output Gratis/1M
🏷️ Termurah: Novita AI
baichuan

Baichuan M2 32B

baichuan · baichuan-m

Open medical model trained for clinical reasoning and patient interaction with on, off, and auto thinking modes

Text→Text
131K ctx · 131K outReasoningOpen
💰Harga:
Input Rp 1.272/1M•Output Rp 1.272/1M
🏷️ Termurah: Novita AI
reflection

Beam 1.0 501B A23B

reflection · beam

Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows

Text→Text
1.0M ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 4.541/1M•Output Rp 18.164/1M
🏷️ Termurah: Kilo Gateway
openai

GPT-6 Astra

openai · gpt-astra

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 145.305/1M•Output Rp 726.521/1M
🏷️ Termurah: IteraCompute
openai

GPT-5 Chat (latest)

openai · gpt

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

TextImage→Text
400K ctx · 128K outReasoningAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 181.631/1M
🏷️ Termurah: OrcaRouter
openai

o4-mini-deep-research

openai · o-deep-research-mini

Research model for long-horizon investigation, synthesis, and analytical reports

TextImage→Text
200K ctx · 100K outReasoningToolsAttachments
💰Harga:
Input Rp 32.694/1M•Output Rp 130.774/1M
🏷️ Termurah: Poe
openai

o3

openai · o

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

TextImagePDF→Text
200K ctx · 100K outReasoningToolsAttachments
💰Harga:
Input Rp 33.024/1M•Output Rp 132.095/1M
🏷️ Termurah: Poe
openai

GPT-4.1 mini

openai · gpt-mini

Affordable GPT-4.1 lane for fast coding help and structured extraction

TextImagePDF→Text
1.0M ctx · 33K outToolsAttachments
💰Harga:
Input Rp 6.605/1M•Output Rp 26.419/1M
🏷️ Termurah: Poe
openai

GPT-5 Nano

openai · gpt-nano

Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 827/1M•Output Rp 6.605/1M
🏷️ Termurah: Poe
openai

GPT-3.5-turbo

openai · gpt

Compact GPT model for low-latency assistance and high-volume workloads

Text→Text
16K ctx · 4K out
💰Harga:
Input Rp 8.174/1M•Output Rp 25.429/1M
🏷️ Termurah: Poe
openai

GPT-5.6 Terra

openai · gpt-terra

Balanced GPT-5.6 model for capable, cost-efficient everyday work

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 217.957/1M
🏷️ Termurah: NanoGPT
openai

GPT-5.1 Chat

openai · gpt

Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations

TextImage→Text
128K ctx · 16K outReasoningToolsAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 181.631/1M
🏷️ Termurah: OrcaRouter
openai

GPT Image 2.5 Flare

openai · gpt-image

Image model for prompt-driven generation, editing, and visual design workflows

TextImage→Image
0 ctx · 0 outAttachments
openai

GPT-5.6 Sol

openai · gpt-sol

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 45.408/1M•Output Rp 272.446/1M
🏷️ Termurah: Ofox
openai

GPT-5.2 Chat

openai · gpt

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

TextImage→Text
128K ctx · 16K outReasoningToolsAttachments
💰Harga:
Input Rp 31.786/1M•Output Rp 254.283/1M
🏷️ Termurah: OrcaRouter
openai

GPT-Image-1

openai · gpt-image

OpenAI image model for production generation, edits, and brand-safe visual workflows

TextImage→Image
0 ctx · 0 outAttachments
openai

GPT-6 Cyber

openai · gpt

Cybersecurity model for finding and validating exploitable vulnerabilities in authorized security research

TextImage→Text
1.1M ctx · 128K outReasoningToolsAttachments
openai

GPT-5 Mini

openai · gpt-mini

Small GPT-5 for responsive agents, coding help, and everyday automation

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 4.129/1M•Output Rp 33.024/1M
🏷️ Termurah: Poe
openai

GPT-6.1 Terra

openai · gpt-terra

Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 18.164/1M•Output Rp 90.816/1M
🏷️ Termurah: NanoGPT
openai

GPT-5-Codex

openai · gpt-codex

Coding-optimized GPT model for repository edits, reviews, and agentic software work

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 19.980/1M•Output Rp 163.468/1M
🏷️ Termurah: Poe
openai

GPT-5.4

openai · gpt

Agent-ready GPT for coding and computer-use workflows at a lower cost

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 41.280/1M•Output Rp 247.678/1M
🏷️ Termurah: Poe
openai

GPT-5 Image

openai · gpt-image

Image model for prompt-driven generation, editing, and visual design workflows

ImageTextPDF→ImageText
400K ctx · 128K outReasoningAttachments
💰Harga:
Input Rp 181.631/1M•Output Rp 181.631/1M
🏷️ Termurah: Kilo Gateway
openai

GPT OSS Safeguard 120B

openai · gpt-oss-safeguard

Safety model for policy screening, moderation, and risk-aware routing workflows

Text→Text
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 2.725/1M•Output Rp 10.898/1M
🏷️ Termurah: Kilo Gateway
openai

GPT-5

openai · gpt

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 20.641/1M•Output Rp 165.119/1M
🏷️ Termurah: Poe
openai

GPT-5.4 mini

openai · gpt-mini

Strong small GPT for coding subagents, quick tool use, and high-volume work

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 12.384/1M•Output Rp 74.304/1M
🏷️ Termurah: Poe
openai

GPT-5.3 Codex

openai · gpt-codex

Coding-optimized GPT model for repository edits, reviews, and agentic software work

TextImagePDF→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 28.896/1M•Output Rp 231.166/1M
🏷️ Termurah: Poe
openai

GPT-5.5

openai · gpt

Default frontier GPT for coding, computer use, research, and knowledge work

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 82.560/1M•Output Rp 495.355/1M
🏷️ Termurah: Poe
openai

GPT-4o (2024-08-06)

openai · gpt

GPT model for general reasoning, writing, coding, and tool-assisted tasks

TextImage→Text
128K ctx · 16K outToolsAttachments
💰Harga:
Input Rp 45.408/1M•Output Rp 181.631/1M
🏷️ Termurah: NanoGPT
openai

o1

openai · o

O-series reasoning model for hard analysis, math, coding, and planning

TextImagePDF→Text
200K ctx · 100K outReasoningToolsAttachments
💰Harga:
Input Rp 254.283/1M•Output Rp 980.803/1M
🏷️ Termurah: Poe
openai

GPT-6.1 Sol

openai · gpt-sol

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 29.061/1M•Output Rp 145.305/1M
🏷️ Termurah: IteraCompute
openai

GPT-5.3 Codex Spark

openai · gpt-codex-spark

Coding-optimized GPT model for repository edits, reviews, and agentic software work

TextImagePDF→Text
128K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Poe
openai

GPT-6 Luna

openai · gpt-luna

OpenAI's most efficient model for focused, high-volume tasks

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 1.454/1M•Output Rp 7.266/1M
🏷️ Termurah: IteraCompute
openai

GPT-6.2 Astra

openai · gpt-astra

A frontier reasoning model for coding, computer use, and professional work such as slides, spreadsheets, and documents.

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 145.305/1M•Output Rp 726.521/1M
🏷️ Termurah: NanoGPT
openai

GPT-4o

openai · gpt

Omni-era GPT for multimodal chat, practical coding, and general assistants

TextImagePDF→Text
128K ctx · 16K outToolsAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 90.816/1M
🏷️ Termurah: Cloudflare AI Gateway
openai

GPT-6 Astra (Fast)

openai · gpt-astra

Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 363.261/1M•Output Rp 1.816.301/1M
🏷️ Termurah: Kilo Gateway
openai

o3-pro

openai · o-pro

High-effort o3 tier for difficult technical reasoning and careful answers

TextImage→Text
200K ctx · 100K outReasoningToolsAttachments
💰Harga:
Input Rp 330.237/1M•Output Rp 1.320.947/1M
🏷️ Termurah: Poe
openai

GPT-4.1 nano

openai · gpt-nano

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

TextImage→Text
1.0M ctx · 33K outToolsAttachments
💰Harga:
Input Rp 1.635/1M•Output Rp 6.539/1M
🏷️ Termurah: Poe
openai

GPT-5.2 Pro

openai · gpt-pro

Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 346.749/1M•Output Rp 2.773.987/1M
🏷️ Termurah: Poe
openai

GPT-5.1 Codex Max

openai · gpt-codex

Coding-optimized GPT model for repository edits, reviews, and agentic software work

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 19.980/1M•Output Rp 163.468/1M
🏷️ Termurah: Poe
openai

GPT-5.5 Pro

openai · gpt-pro

Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 495.355/1M•Output Rp 2.972.129/1M
🏷️ Termurah: Poe
openai

GPT-5.4 nano

openai · gpt-nano

Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 3.303/1M•Output Rp 20.641/1M
🏷️ Termurah: Poe
openai

GPT OSS Safeguard 20B

openai · gpt-oss-safeguard

Safety model for policy screening, moderation, and risk-aware routing workflows

Text→Text
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 1.272/1M•Output Rp 3.633/1M
🏷️ Termurah: Kilo Gateway
openai

GPT-5.4 Pro

openai · gpt-pro

More exact GPT-5.4 tier for demanding professional reasoning and agent tasks

TextImage→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 495.355/1M•Output Rp 2.972.129/1M
🏷️ Termurah: Poe
openai

GPT-6.2 Sol

openai · gpt-sol

An efficient reasoning model for everyday work, multistep agentic workflows, and coding.

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 181.631/1M
🏷️ Termurah: NanoGPT
openai

GPT-4o (2024-11-20)

openai · gpt

GPT model for general reasoning, writing, coding, and tool-assisted tasks

TextImage→Text
128K ctx · 16K outToolsAttachments
💰Harga:
Input Rp 45.408/1M•Output Rp 181.631/1M
🏷️ Termurah: NanoGPT
openai

GPT OSS 120B

openai · gpt-oss

Open GPT reasoning model for self-hosted agents and controllable deployments

Text→Text
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 545/1M•Output Rp 2.725/1M
🏷️ Termurah: NanoGPT
openai

GPT OSS 20B

openai · gpt-oss

Open GPT reasoning model for self-hosted agents and controllable deployments

Text→Text
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: InferAll
openai

GPT-5.2

openai · gpt

Reliable GPT generation for broad coding, writing, and tool-assisted product work

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 28.896/1M•Output Rp 231.166/1M
🏷️ Termurah: Poe
openai

GPT-5.1 Codex

openai · gpt-codex

Codex GPT for repository edits, code review, and practical software agents

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 19.980/1M•Output Rp 163.468/1M
🏷️ Termurah: Poe
openai

GPT-6 Sol

openai · gpt-sol

OpenAI model for complex coding and agentic workflows

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 181.631/1M
🏷️ Termurah: NanoGPT
openai

GPT-4o mini

openai · gpt-mini

Small omni GPT for cheap multimodal assistance and production-scale traffic

TextImagePDF→Text
128K ctx · 16K outToolsAttachments
💰Harga:
Input Rp 1.363/1M•Output Rp 5.449/1M
🏷️ Termurah: Cloudflare AI Gateway
openai

GPT-5 Image Mini

openai · gpt-image-mini

Image model for prompt-driven generation, editing, and visual design workflows

PDFImageText→ImageText
400K ctx · 128K outReasoningAttachments
💰Harga:
Input Rp 45.408/1M•Output Rp 36.327/1M
🏷️ Termurah: Kilo Gateway
openai

o1-pro

openai · o-pro

O-series reasoning model for hard analysis, math, coding, and planning

TextImage→Text
200K ctx · 100K outReasoningToolsAttachments
💰Harga:
Input Rp 2.542.821/1M•Output Rp 9.808.022/1M
🏷️ Termurah: Poe
openai

Whisper Large v3 Turbo

openai · whisper

Speech transcription model for accurate audio-to-text and captioning workflows

Audio→Text
448 ctx · 448 outAttachmentsOpen
💰Harga:
Input Rp 42/1M•Output Rp 42/1M
🏷️ Termurah: evroc
openai

GPT-5.4 Image 2

openai · gpt-image

Image model for prompt-driven generation, editing, and visual design workflows

ImageTextPDF→ImageText
272K ctx · 128K outReasoningAttachments
💰Harga:
Input Rp 145.305/1M•Output Rp 272.446/1M
🏷️ Termurah: Kilo Gateway
openai

GPT-5.1 Codex mini

openai · gpt-codex-mini

Coding-optimized GPT model for repository edits, reviews, and agentic software work

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 3.996/1M•Output Rp 32.694/1M
🏷️ Termurah: Poe
openai

GPT-5.5 Instant

openai · gpt

Compact GPT model for low-latency assistance and high-volume workloads

TextImagePDF→Text
400K ctx · 128K outReasoningToolsAttachments
openai

o3-mini

openai · o-mini

Smaller o-series reasoner for economical coding, math, and planning tasks

Text→Text
200K ctx · 100K outReasoningTools
💰Harga:
Input Rp 17.982/1M•Output Rp 72.653/1M
🏷️ Termurah: Poe
openai

GPT-5 Pro

openai · gpt-pro

Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning

TextImage→Text
400K ctx · 272K outReasoningToolsAttachments
💰Harga:
Input Rp 247.678/1M•Output Rp 1.981.419/1M
🏷️ Termurah: Poe
openai

GPT-4o (2024-05-13)

openai · gpt

GPT model for general reasoning, writing, coding, and tool-assisted tasks

TextImage→Text
128K ctx · 4K outToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 272.446/1M
🏷️ Termurah: OrcaRouter
openai

o3-deep-research

openai · o-deep-research

Research model for long-horizon investigation, synthesis, and analytical reports

TextImage→Text
200K ctx · 100K outReasoningToolsAttachments
💰Harga:
Input Rp 163.468/1M•Output Rp 653.869/1M
🏷️ Termurah: Poe
openai

GPT-Image-1.5

openai · gpt-image

Image model for prompt-driven generation, editing, and visual design workflows

TextImage→TextImage
0 ctx · 0 outAttachments
openai

GPT-Realtime-2.1

openai · gpt-realtime

Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior

TextAudioImage→TextAudio
128K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Rp 72.653/1M•Output Rp 435.913/1M
🏷️ Termurah: Vercel AI Gateway
openai

GPT Realtime Whisper

openai · whisper

Streaming speech-to-text model for low-latency transcript deltas from live audio

Audio→Text
16K ctx · 2K outAttachments
openai

o4-mini

openai · o-mini

Fast o-series model for compact reasoning, coding, and tool use

TextImage→Text
200K ctx · 100K outReasoningToolsAttachments
💰Harga:
Input Rp 17.982/1M•Output Rp 72.653/1M
🏷️ Termurah: Poe
openai

GPT-4 Turbo

openai · gpt

Compact GPT model for low-latency assistance and high-volume workloads

TextImage→Text
128K ctx · 4K outToolsAttachments
💰Harga:
Input Rp 163.468/1M•Output Rp 490.402/1M
🏷️ Termurah: Poe
openai

GPT-5.6 Cyber

openai · gpt

Cybersecurity model for authorized vulnerability research and security testing

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
openai

GPT-5.3 Chat (latest)

openai · gpt

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

TextImage→Text
128K ctx · 16K outToolsAttachments
💰Harga:
Input Rp 31.786/1M•Output Rp 254.283/1M
🏷️ Termurah: Merge Gateway
openai

GPT-4

openai · gpt

GPT model for general reasoning, writing, coding, and tool-assisted tasks

Text→Text
8K ctx · 8K outTools
💰Harga:
Input Rp 544.891/1M•Output Rp 1.089.781/1M
🏷️ Termurah: OrcaRouter
openai

GPT-4.1

openai · gpt

Long-lived GPT workhorse for coding, instruction following, and production apps

TextImagePDF→Text
1.0M ctx · 33K outToolsAttachments
💰Harga:
Input Rp 33.024/1M•Output Rp 132.095/1M
🏷️ Termurah: Poe
openai

GPT-5.6 Luna

openai · gpt-luna

Cost-efficient GPT-5.6 model for fast, high-volume workloads

TextImagePDF→Text
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 3.633/1M•Output Rp 21.796/1M
🏷️ Termurah: NanoGPT
openai

GPT-Image-2

openai · gpt-image

Image model for prompt-driven generation, editing, and visual design workflows

TextImage→Image
0 ctx · 0 outAttachments
💰Harga:
Input Rp 91.733/1M•Output Rp 550.394/1M
🏷️ Termurah: Poe
openai

GPT-5.2 Codex

openai · gpt-codex

Code-specialist GPT for repository edits, reviews, and long-running software agents

TextImagePDF→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 29.061/1M•Output Rp 236.120/1M
🏷️ Termurah: Poe
openai

Whisper 3 Large

openai · whisper

Open Whisper checkpoint for robust multilingual transcription and captioning

Audio→Text
448 ctx · 448 outAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
openai

GPT Image 2.5 Sunburst

openai · gpt-image

Image model for prompt-driven generation, editing, and visual design workflows

TextImage→Image
0 ctx · 0 outAttachments
openai

GPT-5.1

openai · gpt

Sharper GPT-5 generation for coding, product work, and tool-assisted tasks

TextImage→Text
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 20.641/1M•Output Rp 165.119/1M
🏷️ Termurah: Poe
baidu

CoBuddy

baidu · cobuddy

Baidu Qianfan model optimized for code generation and tool-using coding agents

Text→Text
131K ctx · 66K outReasoningTools
💰Harga:
Input Rp 5.086/1M•Output Rp 20.525/1M
🏷️ Termurah: Novita AI
baidu

ERNIE 4.5 21B A3B

baidu · ernie

Open ERNIE text MoE with 21B total and 3B active parameters

Text→Text
131K ctx · 8K outToolsOpen
baidu

ERNIE 4.5 300B A47B

baidu · ernie

Open ERNIE text MoE with 300B total and 47B active parameters

Text→Text
131K ctx · 12K outToolsOpen
baidu

ERNIE 4.5 VL 424B A47B

baidu · ernie

Multimodal reasoning model for visual analysis, planning, and tool use

ImageText→Text
123K ctx · 16K outReasoningAttachmentsOpen
💰Harga:
Input Rp 7.629/1M•Output Rp 22.704/1M
🏷️ Termurah: Jiekou.AI
sdaia

ALLaM-2-7b

sdaia · allam

ALLaM-2-7b instruction tuned model by SDAIA

Text→Text
4K ctx · 4K outOpen
trendyol

Trendyol Asure 12B

trendyol · asure

Turkish-language multimodal instruct model built on Gemma 3 12B for e-commerce text, chat, and image-text tasks

TextImage→Text
131K ctx · undefined outAttachmentsOpen
aleph-alpha

Kolibri 1

aleph-alpha · kolibri

Aleph Alpha's German and English mixture-of-experts reasoning model (78B total, 3.46B active) for chat, RAG and agents

Text→Text
1.0M ctx · undefined outReasoningToolsOpen
💰Harga:
Input Rp 2.362/1M•Output Rp 9.264/1M
🏷️ Termurah: Munito AI
zhipuai

GLM-4.5-Flash

zhipuai · glm-flash

Efficient GLM model for fast reasoning, coding, and agent workflows

Text→Text
131K ctx · 98K outReasoningTools
zhipuai

GLM-4.6V-Flash

zhipuai · glmv-flash

Lightweight GLM vision model for visual reasoning, documents, and multimodal agents

TextImageVideo→Text
128K ctx · 33K outReasoningToolsAttachmentsOpen
zhipuai

GLM-4.7-FlashX

zhipuai · glm-flash

Efficient GLM model for fast reasoning, coding, and agent workflows

Text→Text
200K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-4.5V

zhipuai · glmv

GLM vision model for visual reasoning, documents, and multimodal agents

TextImageVideo→Text
64K ctx · 16K outReasoningToolsAttachmentsOpen
zhipuai

GLM-5-Turbo

zhipuai · glm-turbo

Faster GLM-5 lane for coding agents that need lower latency

Text→Text
200K ctx · 131K outReasoningTools
zhipuai

GLM-4.7-Flash

zhipuai · glm-flash

Budget GLM lane for fast coding help, routing, and everyday automation

Text→Text
200K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-5.2

zhipuai · glm

Open flagship GLM for long-horizon coding agents and million-token context work

Text→Text
1M ctx · 131K outReasoningToolsOpen
zhipuai

GLM-5

zhipuai · glm

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

Text→Text
205K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-4.5

zhipuai · glm

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

Text→Text
131K ctx · 98K outReasoningToolsOpen
zhipuai

GLM-5.3

zhipuai · glm

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Text→Text
1M ctx · 131K outReasoningToolsOpen
zhipuai

GLM-5.3-Flash

zhipuai · glm-flash

Native multimodal GLM model for efficient coding and long-horizon agent tasks

TextImageVideoPDF→Text
1M ctx · 131K outReasoningToolsAttachmentsOpen
zhipuai

GLM-4.5-Air

zhipuai · glm-air

Lighter GLM-4.5 variant for fast coding assistance and cheaper agents

Text→Text
131K ctx · 98K outReasoningToolsOpen
zhipuai

GLM-5.1

zhipuai · glm

Strong GLM coding model for agentic engineering, terminals, and repository generation

Text→Text
200K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-5V-Turbo

zhipuai · glmv-turbo

Fast GLM vision model for screenshots, documents, and multimodal agent tasks

TextImageVideoPDF→Text
200K ctx · 131K outReasoningToolsAttachments
zhipuai

GLM-4.6

zhipuai · glm

Late GLM-4 workhorse for coding agents, reasoning, and structured tasks

Text→Text
205K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-4.6V

zhipuai · glmv

GLM vision model for visual reasoning, documents, and multimodal agents

TextImageVideo→Text
128K ctx · 33K outReasoningToolsAttachmentsOpen
zhipuai

GLM-Image

zhipuai · glm-image

GLM-Image is an image generation model adopts a hybrid autoregressive + diffusion decoder architecture. In general image generation quality, GLM‑Image aligns with mainstream latent diffusion approaches, but it shows significant advantages in text-rendering and knowledge‑intensive generation scenarios. It performs especially well in tasks requiring precise semantic understanding and complex information expression, while maintaining strong capabilities in high‑fidelity and fine‑grained detail generation. In addition to text‑to‑image generation, GLM‑Image also supports a rich set of image‑to‑image tasks including image editing, style transfer, identity‑preserving generation, and multi‑subject consistency.

TextImage→Image
10K ctx · 0 outAttachmentsOpen
zhipuai

GLM-4.7

zhipuai · glm

Mature GLM model for dependable coding, reasoning, and structured agent tasks

Text→Text
205K ctx · 131K outReasoningToolsOpen
zhipuai

AutoGLM Phone 9B Multilingual

zhipuai · autoglm

Multilingual visual model for operating smartphone interfaces and mobile agents

TextImage→Text
66K ctx · 66K outAttachmentsOpen
stepfun

Step 3.5 Flash

stepfun · step-flash

StepFun flash lane for quick multimodal reasoning and coding assistance

Text→Text
256K ctx · 256K outReasoningToolsOpen
💰Harga:
Input Rp 1.817/1M•Output Rp 5.449/1M
🏷️ Termurah: ZenMux
stepfun

Step 3.5 Flash 2603

stepfun · step-flash

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Text→Text
256K ctx · 256K outReasoningToolsOpen
stepfun

Step 3.7 Flash

stepfun · step-flash

Newer StepFun flash model for faster agents, coding, and multimodal prompts

TextImageVideo→Text
256K ctx · 256K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 3.633/1M•Output Rp 20.888/1M
🏷️ Termurah: Novita AI
stepfun

Step 5 Preview

stepfun · step

StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window

TextImageVideo→Text
1M ctx · 1M outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 18.164/1M•Output Rp 49.041/1M
🏷️ Termurah: NanoGPT
ai21

Jamba Large

ai21 · jamba-large

AI21's hybrid SSM-Transformer long-context model for enterprise agents and grounded generation

Text→Text
256K ctx · 4K outToolsOpen
ai21

Jamba Mini

ai21 · jamba-mini

AI21's efficient, lightweight hybrid SSM-Transformer model for a wide range of tasks

Text→Text
256K ctx · 4K outToolsOpen
openbmb

MiniCPM5-2B

openbmb · minicpm

Dense 2B-class open-source model for on-device and resource-constrained use, with native long-context support, tool calling, and agentic tasks

Text→Text
131K ctx · 131K outReasoningToolsOpen
openbmb

MiniCPM-V 4.7 1B

openbmb · minicpm-v

Compact MiniCPM-V model for single-image, multi-image and video understanding

TextImageVideo→Text
262K ctx · 262K outReasoningToolsAttachmentsOpen
openbmb

MiniCPM-V 4.7 35B-A3B

openbmb · minicpm-v

First MoE MiniCPM-V model for single-image, multi-image and video understanding

TextImageVideo→Text
262K ctx · 262K outReasoningToolsAttachmentsOpen
openbmb

MiniCPM5-1B

openbmb · minicpm

Dense 1B-class open-source model for on-device and resource-constrained use, with native long-context support, Think / No Think chat modes, and tool calling

Text→Text
131K ctx · 131K outReasoningToolsOpen
paddlepaddle

PaddleOCR VL

paddlepaddle · paddleocr

Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts

TextImage→Text
131K ctx · 16K outAttachmentsOpen
💰Harga:
Input Rp 364/1M•Output Rp 364/1M
🏷️ Termurah: Novita AI
meta

Muse Glimmer 30B

meta · muse-glimmer

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

TextImage→Text
131K ctx · 131K outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
meta

Llama-3.2-1B

meta · llama

Compact open Llama base model for lightweight and on-device use

Text→Text
131K ctx · 8K outOpen
meta

Llama-3.1-70B-Instruct

meta · llama

Open Llama instruction model for multilingual chat, reasoning, and coding

Text→Text
128K ctx · 4K outToolsOpen
💰Harga:
Input Rp 17.982/1M•Output Rp 17.982/1M
🏷️ Termurah: Merge Gateway
meta

Llama 3.2 1B Instruct

meta · llama

Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants

Text→Text
131K ctx · 32K outToolsOpen
💰Harga:
Input Rp 182/1M•Output Rp 182/1M
🏷️ Termurah: Inference
meta

Llama 4 Scout 17B Instruct

meta · llama

Open Llama with long-context vision for efficient multimodal agents

TextImage→Text
10M ctx · 16K outToolsAttachmentsOpen
meta

Muse Wonder

meta · muse-wonder

Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.

TextImageVideoPDFAudio→Text
1.0M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 72.653/1M•Output Rp 363.261/1M
🏷️ Termurah: CommandCode
meta

Llama 4 Maverick 17B Instruct

meta · llama

Open multimodal Llama for strong reasoning with efficient everyday serving

TextImage→Text
1M ctx · 16K outToolsAttachmentsOpen
meta

Llama Prompt Guard 2 86M

meta · llama-prompt-guard

86M-parameter (mDeBERTa-base) multilingual classifier that detects prompt injection and jailbreak attempts

Text→Text
512 ctx · 512 outOpen
meta

Llama-3.2-11B-Vision-Instruct

meta · llama

Open multimodal Llama model for image understanding, captioning, and visual QA

TextImage→Text
128K ctx · 4K outToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
meta

Llama 3.2 3B Instruct

meta · llama

Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval

Text→Text
131K ctx · 131K outToolsOpen
💰Harga:
Input Rp 364/1M•Output Rp 364/1M
🏷️ Termurah: Inference
meta

Llama-3.1-8B-Instruct

meta · llama

Compact open Llama model for lightweight chat, drafting, and self-hosting

Text→Text
128K ctx · 4K outToolsOpen
💰Harga:
Input Rp 455/1M•Output Rp 455/1M
🏷️ Termurah: Inference
meta

Muse Wonder Full

meta · muse-wonder

Muse Wonder Full is the most capable model in Meta's Muse Wonder series, built for long-running professional agents and ultra-long-horizon software engineering. It shares Muse Wonder's Active Memory and Active Focus capabilities and generally scores higher on Meta's agentic and coding evaluations.

TextImageVideoAudio→Text
1.0M ctx · undefined outReasoningToolsAttachments
meta

Llama-3.3-70B-Instruct

meta · llama

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

Text→Text
128K ctx · 4K outToolsOpen
💰Harga:
Input Rp 3.996/1M•Output Rp 9.082/1M
🏷️ Termurah: Merge Gateway
meta

Muse Spark 1.3

meta · muse-spark

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.

TextImageVideoPDFAudio→Text
1.0M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 77.193/1M
🏷️ Termurah: NanoGPT
meta

Muse Ember

meta · muse-ember

Muse Ember is Meta's smallest and most efficient reasoning model, built for the work agents repeat all day: tool calls, coding subtasks, routing, extraction, and long-document parsing. It pairs with Muse Wonder or Muse Spark, which plan while Muse Ember handles the volume.

TextImageVideoPDFAudio→Text
1.0M ctx · 524K outReasoningToolsAttachments
💰Harga:
Input Rp 1.817/1M•Output Rp 9.082/1M
🏷️ Termurah: Cloudflare AI Gateway
meta

Muse Spark Open

meta · muse-spark

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

TextImageVideoAudio→Text
1.0M ctx · 131K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 22.704/1M•Output Rp 77.193/1M
🏷️ Termurah: NanoGPT
meta

Llama Prompt Guard 2 22M

meta · llama-prompt-guard

22M-parameter (DeBERTa-xsmall) English classifier that detects prompt injection and jailbreak attempts

Text→Text
512 ctx · 512 outOpen
meta

Muse Spark 1.2

meta · muse-spark

Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.

TextImageVideoPDFAudio→Text
1.0M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 77.193/1M
🏷️ Termurah: NanoGPT
meta

Llama-3.2-3B

meta · llama

Small open Llama base model for lightweight text generation and self-hosting

Text→Text
131K ctx · 8K outOpen
meta

Muse Spark 1.1

meta · muse-spark

Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.

TextImagePDFVideo→Text
1.0M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 77.193/1M
🏷️ Termurah: NanoGPT
meta

Llama-Guard-3-8B

meta · llama-guard

Llama 3.1-based safety classifier for moderating prompts and model responses

Text→Text
128K ctx · 4K outOpen
meta

Llama Guard 4 12B

meta · llama-guard

Multimodal Llama 4-based safety classifier for moderating prompts and responses

TextImage→Text
164K ctx · 164K outAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
meta

Llama-3.2-90B-Vision-Instruct

meta · llama

Large open multimodal Llama model for image reasoning, document QA, and captioning

TextImage→Text
128K ctx · 4K outToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
mistral

Mistral Nemo

mistral · mistral-nemo

Efficient Mistral-NVIDIA open model for multilingual chat and local deployment

Text→Text
128K ctx · 128K outToolsOpen
💰Harga:
Input Rp 527/1M•Output Rp 545/1M
🏷️ Termurah: Vercel AI Gateway
mistral

Devstral Medium

mistral · devstral-medium

Mistral coding agent model for repository tasks and software engineering workflows

Text→Text
128K ctx · 128K outTools
mistral

Ministral 3 3B 2512

mistral · ministral

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

TextImage→Text
131K ctx · 105K outToolsAttachmentsOpen
💰Harga:
Input Rp 1.817/1M•Output Rp 1.817/1M
🏷️ Termurah: Eden AI
mistral

Mistral Large

mistral · mistral-large

Flagship Mistral model for advanced reasoning, coding, and multilingual work

TextPDF→Text
128K ctx · 102K outToolsAttachments
mistral

Saba

mistral · mistral

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

TextPDF→Text
33K ctx · 26K outToolsAttachments
mistral

Pixtral Large (latest)

mistral · pixtral-large

Mistral's larger vision model for document-heavy image understanding and chat

TextImage→Text
128K ctx · 128K outToolsAttachmentsOpen
💰Harga:
Input Rp 36.327/1M•Output Rp 108.979/1M
🏷️ Termurah: Merge Gateway
mistral

Magistral Small

mistral · magistral-small

Open Mistral reasoning model for transparent step-by-step problem solving

Text→Text
131K ctx · 8K outReasoningToolsOpen
mistral

Pixtral Large (25.02)

mistral · pixtral-large

Mistral vision-language model for image understanding and multimodal chat

TextImage→Text
128K ctx · 8K outToolsAttachments
mistral

Ministral 14B

mistral · ministral

Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use

TextImage→Text
262K ctx · 262K outToolsAttachmentsOpen
💰Harga:
Input Rp 3.633/1M•Output Rp 3.633/1M
🏷️ Termurah: Vercel AI Gateway
mistral

Devstral 2

mistral · devstral

Mistral's coding-agent model for repository work, terminal tasks, and software fixes

Text→Text
262K ctx · 262K outToolsOpen
💰Harga:
Input Rp 7.266/1M•Output Rp 36.327/1M
🏷️ Termurah: Eden AI
mistral

Mistral Small 3.2

mistral · mistral-small

Efficient Mistral model for fast chat, extraction, and production assistants

TextImage→Text
128K ctx · 16K outToolsAttachmentsOpen
💰Harga:
Input Rp 1.817/1M•Output Rp 5.449/1M
🏷️ Termurah: LLM Gateway
mistral

Codestral 25.08

mistral · codestral

Mistral code model for low-latency completion, fill-in-the-middle, and code generation

Text→Text
128K ctx · 8K outTools
💰Harga:
Input Rp 5.449/1M•Output Rp 16.347/1M
🏷️ Termurah: Eden AI
mistral

Devstral Small 2

mistral · devstral-small

Compact multimodal coding model for repository exploration, file editing, and software agents

TextImage→Text
262K ctx · 262K outToolsAttachmentsOpen
mistral

Mistral Medium 3.1

mistral · mistral-medium

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

TextImagePDF→Text
131K ctx · 105K outToolsAttachments
mistral

Mistral Small 3.2 24B

mistral · mistral-small

Efficient Mistral model for fast chat, extraction, and production assistants

ImageText→Text
256K ctx · 16K outToolsAttachmentsOpen
mistral

Mistral Medium 3.5

mistral · mistral-medium

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

TextImagePDF→Text
262K ctx · 210K outReasoningToolsAttachments
💰Harga:
Input Rp 27.245/1M•Output Rp 136.223/1M
🏷️ Termurah: Eden AI
mistral

Voxtral Mini 3B 2507

mistral · voxtral-mini

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

TextAudio→Text
33K ctx · 33K outToolsAttachmentsOpen
mistral

Mistral Small 3.1 24B

mistral · mistral-small

Efficient Mistral model for fast chat, extraction, and production assistants

TextImage→Text
128K ctx · 102K outAttachmentsOpen
mistral

Devstral Small

mistral · devstral-small

Mistral coding agent model for repository tasks and software engineering workflows

Text→Text
128K ctx · 128K outToolsOpen
mistral

Voxtral Small (latest)

mistral · voxtral-small

Instruct model with native audio input for speech understanding and tool use

TextAudio→Text
32K ctx · 32K outToolsAttachmentsOpen
💰Harga:
Input Rp 1.817/1M•Output Rp 5.449/1M
🏷️ Termurah: LLMTR
mistral

Ministral 3B

mistral · ministral

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Text→Text
128K ctx · 8K outTools
💰Harga:
Input Rp 1.817/1M•Output Rp 1.817/1M
🏷️ Termurah: Vercel AI Gateway
mistral

Pixtral 12B

mistral · pixtral

Mistral vision-language model for image understanding and multimodal chat

TextImage→Text
128K ctx · 128K outToolsAttachmentsOpen
mistral

Mistral Medium 3

mistral · mistral-medium

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

TextImage→Text
131K ctx · 131K outToolsAttachments
💰Harga:
Input Rp 7.266/1M•Output Rp 36.327/1M
🏷️ Termurah: Merge Gateway
mistral

Magistral Small 1.2

mistral · magistral-small

Open multimodal reasoning model for transparent analysis of text and images

TextImage→Text
131K ctx · 131K outReasoningToolsAttachmentsOpen
mistral

Mistral Small 3

mistral · mistral-small

Efficient Mistral model for fast chat, extraction, and production assistants

Text→Text
33K ctx · 16K outOpen
mistral

Ministral 3 8B 2512

mistral · ministral

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

TextImage→Text
262K ctx · 210K outToolsAttachmentsOpen
💰Harga:
Input Rp 2.725/1M•Output Rp 2.725/1M
🏷️ Termurah: Eden AI
mistral

Mistral Medium 3.5

mistral · mistral-medium

Balanced Mistral model for enterprise assistants, multilingual work, and tools

TextImage→Text
262K ctx · 262K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 27.245/1M•Output Rp 136.223/1M
🏷️ Termurah: Eden AI
mistral

Ministral 3 8B

mistral · ministral

Compact open vision-language model for edge deployment, instruction following, and tool use

TextImage→Text
262K ctx · 262K outToolsAttachmentsOpen
mistral

Codestral-22B-v0.1

mistral · codestral

Open Mistral code model for fill-in-the-middle and 80+ programming languages

Text→Text
33K ctx · 8K outOpen
mistral

Mixtral 8x22B Instruct

mistral · mixtral

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

TextPDF→Text
66K ctx · 52K outToolsAttachmentsOpen
mistral

Mistral Large 3

mistral · mistral-large

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

TextImage→Text
262K ctx · 262K outToolsAttachmentsOpen
💰Harga:
Input Rp 9.082/1M•Output Rp 27.245/1M
🏷️ Termurah: Eden AI
mistral

Codestral (latest)

mistral · codestral

Mistral code model for completions, refactors, and developer IDE workflows

Text→Text
256K ctx · 4K outToolsOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 16.347/1M
🏷️ Termurah: Eden AI
mistral

Mistral Small (latest)

mistral · mistral-small

Efficient Mistral model for fast chat, extraction, and production assistants

TextImage→Text
256K ctx · 256K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 2.725/1M•Output Rp 10.898/1M
🏷️ Termurah: Eden AI
mistral

Mistral 7B Instruct v0.3

mistral · mistral

Open 7B Mistral instruction model with function calling

Text→Text
33K ctx · 33K outToolsOpen
mistral

Voxtral Small 24B 2507

mistral · voxtral-small

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

TextAudio→Text
33K ctx · 33K outToolsAttachmentsOpen
mistral

Mixtral 8x7B Instruct v0.1

mistral · mixtral

Open sparse mixture-of-experts Mistral instruction model

Text→Text
33K ctx · 33K outOpen
mistral

Mistral Embed

mistral · mistral-embed

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Text→Text
8K ctx · 3K out
mistral

Ministral 3 14B

mistral · ministral

Open vision-language model for efficient local deployment, instruction following, and tool use

TextImage→Text
262K ctx · 262K outToolsAttachmentsOpen
mistral

Mistral Large 2407

mistral · mistral-large

Flagship Mistral model for advanced reasoning, coding, and multilingual work

TextPDF→Text
131K ctx · 105K outToolsAttachmentsOpen
💰Harga:
Input Rp 36.327/1M•Output Rp 108.979/1M
🏷️ Termurah: Eden AI
mistral

Devstral 2 (latest)

mistral · devstral-medium

Mistral coding agent model for repository tasks and software engineering workflows

Text→Text
262K ctx · 262K outToolsOpen
💰Harga:
Input Rp 7.266/1M•Output Rp 36.327/1M
🏷️ Termurah: Eden AI
mistral

Mistral Medium (latest)

mistral · mistral-medium

Balanced Mistral model for enterprise assistants, multilingual work, and tools

TextImage→Text
262K ctx · 262K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 7.266/1M•Output Rp 36.327/1M
🏷️ Termurah: Merge Gateway
mistral

Mistral Large 2.1

mistral · mistral-large

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Text→Text
131K ctx · 16K outToolsOpen
mistral

Mistral Small 3.1 24B

mistral · mistral-small

Efficient multimodal model for instruction following, coding, reasoning, and function calling

TextImage→Text
128K ctx · 16K outToolsAttachmentsOpen
mistral

Mistral Large (latest)

mistral · mistral-large

Flagship Mistral model for advanced reasoning, coding, and multilingual work

TextImage→Text
262K ctx · 262K outToolsAttachmentsOpen
💰Harga:
Input Rp 9.082/1M•Output Rp 27.245/1M
🏷️ Termurah: Merge Gateway
mistral

Magistral Medium (latest)

mistral · magistral-medium

Mistral reasoning model for transparent analysis, math, and complex decisions

Text→Text
128K ctx · 16K outReasoningTools
💰Harga:
Input Rp 36.327/1M•Output Rp 90.816/1M
🏷️ Termurah: Merge Gateway
mistral

Ministral 8B Instruct

mistral · ministral

Efficient open Mistral edge model for on-device chat and function calling

Text→Text
131K ctx · 8K outToolsOpen
mistral

Mistral Medium 3

mistral · mistral-medium

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

TextImagePDF→Text
131K ctx · 105K outToolsAttachments
💰Harga:
Input Rp 7.992/1M•Output Rp 39.959/1M
🏷️ Termurah: Eden AI
mistral

Ministral 3 14B 2512

mistral · ministral

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

TextImage→Text
262K ctx · 210K outToolsAttachmentsOpen
💰Harga:
Input Rp 3.633/1M•Output Rp 3.633/1M
🏷️ Termurah: Eden AI
mistral

Mistral Small 4

mistral · mistral-small

Fast Mistral production model for chat, extraction, and cost-sensitive agents

TextImage→Text
256K ctx · 256K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 2.725/1M•Output Rp 10.898/1M
🏷️ Termurah: Eden AI
mistral

Ministral 3 3B

mistral · ministral

Compact open vision-language model for edge deployment, instruction following, and tool use

TextImage→Text
262K ctx · 262K outToolsAttachmentsOpen
mistral

Mistral Large 4

mistral · mistral-large

Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work

TextImage→Text
1.0M ctx · 262K outReasoningToolsAttachments
💰Harga:
Input Rp 12.715/1M•Output Rp 38.143/1M
🏷️ Termurah: Vercel AI Gateway
anthropic

Claude Haiku 5.5

anthropic · claude-haiku

Fast Claude model for responsive assistance, classification, and lightweight agents

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 909/1M•Output Rp 4.541/1M
🏷️ Termurah: IteraCompute
anthropic

Claude Opus 4.5

anthropic · claude-opus

Flagship Claude model for deep reasoning, coding, and long-horizon agents

TextImagePDF→Text
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 454.076/1M
🏷️ Termurah: Eden AI
anthropic

Claude Opus 4 (latest)

anthropic · claude-opus

Flagship Claude model for deep reasoning, coding, and long-horizon agents

TextImagePDF→Text
200K ctx · 32K outReasoningToolsAttachments
anthropic

Claude Opus 5.5

anthropic · claude-opus

Claude model for long-running agentic coding and knowledge work

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 181.631/1M
🏷️ Termurah: IteraCompute
anthropic

Claude Opus 4.1

anthropic · claude-opus

Flagship Claude model for deep reasoning, coding, and long-horizon agents

TextImagePDF→Text
200K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Rp 272.446/1M•Output Rp 1.362.226/1M
🏷️ Termurah: Merge Gateway
anthropic

Claude Haiku 3.5

anthropic · claude-haiku

Fast Claude model for responsive assistance, classification, and lightweight agents

TextImagePDF→Text
200K ctx · 8K outToolsAttachments
anthropic

Claude Haiku 3

anthropic · claude-haiku

Legacy model retained for compatibility with older integrations

TextImagePDF→Text
200K ctx · 4K outToolsAttachments
anthropic

Claude Sonnet 4 (latest)

anthropic · claude-sonnet

Balanced Claude model for coding, analysis, agent workflows, and cost control

TextImagePDF→Text
200K ctx · 64K outReasoningToolsAttachments
anthropic

Claude Opus 5

anthropic · claude-opus

Strongest Claude Opus model for coding, agents, and professional work

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 454.076/1M
🏷️ Termurah: NanoGPT
anthropic

Claude Opus 4.1 (latest)

anthropic · claude-opus

Flagship Claude model for deep reasoning, coding, and long-horizon agents

TextImagePDF→Text
200K ctx · 32K outReasoningToolsAttachments
anthropic

Claude Sonnet 4.5

anthropic · claude-sonnet

Balanced Claude model for coding, analysis, agent workflows, and cost control

TextImagePDF→Text
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 54.490/1M•Output Rp 272.446/1M
🏷️ Termurah: LLM Gateway
anthropic

Claude Sonnet 4.5 (latest)

anthropic · claude-sonnet

Balanced Claude model for coding, analysis, agent workflows, and cost control

TextImagePDF→Text
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 54.490/1M•Output Rp 272.446/1M
🏷️ Termurah: Perplexity Agent
anthropic

Claude Sonnet 5.5

anthropic · claude-sonnet

Fast Claude model for everyday coding, agents, and knowledge work

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 18.164/1M•Output Rp 90.816/1M
🏷️ Termurah: IteraCompute
anthropic

Claude Sonnet 4

anthropic · claude-sonnet

Balanced Claude model for coding, analysis, agent workflows, and cost control

TextImagePDF→Text
200K ctx · 64K outReasoningToolsAttachments
anthropic

Claude Sonnet 4.6

anthropic · claude-sonnet

Claude workhorse for coding agents, careful analysis, and production cost control

TextImagePDF→Text
1M ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 54.490/1M•Output Rp 272.446/1M
🏷️ Termurah: CrossModel
anthropic

Claude Fable 5.1

anthropic · claude-fable

Claude model for demanding reasoning and long-horizon agentic work

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 454.076/1M
🏷️ Termurah: IteraCompute
anthropic

Claude Sonnet 3.7

anthropic · claude-sonnet

Balanced Claude model for coding, analysis, agent workflows, and cost control

TextImagePDF→Text
200K ctx · 64K outReasoningToolsAttachments
anthropic

Claude Opus 4.5 (latest)

anthropic · claude-opus

Flagship Claude model for deep reasoning, coding, and long-horizon agents

TextImagePDF→Text
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 454.076/1M
🏷️ Termurah: Perplexity Agent
anthropic

Claude Haiku 4.5

anthropic · claude-haiku

Fast Claude model for responsive assistance, classification, and lightweight agents

TextImagePDF→Text
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 18.164/1M•Output Rp 90.816/1M
🏷️ Termurah: LLM Gateway
anthropic

Claude Haiku 4.5 (latest)

anthropic · claude-haiku

Fast Claude lane for lightweight agents, office tasks, and responsive chat

TextImagePDF→Text
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 18.164/1M•Output Rp 90.816/1M
🏷️ Termurah: CrossModel
anthropic

Claude Opus 4.7

anthropic · claude-opus

Stronger Opus tier for advanced software work and high-stakes reasoning

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 454.076/1M
🏷️ Termurah: CrossModel
anthropic

Claude Sonnet 3.5 v2

anthropic · claude-sonnet

Balanced Claude model for coding, analysis, agent workflows, and cost control

TextImagePDF→Text
200K ctx · 8K outToolsAttachments
anthropic

Claude Sonnet 5

anthropic · claude-sonnet

Everyday Claude agent model for coding, planning, browsing, and general work

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 181.631/1M
🏷️ Termurah: NanoGPT
anthropic

Claude Fable 5

anthropic · claude-fable

Claude model for creative writing, analysis, and controlled agent workflows

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 181.631/1M•Output Rp 908.151/1M
🏷️ Termurah: NanoGPT
anthropic

Claude Opus 4.6

anthropic · claude-opus

High-end Claude for difficult coding, planning, and slower expert reasoning

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 454.076/1M
🏷️ Termurah: Perplexity Agent
anthropic

Claude Fable 5.2

anthropic · claude-fable

Claude model for demanding reasoning and long-horizon agentic work

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 145.305/1M•Output Rp 726.521/1M
🏷️ Termurah: CrossModel
anthropic

Claude Mythos 5

anthropic · claude-mythos

Restricted Claude model for advanced cybersecurity and biology research workflows

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
anthropic

Claude Mythos 5.1

anthropic · claude-mythos

Restricted Claude model for advanced cybersecurity and biology research workflows

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
anthropic

Claude Opus 4.8

anthropic · claude-opus

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 454.076/1M
🏷️ Termurah: CrossModel
anthropic

Claude Opus 4

anthropic · claude-opus

Flagship Claude model for deep reasoning, coding, and long-horizon agents

TextImagePDF→Text
200K ctx · 32K outReasoningToolsAttachments
writer

Palmyra X5

writer · palmyra

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

TextImage→Text
1M ctx · 8K outReasoningToolsAttachments
💰Harga:
Input Rp 10.898/1M•Output Rp 108.979/1M
🏷️ Termurah: Kilo Gateway
writer

Palmyra X4

writer · palmyra

Enterprise language model for workflow automation, coding, data analysis, and tool use

Text→Text
128K ctx · 4K outReasoningTools
💰Harga:
Input Rp 45.408/1M•Output Rp 181.631/1M
🏷️ Termurah: Merge Gateway
allenai

olmOCR 2 7B

allenai · olmocr

Vision-language OCR model from Ai2 (Allen Institute for AI) that extracts text from documents where tables, equations, and poor-quality scans defeat traditional OCR

TextImage→Text
16K ctx · undefined outAttachmentsOpen
unbiased

Pareto

unbiased · pareto

Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer

TextImage→Text
262K ctx · 131K outToolsAttachments
💰Harga:
Input Rp 45.408/1M•Output Rp 136.223/1M
🏷️ Termurah: Cloudflare AI Gateway
unbiased

Pareto 26.10

unbiased · pareto

Blended multimodal model that selects frontier and open models for each request and blends their outputs into one answer

TextImage→Text
1.0M ctx · 131K outToolsAttachments
💰Harga:
Input Rp 14.531/1M•Output Rp 58.122/1M
🏷️ Termurah: NanoGPT
amazon

Nova Pro 1.0

amazon · nova-pro

Flagship model for demanding analysis, coding, and production agent workflows

TextImage→Text
300K ctx · 5K outToolsAttachments
💰Harga:
Input Rp 14.513/1M•Output Rp 58.049/1M
🏷️ Termurah: NanoGPT
amazon

Nova Micro

amazon · nova-micro

Efficient model for low-latency assistance, extraction, and routine automation

Text→Text
128K ctx · 10K outTools
💰Harga:
Input Rp 636/1M•Output Rp 2.543/1M
🏷️ Termurah: Kilo Gateway
amazon

Nova 2 Lite

amazon · nova-lite

Multimodal reasoning model for visual analysis, planning, and tool use

TextImageVideoPDF→Text
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 5.994/1M•Output Rp 49.949/1M
🏷️ Termurah: Vercel AI Gateway
amazon

Nova Pro

amazon · nova-pro

Flagship model for demanding analysis, coding, and production agent workflows

TextImageVideoPDF→Text
300K ctx · 10K outToolsAttachments
💰Harga:
Input Rp 14.531/1M•Output Rp 58.122/1M
🏷️ Termurah: Kilo Gateway
amazon

Nova Premier

amazon · nova-premier

Multimodal model for complex analysis, long-context understanding, tool use, and model distillation

TextImageVideoPDF→Text
1M ctx · 10K outToolsAttachments
amazon

Nova Lite 1.0

amazon · nova-lite

Efficient model for low-latency assistance, extraction, and routine automation

TextImage→Text
300K ctx · 5K outToolsAttachments
💰Harga:
Input Rp 1.081/1M•Output Rp 4.323/1M
🏷️ Termurah: NanoGPT
amazon

Nova Lite

amazon · nova-lite

Efficient model for low-latency assistance, extraction, and routine automation

TextImageVideoPDF→Text
300K ctx · 10K outToolsAttachments
💰Harga:
Input Rp 1.090/1M•Output Rp 4.360/1M
🏷️ Termurah: Kilo Gateway
amazon

Nova 2 Lite

amazon · nova-lite

Multimodal reasoning model for visual analysis, planning, and tool use

TextImageVideoPDF→Text
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 5.449/1M•Output Rp 45.408/1M
🏷️ Termurah: Kilo Gateway
amazon

Nova Micro 1.0

amazon · nova-micro

Efficient model for low-latency assistance, extraction, and routine automation

Text→Text
128K ctx · 5K outTools
💰Harga:
Input Rp 636/1M•Output Rp 2.543/1M
🏷️ Termurah: Kilo Gateway
ibm

Granite-4.0-H-Micro

ibm · granite-micro

Compact open-weight hybrid Granite model for lightweight enterprise chat and tool calling

Text→Text
131K ctx · 131K outToolsOpen
ibm

Granite 4.2 8B

ibm · granite

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Text→Text
131K ctx · 118K outReasoningToolsOpen
ibm

Granite-4.0-H-Small

ibm · granite-small

Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads

Text→Text
131K ctx · 131K outToolsOpen
💰Harga:
Input Rp 1.156/1M•Output Rp 4.814/1M
🏷️ Termurah: watsonx.ai
nex-agi

Nex-N2-Pro

nex-agi · nex-n-pro

Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows

TextImage→Text
262K ctx · 262K outReasoningToolsAttachmentsOpen
cognitivecomputations

Uncensored

cognitivecomputations · dolphin

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Text→Text
128K ctx · 8K outOpen
💰Harga:
Input Rp 3.633/1M•Output Rp 16.347/1M
🏷️ Termurah: Kilo Gateway
canopylabs

Orpheus V1 English

canopylabs · orpheus

Expressive English text-to-speech model with bracketed vocal directions

Text→Audio
4K ctx · 50K out
canopylabs

Orpheus Arabic Saudi

canopylabs · orpheus

Expressive Saudi Arabic text-to-speech model with bracketed vocal directions

Text→Audio
4K ctx · 50K out
deepseek

DeepSeek V4 Pro 0423

deepseek · deepseek-pro

DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes

Text→Text
1M ctx · 384K outReasoningToolsOpen
💰Harga:
Input Rp 29.969/1M•Output Rp 59.938/1M
🏷️ Termurah: Merge Gateway
deepseek

DeepSeek V3.2

deepseek · deepseek

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

Text→Text
128K ctx · 64K outReasoningToolsOpen
💰Harga:
Input Rp 3.949/1M•Output Rp 5.922/1M
🏷️ Termurah: TokenGo
deepseek

DeepSeek V4.1 Flash

deepseek · deepseek-flash

DeepSeek V4.1 Flash model for reasoning and agentic coding

TextImage→Text
1M ctx · 384K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 905/1M•Output Rp 3.619/1M
🏷️ Termurah: Kilo Gateway
deepseek

DeepSeek OCR 2

deepseek · deepseek-ocr

High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes

TextImage→Text
8K ctx · 8K outAttachmentsOpen
💰Harga:
Input Rp 545/1M•Output Rp 545/1M
🏷️ Termurah: Novita AI
deepseek

DeepSeek V4 Flash

deepseek · deepseek-flash

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

Text→Text
1M ctx · 384K outReasoningToolsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Obscurify.ai
deepseek

DeepSeek V4 Flash 0731

deepseek · deepseek-flash

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

Text→Text
1M ctx · 384K outReasoningToolsOpen
💰Harga:
Input Rp 800/1M•Output Rp 2.398/1M
🏷️ Termurah: NanoGPT
deepseek

DeepSeek Reasoner

deepseek · deepseek

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Text→Text
1M ctx · 384K outReasoningToolsOpen
💰Harga:
Input Rp 4.396/1M•Output Rp 13.187/1M
🏷️ Termurah: OrcaRouter
deepseek

DeepSeek-V3

deepseek · deepseek

Open DeepSeek MoE chat model for coding, math, and general reasoning

Text→Text
131K ctx · 8K outToolsOpen
💰Harga:
Input Rp 4.905/1M•Output Rp 19.980/1M
🏷️ Termurah: Merge Gateway
deepseek

DeepSeek-R1

deepseek · deepseek-r

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Text→Text
128K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Rp 24.521/1M•Output Rp 98.081/1M
🏷️ Termurah: Kilo Gateway
deepseek

DeepSeek-R1-Distill-Qwen-32B

deepseek · deepseek-r

R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving

Text→Text
131K ctx · 33K outReasoningOpen
deepseek

DeepSeek V3 0324

deepseek · deepseek

March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding

Text→Text
164K ctx · 164K outToolsOpen
💰Harga:
Input Rp 5.086/1M•Output Rp 20.706/1M
🏷️ Termurah: Jiekou.AI
deepseek

DeepSeek V4 Flash 0423

deepseek · deepseek-flash

Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads

Text→Text
1M ctx · 384K outReasoningToolsOpen
💰Harga:
Input Rp 2.525/1M•Output Rp 5.050/1M
🏷️ Termurah: Merge Gateway
deepseek

DeepSeek R1 0528 Qwen3 8B

deepseek · deepseek-r

DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning

Text→Text
131K ctx · 32K outReasoningOpen
💰Harga:
Input Rp 1.090/1M•Output Rp 1.635/1M
🏷️ Termurah: Novita AI
deepseek

DeepSeek R1 0528

deepseek · deepseek-r

May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning

Text→Text
164K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Rp 10.372/1M•Output Rp 41.521/1M
🏷️ Termurah: Kilo Gateway
deepseek

DeepSeek Chat

deepseek · deepseek

DeepSeek chat model for instruction following, coding, and analysis

Text→Text
1M ctx · 384K outToolsOpen
💰Harga:
Input Rp 2.725/1M•Output Rp 10.898/1M
🏷️ Termurah: Eden AI
deepseek

DeepSeek V4 Pro

deepseek · deepseek-pro

Open MoE flagship with million-token context for coding and long agent runs

Text→Text
1M ctx · 384K outReasoningToolsOpen
💰Harga:
Input Rp 7.901/1M•Output Rp 15.802/1M
🏷️ Termurah: TokenGo
deepseek

DeepSeek V4 Pro 0813

deepseek · deepseek-pro

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Text→Text
1M ctx · 384K outReasoningToolsOpen
💰Harga:
Input Rp 10.898/1M•Output Rp 32.512/1M
🏷️ Termurah: IteraCompute
deepseek

DeepSeek-V3.1

deepseek · deepseek

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

Text→Text
131K ctx · 8K outReasoningToolsOpen
💰Harga:
Input Rp 3.451/1M•Output Rp 12.896/1M
🏷️ Termurah: TokenGo
deepseek

DeepSeek V3 0324

deepseek · deepseek

DeepSeek chat model for instruction following, coding, and analysis

Text→Text
164K ctx · 147K outToolsOpen
💰Harga:
Input Rp 4.541/1M•Output Rp 18.164/1M
🏷️ Termurah: Kilo Gateway
deepseek

DeepSeek V4 Flash Vision Exp

deepseek · deepseek-flash

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

TextImage→Text
1M ctx · 384K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 2.725/1M•Output Rp 10.898/1M
🏷️ Termurah: CommandCode
deepseek

DeepSeek V4.1 Flash 1017

deepseek · deepseek-flash

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

TextImage→Text
1M ctx · 384K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 818/1M•Output Rp 4.541/1M
🏷️ Termurah: Ambient
deepseek

DeepSeek V3.1

deepseek · deepseek

DeepSeek chat model for instruction following, coding, and analysis

Text→Text
164K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Rp 4.541/1M•Output Rp 17.255/1M
🏷️ Termurah: Kilo Gateway
xai

Grok 4.3

xai · grok

xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk

TextImagePDF→Text
1M ctx · 30K outReasoningToolsAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 45.408/1M
🏷️ Termurah: Vertex
xai

X-Ai/Grok-4-Fast-Reasoning

xai · grok

Fast Grok model for responsive chat, reasoning, and tool-assisted work

TextImageAudioVideo→Text
2M ctx · 2M outReasoningToolsAttachments
💰Harga:
Input Rp 3.633/1M•Output Rp 9.082/1M
🏷️ Termurah: Poe
xai

Grok 4.1 Fast

xai · grok

xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses

TextImage→Text
2M ctx · 30K outToolsAttachments
xai

Grok Voice Transcribe 2.0

xai · grok-transcribe

Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming

Audio→Text
0 ctx · 0 outAttachments
xai

Grok 4.1 Fast (Reasoning)

xai · grok

xAI's fast agentic tool-calling model with a 2M context window and built-in reasoning

TextImage→Text
2M ctx · 30K outReasoningToolsAttachments
💰Harga:
Input Rp 3.633/1M•Output Rp 9.082/1M
🏷️ Termurah: Vertex
xai

Grok 4.5

xai · grok

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

TextImage→Text
500K ctx · 500K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 108.979/1M
🏷️ Termurah: Perplexity Agent
xai

Grok Imagine Video 1.5 Lite

xai · grok-imagine-video-lite

Cost-efficient video model for text-to-video and image-to-video generation

TextImage→Video
1K ctx · 0 outAttachments
xai

Grok Imagine Video 1.5

xai · grok-imagine-video

Video model for text-to-video, image-to-video, and reference-to-video generation with optional voice references

TextImageAudio→Video
1K ctx · 0 outAttachments
xai

Grok TTS

xai · grok-tts

Convert text into spoken audio with a single API call. The API supports a rich set of expressive voices, inline speech tags for fine-grained delivery control, and output formats from high-fidelity MP3 to telephony-optimized μ-law.

Text→Audio
15K ctx · 15K out
xai

x-AI/Grok-Code-Fast 1

xai · grok-code

Fast Grok model for responsive chat, reasoning, and tool-assisted work

Text→Text
256K ctx · 10K outReasoningTools
💰Harga:
Input Rp 3.633/1M•Output Rp 27.245/1M
🏷️ Termurah: Poe
xai

Grok 4.7

xai · grok

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

TextImagePDF→Text
500K ctx · 500K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 108.979/1M
🏷️ Termurah: Perplexity Agent
xai

Grok Imagine Image

xai · grok-imagine-image

Image model for prompt-driven generation, editing, and visual design workflows

TextImage→Image
16K ctx · 0 outAttachments
xai

Grok Imagine Image 2.0

xai · grok-imagine-image

Image model for prompt-driven generation, editing, and visual design workflows

TextImage→Image
64K ctx · 0 outAttachments
xai

X-Ai/Grok-4-Fast-Non-Reasoning

xai · grok

Fast Grok model for responsive chat, reasoning, and tool-assisted work

TextImageAudioVideo→Text
2M ctx · 2M outToolsAttachments
💰Harga:
Input Rp 3.633/1M•Output Rp 9.082/1M
🏷️ Termurah: Eden AI
xai

Grok 4.6

xai · grok

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

TextImage→Text
500K ctx · 500K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 108.979/1M
🏷️ Termurah: Perplexity Agent
xai

Grok 4.20 (Reasoning)

xai · grok

Reasoning Grok for document-heavy analysis and long-horizon tool use

TextImagePDF→Text
1M ctx · 30K outReasoningToolsAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 45.408/1M
🏷️ Termurah: Impossibl
xai

Grok 4.20 (Non-Reasoning)

xai · grok

Grok model for agentic tool use, reasoning, coding, and live assistance

TextImagePDF→Text
1M ctx · 30K outToolsAttachments
💰Harga:
Input Rp 22.704/1M•Output Rp 45.408/1M
🏷️ Termurah: Impossibl
xai

Grok Build 0.1

xai · grok-build

Fast Grok coding model tuned for agentic engineering and iterative edits

TextImagePDF→Text
256K ctx · 256K outReasoningToolsAttachments
💰Harga:
Input Rp 18.164/1M•Output Rp 36.327/1M
🏷️ Termurah: Impossibl
xai

Grok Imagine Image Quality

xai · grok-imagine-image

Higher-fidelity Grok Imagine image model for prompt-driven generation, editing, and visual design workflows

TextImage→Image
16K ctx · 0 outAttachments
liquid

LFM2 24B A2B

liquid · lfm

Efficient open Liquid MoE instruct model for on-device chat and tool calling

Text→Text
33K ctx · 33K outToolsOpen
cohere

Aya Expanse 32B

cohere · aya

Open multilingual model optimized for generation across 23 languages

Text→Text
128K ctx · 4K outOpen
💰Harga:
Input Rp 9.082/1M•Output Rp 27.245/1M
🏷️ Termurah: Eden AI
cohere

Command R7B Arabic

cohere · command-r

Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge

Text→Text
128K ctx · 4K outToolsOpen
cohere

North Mini Code

cohere · north-mini

Cohere coding model for practical software engineering and agentic edits

Text→Text
256K ctx · 64K outReasoningToolsOpen
cohere

Command A Vision

cohere · command-a

Cohere vision model for multilingual document analysis, OCR, and image understanding

TextImage→Text
128K ctx · 8K outAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Eden AI
cohere

Aya Vision 32B

cohere · aya-vision

Open multilingual vision model for OCR, visual reasoning, and image question answering

TextImage→Text
16K ctx · 4K outAttachmentsOpen
cohere

Tiny Aya Fire

cohere · aya-tiny

Compact multilingual model specialized for South Asian languages

Text→Text
8K ctx · 8K outToolsOpen
cohere

Tiny Aya Earth

cohere · aya-tiny

Compact multilingual model specialized for West Asian and African languages

Text→Text
8K ctx · 8K outToolsOpen
cohere

Tiny Aya Water

cohere · aya-tiny

Compact multilingual model specialized for European and Asia-Pacific languages

Text→Text
8K ctx · 8K outToolsOpen
cohere

Command A

cohere · command-a

Cohere command model for multilingual enterprise agents, tools, and chat

Text→Text
256K ctx · 8K outToolsOpen
💰Harga:
Input Rp 45.408/1M•Output Rp 181.631/1M
🏷️ Termurah: Kilo Gateway
cohere

Tiny Aya Global

cohere · aya-tiny

Compact multilingual model balanced across 70 languages and regions

Text→Text
8K ctx · 8K outToolsOpen
cohere

Aya Vision 8B

cohere · aya-vision

Compact open multilingual vision model for OCR and visual question answering

TextImage→Text
16K ctx · 4K outAttachmentsOpen
cohere

Aya Expanse 8B

cohere · aya

Compact open multilingual model optimized for generation across 23 languages

Text→Text
8K ctx · 4K outOpen
cohere

North Small Translate

cohere · north-small

Open-weight translation model for more than 50 languages and locale variants

Text→Text
16K ctx · 16K outOpen
cohere

Command R7B

cohere · command-r

Cohere retrieval model for long-context chat and enterprise RAG workflows

Text→Text
128K ctx · 4K outToolsOpen
💰Harga:
Input Rp 682/1M•Output Rp 2.725/1M
🏷️ Termurah: Eden AI
cohere

Command A Reasoning

cohere · command-a

Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows

Text→Text
256K ctx · 32K outReasoningToolsOpen
cohere

Command A Translate

cohere · command-a

Translation model for multilingual conversion, localization, and cross-language workflows

Text→Text
8K ctx · 8K outToolsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Eden AI
cohere

Command A

cohere · command-a

Cohere command model for multilingual enterprise agents, tools, and chat

Text→Text
256K ctx · 8K outToolsOpen
💰Harga:
Input Rp 45.408/1M•Output Rp 181.631/1M
🏷️ Termurah: Eden AI
cohere

Command A Plus

cohere · command-a-plus

Cohere's stronger command model for multilingual agents and enterprise workflows

TextImage→Text
128K ctx · 64K outReasoningToolsAttachmentsOpen
cohere

Command R+

cohere · command-r-plus

Cohere's RAG workhorse for long-context enterprise search and tool use

Text→Text
128K ctx · 4K outToolsOpen
💰Harga:
Input Rp 45.408/1M•Output Rp 181.631/1M
🏷️ Termurah: Eden AI
cohere

Command R

cohere · command-r

Cohere retrieval model for long-context chat and enterprise RAG workflows

Text→Text
128K ctx · 4K outToolsOpen
💰Harga:
Input Rp 2.725/1M•Output Rp 10.898/1M
🏷️ Termurah: Eden AI
inference-net

Schematron V2 Small

inference-net · schematron-small

Efficient model for low-latency assistance, extraction, and routine automation

Text→Text
128K ctx · 4K out
💰Harga:
Input Rp 909/1M•Output Rp 4.178/1M
🏷️ Termurah: NanoGPT
inference-net

Schematron V2 Turbo

inference-net · schematron-turbo

Efficient model for low-latency assistance, extraction, and routine automation

Text→Text
128K ctx · 8K out
💰Harga:
Input Rp 545/1M•Output Rp 2.725/1M
🏷️ Termurah: NanoGPT
aisingapore

Gemma-SEA-LION-v4-27B-IT

aisingapore · sea-lion

Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following

TextImage→Text
128K ctx · 128K outAttachmentsOpen
💰Harga:
Input Rp 4.360/1M•Output Rp 8.719/1M
🏷️ Termurah: NanoGPT
swiss-ai

Apertus 1.5 70B

swiss-ai · apertus

Fully open multilingual multimodal reasoner from the Swiss AI Initiative with image and audio understanding, an optional thinking mode, and a 262K context window

TextImageAudio→Text
262K ctx · 8K outReasoningToolsAttachmentsOpen
swiss-ai

Apertus 8B

swiss-ai · apertus

Fully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant.

Text→Text
66K ctx · 8K outToolsOpen
swiss-ai

Apertus v1.5 8B

swiss-ai · apertus

Fully open 8B multilingual multimodal LLM from the Swiss AI Initiative (ETH Zurich, EPFL, CSCS) supporting 1,000+ languages, with weights, training data, and methods fully documented. Apache 2.0.

TextImageAudio→Text
262K ctx · undefined outReasoningToolsAttachmentsOpen
swiss-ai

Apertus 70B

swiss-ai · apertus

Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.

Text→Text
66K ctx · 8K outToolsOpen
deepreinforce

Ornith 1.0 9B

deepreinforce · ornith

Open coding-reasoning model for repository tasks and self-improving agents

TextImage→Text
262K ctx · undefined outReasoningToolsAttachmentsOpen
deepreinforce

Ornith 1.0 31B

deepreinforce · ornith

Open coding-reasoning model for repository tasks and self-improving agents

TextImage→Text
262K ctx · undefined outReasoningToolsAttachmentsOpen
deepreinforce

Ornith 1.5 35B A3B

deepreinforce · ornith

Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding

TextImage→Text
262K ctx · undefined outReasoningToolsAttachmentsOpen
deepreinforce

Ornith 1.0 35B

deepreinforce · ornith

Large coding-reasoning model for agentic software tasks and RL search

TextImage→Text
262K ctx · undefined outReasoningToolsAttachmentsOpen
deepreinforce

Ornith 1.5 122B

deepreinforce · ornith

Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding

TextImage→Text
262K ctx · 33K outReasoningToolsAttachmentsOpen
deepreinforce

Ornith 1.0 397B

deepreinforce · ornith

Large coding-reasoning model for agentic software tasks and RL search

TextImage→Text
262K ctx · undefined outReasoningToolsAttachmentsOpen
quiverai

Arrow 2 Telos

quiverai · arrow

High-fidelity SVG generation model for complex vector work and long-context refinement

TextImage→TextImage
1.1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 108.979/1M•Output Rp 544.891/1M
🏷️ Termurah: Kilo Gateway
quiverai

Arrow 2

quiverai · arrow

Fast SVG generation model for creation, vectorization, editing, and animation

TextImage→TextImage
131K ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 72.653/1M•Output Rp 363.261/1M
🏷️ Termurah: Kilo Gateway
black-forest-labs

FLUX.1 Kontext [dev]

black-forest-labs · flux-kontext-dev

Open-weight FLUX.1 Kontext model for instruction-based image editing

TextImage→Image
0 ctx · 0 outAttachmentsOpen
black-forest-labs

FLUX.1 [schnell]

black-forest-labs · flux-schnell

Fast few-step FLUX.1 text-to-image model under Apache 2.0

Text→Image
0 ctx · 0 outOpen
black-forest-labs

FLUX.1 [dev]

black-forest-labs · flux-dev

Open-weight FLUX.1 text-to-image model for high-quality guidance-distilled generation

Text→Image
0 ctx · 0 outOpen
poolside

Laguna M.1

poolside · laguna-m

Poolside's open-weight model for agentic coding and long-horizon work

Text→Text
262K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Poolside
poolside

Laguna XS 2.1

poolside · laguna-xs

Agentic coding model from Poolside in the XS size class for local deployment

Text→Text
262K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Poolside
poolside

Laguna S 2.1

poolside · laguna-s

Agentic coding model from Poolside in the XS size class for local deployment

Text→Text
1.0M ctx · 33K outReasoningToolsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Poolside
poolside

Laguna XS.2

poolside · laguna-xs

Agentic coding model from Poolside in the XS size class for local deployment

Text→Text
262K ctx · 33K outReasoningToolsOpen
sakana

Fugu

sakana · fugu

Multi-agent model for routing expert agents across complex analytical tasks

TextImage→Text
1M ctx · undefined outReasoningToolsAttachments
sakana

Fugu Ultra

sakana · fugu-ultra

Quality-first multi-agent model for hard research, analysis, and competitions

TextImage→Text
1M ctx · undefined outReasoningToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 544.891/1M
🏷️ Termurah: NanoGPT
sakana

Sakana Namazu

sakana · sakana-namazu

Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows

TextImagePDF→Text
262K ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 17.255/1M•Output Rp 72.653/1M
🏷️ Termurah: Kilo Gateway
sakana

Fugu Max

sakana · fugu-max

Multi-agent model for routing expert agents across complex analytical tasks

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 36.327/1M•Output Rp 108.979/1M
🏷️ Termurah: NanoGPT
sakana

Fugu Ultra v2

sakana · fugu-ultra

Quality-first multi-agent model for hard research, analysis, and competitions

TextImagePDF→Text
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 90.816/1M•Output Rp 544.891/1M
🏷️ Termurah: Kilo Gateway
moonshotai

Kimi K3

moonshotai · kimi

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

TextImageVideo→Text
1.0M ctx · 1.0M outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
moonshotai

Kimi K2 Instruct 0905

moonshotai · kimi

September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding

Text→Text
262K ctx · 98K outToolsOpen
💰Harga:
Input Rp 10.898/1M•Output Rp 45.408/1M
🏷️ Termurah: Novita AI
moonshotai

Kimi K2.8 Preview

moonshotai · kimi

Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code

TextImageVideo→Text
1.0M ctx · undefined outReasoningToolsAttachments
moonshotai

Kimi K2 Thinking

moonshotai · kimi

Thinking Kimi model for slower research passes, planning, and hard technical questions

Text→Text
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Rp 10.530/1M•Output Rp 42.118/1M
🏷️ Termurah: Qiniu
moonshotai

Kimi K2 0711

moonshotai · kimi

Kimi model for long-context chat, coding, and agentic reasoning

Text→Text
131K ctx · 98K outToolsOpen
💰Harga:
Input Rp 10.353/1M•Output Rp 41.775/1M
🏷️ Termurah: Kilo Gateway
moonshotai

Kimi K3.1 Pro

moonshotai · kimi-pro

Multimodal Kimi model with a 1M-token context window and always-on reasoning, for coding, 3D creation and financial research

TextImageVideo→Text
1.0M ctx · 1.0M outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 25.429/1M•Output Rp 127.142/1M
🏷️ Termurah: NanoGPT
moonshotai

Kimi K2.7 Code Highspeed

moonshotai · kimi-code

Lower-latency Kimi Code variant for interactive edits and coding-agent loops

TextImageVideo→Text
262K ctx · 262K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 34.510/1M•Output Rp 145.305/1M
🏷️ Termurah: NanoGPT
moonshotai

Kimi K2.7 Code

moonshotai · kimi-code

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

TextImageVideo→Text
262K ctx · 262K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 10.898/1M•Output Rp 54.490/1M
🏷️ Termurah: NanoGPT
moonshotai

Kimi K2.6

moonshotai · kimi

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

TextImageVideo→Text
262K ctx · 262K outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1M•Output Gratis/1M
🏷️ Termurah: Nvidia
moonshotai

Kimi K2 Instruct

moonshotai · kimi

Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents

Text→Text
131K ctx · 33K outToolsOpen
💰Harga:
Input Rp 7.266/1M•Output Rp 32.694/1M
🏷️ Termurah: NanoGPT
moonshotai

Kimi K2 Thinking Turbo

moonshotai · kimi

Kimi reasoning model for long-horizon research, planning, and tool use

Text→Text
262K ctx · 262K outReasoningToolsOpen
moonshotai

Kimi K2.5

moonshotai · kimi

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

TextImageVideo→Text
262K ctx · 262K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 9.082/1M•Output Rp 45.408/1M
🏷️ Termurah: OpenRouter
recursive

Flint

recursive · flint

Open-weight mixture-of-experts model with about 2.5B active parameters for local coding agents

Text→Text
262K ctx · 262K outReasoningToolsOpen
thedrummer

Cydonia 24B V4.1

thedrummer · cydonia

Open-weight instruction model for adaptable chat and self-hosted production workloads

Text→Text
131K ctx · 118K outOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 9.082/1M
🏷️ Termurah: Kilo Gateway
thedrummer

Skyfall 36B V2

thedrummer · skyfall

Open-weight instruction model for adaptable chat and self-hosted production workloads

Text→Text
33K ctx · 29K outOpen
💰Harga:
Input Rp 9.990/1M•Output Rp 14.531/1M
🏷️ Termurah: Kilo Gateway
thedrummer

UnslopNemo 12B

thedrummer · unslopnemo

Open-weight instruction model for adaptable chat and self-hosted production workloads

Text→Text
1.0M ctx · 819K outOpen
💰Harga:
Input Rp 7.266/1M•Output Rp 7.266/1M
🏷️ Termurah: Kilo Gateway
minimax

MiniMax-M3

minimax · minimax-m

MiniMax multimodal model for long-context coding, perception, and agent planning

TextImageVideo→Text
1.0M ctx · 512K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 21.796/1M
🏷️ Termurah: Eden AI
minimax

MiniMax M1 80K

minimax · minimax-m

Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget

Text→Text
1M ctx · 80K outReasoningToolsOpen
minimax

MiniMax-M2.5

minimax · minimax-m

Prior MiniMax coding model for agent workflows, office edits, and automation

Text→Text
205K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 21.796/1M
🏷️ Termurah: Eden AI
minimax

MiniMax Text 01 (MiniMax)

minimax · minimax

MiniMax model for chat, coding, office work, and agentic tasks

Text→Text
1M ctx · 131K outTools
minimax

MiniMax-M2 Her

minimax · minimax-m

MiniMax M2 variant tuned for conversational and character-driven agent interactions

Text→Text
66K ctx · 2K outReasoningTools
minimax

MiniMax-M2.7-highspeed

minimax · minimax-m

Low-latency M2.7 variant for interactive coding plans and agent loops

Text→Text
205K ctx · 131K outReasoningToolsOpen
minimax

MiniMax-M2

minimax · minimax-m

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Text→Text
205K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 21.796/1M
🏷️ Termurah: Eden AI
minimax

MiniMax-M2.1

minimax · minimax-m

Earlier MiniMax agent model for practical coding and productivity tasks

Text→Text
205K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 21.796/1M
🏷️ Termurah: Eden AI
minimax

MiniMax-M2.5-highspeed

minimax · minimax-m

High-speed MiniMax model for low-latency coding and agent workflows

Text→Text
205K ctx · 131K outReasoningToolsOpen
minimax

MiniMax-M3.1-Flash-Preview

minimax · minimax-m-flash

Frontier multimodal coding model with 1M context window and tunable thinking depth

TextImageVideo→Text
1M ctx · 512K outReasoningToolsAttachments
minimax

MiniMax-M3.1-Flash

minimax · minimax-m-flash

Frontier multimodal coding model with 1M context window and tunable thinking depth

TextImageVideo→Text
1M ctx · 512K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 1.363/1M•Output Rp 5.449/1M
🏷️ Termurah: Eden AI
minimax

MiniMax image-01

minimax · minimax-image

MiniMax text-to-image generation model. The API also takes one character (portrait) reference to keep a person consistent, but it cannot edit an input image

Text→Image
0 ctx · 0 out
minimax

MiniMax H3

minimax · minimax-h

MiniMax general-purpose video model with multimodal references and synchronized stereo audio. Open H3-Base checkpoints; Context-IR and 2K regeneration are not included in the initial weights release.

TextImageVideoAudio→VideoAudio
0 ctx · 0 outAttachmentsOpen
minimax

MiniMax-M2.7

minimax · minimax-m

Open MiniMax flagship for coding agents, office automation, and complex environments

Text→Text
205K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 21.796/1M
🏷️ Termurah: Eden AI
tencent

Hy3

tencent · hy

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Text→Text
256K ctx · 128K outReasoningToolsOpen
💰Harga:
Input Rp 1.199/1M•Output Rp 4.723/1M
🏷️ Termurah: NanoGPT
tencent

Hy4

tencent · hy

A next-generation multimodal productivity model with significantly enhanced Agent and complex task execution capabilities.

TextImage→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 7.574/1M•Output Rp 22.713/1M
🏷️ Termurah: NanoGPT
tencent

Hy3 preview

tencent · hy

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Text→Text
256K ctx · 64K outReasoningToolsOpen
tencent

Hy-MT2-1.8B

tencent · hy-mt

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Text→Text
8K ctx · 4K outOpen
💰Harga:
Input Rp 800/1M•Output Rp 3.215/1M
🏷️ Termurah: Kilo Gateway
tencent

Hy4 preview

tencent · hy

A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.

Text→Text
1.0M ctx · 64K outReasoningToolsOpen
💰Harga:
Input Rp 15.148/1M•Output Rp 45.426/1M
🏷️ Termurah: NanoGPT
tencent

Hy4 flash

tencent · hy-flash

Tencent's lower-cost Hy4 tier for everyday agent and productivity tasks, with image understanding and a 1M-token context window.

TextImage→Text
1.0M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 636/1M•Output Rp 2.552/1M
🏷️ Termurah: NanoGPT
tencent

Hy-MT2-30B-A3B

tencent · hy-mt

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Text→Text
8K ctx · 4K outOpen
💰Harga:
Input Rp 1.345/1M•Output Rp 5.359/1M
🏷️ Termurah: Kilo Gateway
tencent

Hy-MT2-7B

tencent · hy-mt

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Text→Text
8K ctx · 4K outOpen
💰Harga:
Input Rp 1.345/1M•Output Rp 5.359/1M
🏷️ Termurah: Kilo Gateway
meragpt

Restyler 1

meragpt · restyler

meraGPT model that rewrites machine-written prose so it reads as if a person wrote it, keeping its structure

Text→Text
4K ctx · 2K out
huawei

openPangu 2.0 Pro

huawei · pangu-pro

Huawei's 505B MoE flagship (18B active) for long-horizon agents and 512K context work, Ascend-native with slow/fast thinking

Text→Text
524K ctx · 131K outReasoningToolsOpen
huawei

openPangu 2.0 Flash

huawei · pangu-flash

Huawei's 92B MoE lightweight (6B active) for fast agents and 512K context work, Ascend-native with slow/fast thinking

Text→Text
524K ctx · 131K outReasoningToolsOpen
vivgrid

Viv Fast

vivgrid · viv

Fast coding model

TextImage→Text
1M ctx · 256K outReasoningToolsAttachments
relace

Relace Apply 3

relace · relace-apply

General-purpose chat model for instruction following, writing, and analysis

Text→Text
256K ctx · 128K out
💰Harga:
Input Rp 15.439/1M•Output Rp 22.704/1M
🏷️ Termurah: Kilo Gateway
relace

Relace Search

relace · relace-search

Tool-capable chat model for instruction following and agentic application workflows

Text→Text
256K ctx · 128K outTools
💰Harga:
Input Rp 18.164/1M•Output Rp 54.490/1M
🏷️ Termurah: Kilo Gateway
undi95

ReMM SLERP 13B

undi95 · remm

Open-weight instruction model for adaptable chat and self-hosted production workloads

Text→Text
6K ctx · 6K outOpen
💰Harga:
Input Rp 5.449/1M•Output Rp 9.082/1M
🏷️ Termurah: Kilo Gateway