AI Model Catalog

Spesifikasi, Harga & Fitur Model AI

Bandingkan 352 model AI dari 192 provider. Context window, pricing, reasoning, tool calling, dan multimodal — semua di satu tempat.

tencent

Hy3 preview

tencent · Hy

Tencent Hy reasoning model for coding, instruction following, and agent tasks

TextText
256K ctx · 64K outReasoningToolsOpen
💰Harga:
Input Rp 3.075/1MOutput Rp 10.225/1M
🏷️ Termurah: ZenMux
tencent

Hy3

tencent · Hy

Tencent Hy reasoning model for coding, instruction following, and agent tasks

TextText
256K ctx · 64K outReasoningToolsOpen
💰Harga:
Input Rp 1.180/1MOutput Rp 4.648/1M
🏷️ Termurah: NanoGPT
nvidia

Llama 3.3 Nemotron Super 49B v1

nvidia · nemotron

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

TextText
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron 3 Nano 30B A3B

nvidia · nemotron

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

TextText
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron 3.5 Content Safety

nvidia · nemotron

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

TextImageText
128K ctx · 8K outReasoningAttachmentsOpen
nvidia

Nemotron Cascade 2 30B A3B

nvidia · nemotron

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

TextText
256K ctx · 33K outReasoningToolsOpen
nvidia

Nemotron 3 Content Safety

nvidia · nemotron

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

TextText
128K ctx · 4K outOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Llama 3.1 Nemotron 70B Instruct

nvidia · nemotron

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

TextText
128K ctx · 8K outToolsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron Nano 12B v2 VL

nvidia · nemotron

Nemotron multimodal model for visual reasoning and agentic AI workflows

TextImageVideoText
128K ctx · 128K outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron VoiceChat

nvidia · nemotron

Nemotron multimodal model for visual reasoning and agentic AI workflows

TextAudioText
128K ctx · 8K outToolsAttachmentsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Llama Nemotron Rerank VL 1B v2

nvidia · nemotron

Reranking model for improving retrieval quality in search and recommendation systems

TextImageText
128K ctx · 4K outAttachmentsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Llama 3.3 Nemotron Super 49B v1.5

nvidia · nemotron

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

TextText
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron 3 Super 120B A12B

nvidia · nemotron

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

TextText
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Rp 894/1MOutput Rp 4.469/1M
🏷️ Termurah: NanoGPT
nvidia

Nemotron 3 Nano Omni 30B A3B Reasoning

nvidia · nemotron

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

TextImageVideoAudioText
256K ctx · 66K outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron 3.5 Lightning 30B A3B

nvidia · nemotron

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

TextText
262K ctx · 262K outReasoningToolsStructuredOpen
💰Harga:
Input Rp 894/1MOutput Rp 3.576/1M
🏷️ Termurah: Vercel AI Gateway
nvidia

Nemotron Content Safety Reasoning 4B

nvidia · nemotron

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

TextText
128K ctx · 4K outReasoningOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron 3 Ultra 550B A55B

nvidia · nemotron

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

TextText
1M ctx · 128K outReasoningToolsOpen
💰Harga:
Input Rp 8.938/1MOutput Rp 39.326/1M
🏷️ Termurah: Kilo Gateway
nvidia

Mistral Nemotron

nvidia · nemotron

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

TextText
128K ctx · 8K outToolsOpen
nvidia

Llama 3.1 Nemotron Safety Guard 8B v3

nvidia · nemotron

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

TextText
128K ctx · 4K outOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Nemotron Nano 9B v2

nvidia · nemotron

Compact Nemotron model for efficient reasoning and deployable AI agents

TextText
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 1.073/1MOutput Rp 4.112/1M
🏷️ Termurah: Vercel AI Gateway
nvidia

Llama 3.1 Nemotron Ultra 253B

nvidia · nemotron

Flagship Nemotron model for high-throughput reasoning and complex agents

TextText
128K ctx · 8K outReasoningToolsOpen
nvidia

Nemotron Mini 4B Instruct

nvidia · nemotron

Compact Nemotron model for efficient reasoning and deployable AI agents

TextText
128K ctx · 8K outToolsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
nvidia

Llama Nemotron Embed VL 1B v2

nvidia · nemotron

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

TextImageText
33K ctx · 2K outAttachmentsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
aisingapore

Gemma-SEA-LION-v4-27B-IT

aisingapore · gemma

Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following

TextText
128K ctx · 128K outOpen
microsoft

Phi-4-mini

microsoft · phi

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

TextText
128K ctx · 4K outToolsOpen
microsoft

MAI-Code-1-Flash

microsoft · mai

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

TextText
256K ctx · 128K outReasoningToolsStructured
microsoft

MAI-Code-1.1-Flash

microsoft · mai

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

TextImageText
256K ctx · 128K outReasoningToolsAttachmentsStructured
deepseek

DeepSeek-R1-Distill-Qwen-32B

deepseek · deepseek-thinking

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

TextText
131K ctx · 33K outReasoningOpen
💰Harga:
Input Rp 5.363/1MOutput Rp 5.363/1M
🏷️ Termurah: NovitaAI
deepseek

DeepSeek-R1

deepseek · deepseek-thinking

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

TextText
128K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Rp 12.513/1MOutput Rp 44.689/1M
🏷️ Termurah: Kilo Gateway
deepseek

DeepSeek V3 0324

deepseek · deepseek

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

TextText
164K ctx · 164K outToolsOpen
💰Harga:
Input Rp 4.827/1MOutput Rp 20.021/1M
🏷️ Termurah: NovitaAI
deepseek

DeepSeek V4 Flash

deepseek · deepseek-flash

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

TextText
1M ctx · 384K outReasoningToolsStructuredOpen
💰Harga:
Input Rp 1.477/1MOutput Rp 2.953/1M
🏷️ Termurah: OpenRouter
deepseek

DeepSeek V4 Pro 0813

deepseek · deepseek-thinking

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

TextText
1M ctx · 384K outReasoningToolsStructured
💰Harga:
Input Rp 11.798/1MOutput Rp 35.393/1M
🏷️ Termurah: Merge Gateway
deepseek

DeepSeek-V3.1

deepseek · deepseek

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

TextText
131K ctx · 8K outReasoningToolsOpen
💰Harga:
Input Rp 4.469/1MOutput Rp 16.982/1M
🏷️ Termurah: Vercel AI Gateway
deepseek

DeepSeek V4 Pro

deepseek · deepseek-thinking

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

TextText
1M ctx · 384K outReasoningToolsStructuredOpen
💰Harga:
Input Rp 7.776/1MOutput Rp 15.552/1M
🏷️ Termurah: ZenMux
deepseek

DeepSeek-V3

deepseek · deepseek

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

TextText
131K ctx · 8K outToolsOpen
💰Harga:
Input Rp 4.827/1MOutput Rp 20.021/1M
🏷️ Termurah: Vercel AI Gateway
deepseek

DeepSeek V3.2

deepseek · deepseek

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

TextText
128K ctx · 64K outReasoningToolsStructuredOpen
💰Harga:
Input Rp 4.809/1MOutput Rp 7.151/1M
🏷️ Termurah: Kilo Gateway
deepseek

DeepSeek Chat

deepseek · deepseek

DeepSeek chat model for instruction following, coding, and analysis

TextText
1M ctx · 384K outToolsAttachmentsOpen
💰Harga:
Input Rp 2.503/1MOutput Rp 5.006/1M
🏷️ Termurah: OrcaRouter
deepseek

DeepSeek Reasoner

deepseek · deepseek-thinking

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

TextText
1M ctx · 384K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 5.006/1MOutput Rp 7.508/1M
🏷️ Termurah: Eden AI
deepseek

DeepSeek OCR 2

deepseek ·

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

TextImageText
8K ctx · 8K outAttachmentsOpen
💰Harga:
Input Rp 537/1MOutput Rp 537/1M
🏷️ Termurah: NovitaAI
deepseek

DeepSeek V4 Flash 0731

deepseek · deepseek-flash

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

TextText
1M ctx · 384K outReasoningToolsStructuredOpen
💰Harga:
Input Rp 2.324/1MOutput Rp 4.648/1M
🏷️ Termurah: Vercel AI Gateway
arcee-ai

Trinity Large Preview

arcee-ai · trinity

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

TextText
524K ctx · 262K outToolsOpen
arcee-ai

Trinity Mini

arcee-ai · trinity

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

TextText
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 805/1MOutput Rp 2.682/1M
🏷️ Termurah: Vercel AI Gateway
arcee-ai

Trinity Large Thinking

arcee-ai · trinity

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

TextText
524K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Rp 3.933/1MOutput Rp 15.194/1M
🏷️ Termurah: Kilo Gateway
arcee-ai

Trinity Nano Preview

arcee-ai · trinity

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

TextText
131K ctx · 131K outToolsOpen
google

Gemini 3.1 Flash TTS Preview

google · gemini-flash

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

TextAudio
8K ctx · 16K out
google

Gemma 4 26B A4B IT

google · gemma

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

TextImageText
262K ctx · 33K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 1.073/1MOutput Rp 5.899/1M
🏷️ Termurah: OrcaRouter
google

Nano Banana Pro

google · gemini-pro

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

TextImageTextImage
66K ctx · 33K outReasoningAttachments
💰Harga:
Input Rp 35.751/1MOutput Rp 214.503/1M
🏷️ Termurah: Kilo Gateway
google

Nano Banana Pro

google · gemini-pro

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

TextImageTextImage
66K ctx · 33K outReasoningAttachments
💰Harga:
Input Rp 35.751/1MOutput Rp 214.503/1M
🏷️ Termurah: Kilo Gateway
google

Gemini Flash-Lite Latest

google · gemini-flash-lite

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 4.469/1MOutput Rp 26.813/1M
🏷️ Termurah: Merge Gateway
google

Gemini 2.0 Flash

google · gemini-flash

Earlier Gemini Flash workhorse for responsive multimodal apps and tool use

TextImageAudioVideoPDFText
1.0M ctx · 8K outToolsAttachmentsStructured
💰Harga:
Input Rp 1.788/1MOutput Rp 7.508/1M
🏷️ Termurah: Poe
google

Gemini 2.5 Flash TTS

google · gemini-flash

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

TextAudio
33K ctx · 16K out
google

Gemini 3.5 Flash Lite

google · gemini-flash-lite

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 5.363/1MOutput Rp 44.689/1M
🏷️ Termurah: Kilo Gateway
google

Nano Banana 2 Lite

google · gemini-flash-lite

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

TextImageTextImage
66K ctx · 4K outReasoningToolsAttachments
💰Harga:
Input Rp 4.469/1MOutput Rp 26.813/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 3.1 Pro Preview

google · gemini-pro

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 35.751/1MOutput Rp 214.503/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 3.1 Pro Preview Custom Tools

google · gemini-pro

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 35.751/1MOutput Rp 214.503/1M
🏷️ Termurah: Kilo Gateway
google

Gemini Deep Research Preview

google · gemini-pro

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

TextImageVideoAudioPDFTextImage
1.0M ctx · 66K outReasoningToolsAttachments
google

Gemini 2.5 Flash-Lite

google · gemini-flash-lite

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

TextImageAudioVideoPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 1.788/1MOutput Rp 1.788/1M
🏷️ Termurah: LLMTR
google

Gemini Robotics-ER 1.6 Preview

google · gemini

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

TextImageVideoAudioText
131K ctx · 66K outReasoningToolsAttachmentsStructured
google

Gemma 4 31B IT

google · gemma

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

TextImageText
262K ctx · 33K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
google

Gemini 2.5 Computer Use Preview

google · gemini-pro

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

TextImageText
128K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 22.345/1MOutput Rp 178.753/1M
🏷️ Termurah: Merge Gateway
google

Lyria 3 Clip Preview

google · lyria

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

TextImageTextAudio
131K ctx · 66K outAttachments
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Kilo Gateway
google

Veo 3.1 Fast Preview

google · veo

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

TextImageVideoVideo
1K ctx · 0 outAttachments
google

Gemini Embedding 001

google · gemini

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

TextText
2K ctx · 1 out
💰Harga:
Input Rp 2.682/1MOutput Gratis/1M
🏷️ Termurah: Merge Gateway
google

Gemini Flash Latest

google · gemini-flash

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 13.407/1MOutput Rp 67.033/1M
🏷️ Termurah: NanoGPT
google

Gemini 3.5 Flash

google · gemini-flash

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 26.813/1MOutput Rp 160.877/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 3.5 Live Translate Preview

google · gemini-pro

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

AudioAudioText
131K ctx · 66K out
google

Veo 3.1 Lite Preview

google · veo

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

TextImageVideo
1K ctx · 0 outAttachments
google

Gemini Omni Flash Preview

google · gemini

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

TextImageVideoVideo
1.0M ctx · 58K outReasoningAttachments
💰Harga:
Input Rp 26.813/1MOutput Rp 160.877/1M
🏷️ Termurah: Vercel AI Gateway
google

Gemini 3.1 Flash Lite

google · gemini-flash-lite

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 4.469/1MOutput Rp 26.813/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 2.5 Flash

google · gemini-flash

Fast Gemini workhorse for multimodal apps where latency and price matter

TextImageAudioVideoPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 3.754/1MOutput Rp 32.176/1M
🏷️ Termurah: Poe
google

Gemini 3 Pro Preview

google · gemini-pro

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 35.751/1MOutput Rp 214.503/1M
🏷️ Termurah: Merge Gateway
google

Veo 3.1 Preview

google · veo

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

TextImageVideo
1K ctx · 1 outAttachments
google

Gemini 2.5 Pro TTS

google · gemini-pro

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

TextAudio
33K ctx · 16K out
google

Gemini Embedding 2

google · gemini

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

TextImageAudioVideoPDFText
8K ctx · 3K outAttachments
google

Gemma 4 E4B IT

google · gemma

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

TextImageAudioText
131K ctx · 8K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 358/1MOutput Rp 1.788/1M
🏷️ Termurah: Deep Infra
google

Gemma 4 E2B IT

google · gemma

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

TextImageAudioText
131K ctx · 8K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 1.788/1MOutput Rp 1.788/1M
🏷️ Termurah: Pioneer
google

Gemini 3.6 Flash

google · gemini-flash

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 13.407/1MOutput Rp 67.033/1M
🏷️ Termurah: Kilo Gateway
google

Nano Banana 2

google · gemini-flash

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

TextImageVideoPDFTextImage
131K ctx · 33K outReasoningAttachments
💰Harga:
Input Rp 8.938/1MOutput Rp 53.626/1M
🏷️ Termurah: Kilo Gateway
google

Nano Banana 2

google · gemini-flash

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

TextImagePDFTextImage
66K ctx · 66K outReasoningAttachments
💰Harga:
Input Rp 8.938/1MOutput Rp 53.626/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 2.0 Flash-Lite

google · gemini-flash-lite

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

TextImageAudioVideoPDFText
1.0M ctx · 8K outToolsAttachmentsStructured
💰Harga:
Input Rp 930/1MOutput Rp 3.754/1M
🏷️ Termurah: Poe
google

Lyria 3 Pro Preview

google · lyria

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

TextImageTextAudio
131K ctx · 8K outAttachments
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 3.1 Flash Lite Preview

google · gemini-flash-lite

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 4.469/1MOutput Rp 26.813/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 3 Flash Preview

google · gemini-flash

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 8.938/1MOutput Rp 53.626/1M
🏷️ Termurah: Kilo Gateway
google

Nano Banana

google · gemini-flash

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

TextImageTextImage
33K ctx · 33K outReasoningAttachments
💰Harga:
Input Rp 5.363/1MOutput Rp 44.689/1M
🏷️ Termurah: Kilo Gateway
google

Gemini 2.5 Pro

google · gemini-pro

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

TextImageAudioVideoPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 15.552/1MOutput Rp 125.127/1M
🏷️ Termurah: Poe
google

Deep Research Max Preview

google · gemini-pro

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

TextImageVideoAudioPDFTextImage
1.0M ctx · 66K outReasoningToolsAttachments
google

Gemini 3.1 Flash Live Preview

google · gemini-flash

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

TextImageVideoAudioTextAudio
131K ctx · 66K outReasoningToolsAttachments
google

Gemini 3.7 Flash

google · gemini-flash

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

TextImageVideoAudioPDFText
1.0M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 6.704/1MOutput Rp 33.517/1M
🏷️ Termurah: OpenRouter
meta

Llama-Guard-3-8B

meta · llama

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

TextText
128K ctx · 4K outOpen
meta

Llama-3.3-70B-Instruct

meta · llama

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

TextText
128K ctx · 4K outToolsAttachmentsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
meta

Llama 4 Scout 17B Instruct

meta · llama

Open Llama with long-context vision for efficient multimodal agents

TextImageText
3.5M ctx · 16K outToolsAttachmentsOpen
meta

Muse Glimmer 30B

meta · muse

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.

TextImageText
131K ctx · 131K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
meta

Llama-3.1-8B-Instruct

meta · llama

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

TextText
128K ctx · 4K outToolsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
meta

Muse Spark 1.2

meta · muse

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.

TextImageVideoPDFAudioText
1.0M ctx · 131K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 22.345/1MOutput Rp 75.970/1M
🏷️ Termurah: Kilo Gateway
meta

Muse Spark 1.1

meta · muse

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

TextImagePDFVideoText
1M ctx · 32K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 22.345/1MOutput Rp 75.970/1M
🏷️ Termurah: Pioneer
meta

Llama-3.2-1B

meta · llama

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

TextText
131K ctx · 8K outOpen
meta

Llama 4 Maverick 17B Instruct

meta · llama

Open multimodal Llama for strong reasoning with efficient everyday serving

TextImageText
1M ctx · 16K outToolsAttachmentsOpen
meta

Llama-3.2-3B

meta · llama

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

TextText
131K ctx · 8K outOpen
meta

Llama-3.2-11B-Vision-Instruct

meta · llama

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

TextImageText
128K ctx · 4K outToolsAttachmentsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
sdaia

ALLaM-2-7b

sdaia ·

ALLaM-2-7b instruction tuned model by SDAIA

TextText
4K ctx · 4K outOpen
poolside

Laguna M.1

poolside · laguna

Poolside's open-weight model for agentic coding and long-horizon work

TextText
262K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Poolside
poolside

Laguna S 2.1

poolside · laguna

Agentic coding model from Poolside in the XS size class for local deployment

TextText
1.0M ctx · 33K outReasoningToolsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Poolside
poolside

Laguna XS 2.1

poolside · laguna

Agentic coding model from Poolside in the XS size class for local deployment

TextText
262K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: LLMTR
poolside

Laguna XS.2

poolside · laguna

Agentic coding model from Poolside in the XS size class for local deployment

TextText
262K ctx · 33K outReasoningToolsOpen
bytedance-seed

Seed 2.0 Code

bytedance-seed · seed

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

TextImageVideoText
262K ctx · 131K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 8.938/1MOutput Rp 53.626/1M
🏷️ Termurah: Kilo Gateway
bytedance-seed

Seed 2.1 Turbo

bytedance-seed · seed

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

TextImageVideoText
256K ctx · 256K outReasoningToolsAttachments
bytedance-seed

Seed 1.6

bytedance-seed · seed

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

TextText
256K ctx · 64K outReasoningTools
bytedance-seed

Seed Character

bytedance-seed · seed

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

TextImageVideoText
256K ctx · 256K outReasoningToolsAttachments
bytedance-seed

Seed 1.6 Vision

bytedance-seed · seed

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

TextImageText
256K ctx · 32K outToolsAttachments
bytedance-seed

Seed 2.0 Pro

bytedance-seed · seed

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

TextImageVideoText
256K ctx · 128K outReasoningToolsAttachments
bytedance-seed

Seed Evolving

bytedance-seed · seed

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

TextImageVideoText
256K ctx · 256K outReasoningToolsAttachments
bytedance-seed

Seed 2.1 Pro

bytedance-seed · seed

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

TextImageVideoText
256K ctx · 256K outReasoningToolsAttachments
bytedance-seed

Seed 1.6 Flash

bytedance-seed · seed

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

TextText
256K ctx · 32K outTools
bytedance-seed

Seed 2.0 Mini

bytedance-seed · seed

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

TextImageVideoText
256K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Rp 1.788/1MOutput Rp 7.151/1M
🏷️ Termurah: Kilo Gateway
bytedance-seed

Seed 1.8

bytedance-seed · seed

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

TextText
256K ctx · 64K outReasoningTools
bytedance-seed

Seed 2.0 Lite

bytedance-seed · seed

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

TextImageVideoText
256K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Rp 4.469/1MOutput Rp 35.751/1M
🏷️ Termurah: Kilo Gateway
moonshotai

Kimi K2.7 Code

moonshotai · kimi-k2

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

TextImageVideoText
262K ctx · 262K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 12.334/1MOutput Rp 62.385/1M
🏷️ Termurah: Ambient
moonshotai

Kimi K3

moonshotai · kimi-k3

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

TextImageVideoText
1.0M ctx · 131K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 53.626/1MOutput Rp 223.441/1M
🏷️ Termurah: ai&
moonshotai

Kimi K2 Thinking Turbo

moonshotai · kimi-thinking

Kimi reasoning model for long-horizon research, planning, and tool use

TextText
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Rp 20.557/1MOutput Rp 143.002/1M
🏷️ Termurah: ZenMux
moonshotai

Kimi K2.5

moonshotai · kimi-k2

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

TextImageVideoText
262K ctx · 262K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 5.363/1MOutput Rp 33.963/1M
🏷️ Termurah: NanoGPT
moonshotai

Kimi K2.7 Code Highspeed

moonshotai · kimi-k2

Lower-latency Kimi Code variant for interactive edits and coding-agent loops

TextImageVideoText
262K ctx · 262K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 33.963/1MOutput Rp 143.002/1M
🏷️ Termurah: Vercel AI Gateway
moonshotai

Kimi K2 Thinking

moonshotai · kimi-thinking

Thinking Kimi model for slower research passes, planning, and hard technical questions

TextText
262K ctx · 262K outReasoningToolsOpen
💰Harga:
Input Rp 8.402/1MOutput Rp 35.751/1M
🏷️ Termurah: Vercel AI Gateway
moonshotai

Kimi K2.6

moonshotai · kimi-k2

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

TextImageVideoText
262K ctx · 262K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
anthropic

Claude Opus 4

anthropic · claude-opus

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

TextImagePDFText
200K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Rp 268.129/1MOutput Rp 1.340.641/1M
🏷️ Termurah: Merge Gateway
anthropic

Claude Opus 4.7

anthropic · claude-opus

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

TextImagePDFText
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 89.377/1MOutput Rp 446.881/1M
🏷️ Termurah: Eden AI
anthropic

Claude Mythos 5

anthropic · claude-mythos

Restricted Claude model for advanced cybersecurity and biology research workflows

TextImagePDFText
1M ctx · 128K outReasoningToolsAttachmentsStructured
anthropic

Claude Opus 4.1

anthropic · claude-opus

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

TextImagePDFText
200K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Rp 268.129/1MOutput Rp 1.340.641/1M
🏷️ Termurah: Merge Gateway
anthropic

Claude Sonnet 3.5 v2

anthropic · claude-sonnet

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

TextImagePDFText
200K ctx · 8K outToolsAttachments
anthropic

Claude Opus 4.8

anthropic · claude-opus

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

TextImagePDFText
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 89.377/1MOutput Rp 446.881/1M
🏷️ Termurah: Eden AI
anthropic

Claude Haiku 3.5

anthropic · claude-haiku

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

TextImagePDFText
200K ctx · 8K outToolsAttachments
anthropic

Claude Opus 4.1 (latest)

anthropic · claude-opus

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

TextImagePDFText
200K ctx · 32K outReasoningToolsAttachments
anthropic

Claude Sonnet 5

anthropic · claude-sonnet

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

TextImagePDFText
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 35.751/1MOutput Rp 178.753/1M
🏷️ Termurah: Kilo Gateway
anthropic

Claude Sonnet 3.7

anthropic · claude-sonnet

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

TextImagePDFText
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 53.626/1MOutput Rp 268.129/1M
🏷️ Termurah: Merge Gateway
anthropic

Claude Sonnet 4.5

anthropic · claude-sonnet

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

TextImagePDFText
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 53.626/1MOutput Rp 268.129/1M
🏷️ Termurah: Merge Gateway
anthropic

Claude Opus 4.5 (latest)

anthropic · claude-opus

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

TextImagePDFText
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 89.377/1MOutput Rp 446.881/1M
🏷️ Termurah: Eden AI
anthropic

Claude Sonnet 4.6

anthropic · claude-sonnet

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

TextImagePDFText
1M ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 53.626/1MOutput Rp 268.129/1M
🏷️ Termurah: Eden AI
anthropic

Claude Opus 4 (latest)

anthropic · claude-opus

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

TextImagePDFText
200K ctx · 32K outReasoningToolsAttachments
anthropic

Claude Haiku 4.5

anthropic · claude-haiku

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

TextImagePDFText
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 17.876/1MOutput Rp 89.377/1M
🏷️ Termurah: Merge Gateway
anthropic

Claude Sonnet 4.5 (latest)

anthropic · claude-sonnet

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

TextImagePDFText
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 53.626/1MOutput Rp 268.129/1M
🏷️ Termurah: Perplexity Agent
anthropic

Claude Opus 4.5

anthropic · claude-opus

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

TextImagePDFText
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 89.377/1MOutput Rp 446.881/1M
🏷️ Termurah: Eden AI
anthropic

Claude Fable 5

anthropic · claude-fable

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

TextImagePDFText
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 178.753/1MOutput Rp 893.761/1M
🏷️ Termurah: Kilo Gateway
anthropic

Claude Sonnet 4

anthropic · claude-sonnet

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

TextImagePDFText
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 53.626/1MOutput Rp 268.129/1M
🏷️ Termurah: Merge Gateway
anthropic

Claude Sonnet 4 (latest)

anthropic · claude-sonnet

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

TextImagePDFText
200K ctx · 64K outReasoningToolsAttachments
anthropic

Claude Haiku 4.5 (latest)

anthropic · claude-haiku

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

TextImagePDFText
200K ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 17.876/1MOutput Rp 89.377/1M
🏷️ Termurah: Perplexity Agent
anthropic

Claude Opus 4.6

anthropic · claude-opus

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

TextImagePDFText
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 89.377/1MOutput Rp 446.881/1M
🏷️ Termurah: Eden AI
anthropic

Claude Haiku 3

anthropic · claude-haiku

Legacy model retained for compatibility with older integrations

TextImagePDFText
200K ctx · 4K outToolsAttachments
anthropic

Claude Opus 5

anthropic · claude-opus

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

TextImagePDFText
1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 89.377/1MOutput Rp 446.881/1M
🏷️ Termurah: Kilo Gateway
cohere

Aya Expanse 32B

cohere ·

Open multilingual model optimized for generation across 23 languages

TextText
128K ctx · 4K outOpen
cohere

Command A Reasoning

cohere · command-a

Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows

TextText
256K ctx · 32K outReasoningToolsOpen
cohere

Aya Vision 32B

cohere ·

Open multilingual vision model for OCR, visual reasoning, and image question answering

TextImageText
16K ctx · 4K outAttachmentsOpen
cohere

Command R+

cohere · command-r

Cohere's RAG workhorse for long-context enterprise search and tool use

TextText
128K ctx · 4K outToolsOpen
💰Harga:
Input Rp 44.689/1MOutput Rp 178.753/1M
🏷️ Termurah: Kilo Gateway
cohere

Command A Translate

cohere · command-a

Translation model for multilingual conversion, localization, and cross-language workflows

TextText
8K ctx · 8K outToolsOpen
cohere

Command R7B Arabic

cohere · command-r

Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge

TextText
128K ctx · 4K outToolsOpen
cohere

Aya Expanse 8B

cohere ·

Compact open multilingual model optimized for generation across 23 languages

TextText
8K ctx · 4K outOpen
cohere

Command A Vision

cohere · command-a

Cohere vision model for multilingual document analysis, OCR, and image understanding

TextImageText
128K ctx · 8K outAttachmentsOpen
cohere

Command A Plus

cohere · command-a

Cohere's stronger command model for multilingual agents and enterprise workflows

TextImageText
128K ctx · 64K outReasoningToolsAttachmentsStructuredOpen
cohere

Command A

cohere · command-a

Cohere command model for multilingual enterprise agents, tools, and chat

TextText
256K ctx · 8K outToolsOpen
💰Harga:
Input Rp 44.689/1MOutput Rp 178.753/1M
🏷️ Termurah: Eden AI
cohere

Command R7B

cohere · command-r

Cohere retrieval model for long-context chat and enterprise RAG workflows

TextText
128K ctx · 4K outToolsOpen
💰Harga:
Input Rp 671/1MOutput Rp 2.682/1M
🏷️ Termurah: Kilo Gateway
cohere

Command R

cohere · command-r

Cohere retrieval model for long-context chat and enterprise RAG workflows

TextText
128K ctx · 4K outToolsOpen
💰Harga:
Input Rp 2.682/1MOutput Rp 10.726/1M
🏷️ Termurah: Kilo Gateway
cohere

North Mini Code

cohere · north

Cohere coding model for practical software engineering and agentic edits

TextText
256K ctx · 64K outReasoningToolsStructuredOpen
cohere

Aya Vision 8B

cohere ·

Compact open multilingual vision model for OCR and visual question answering

TextImageText
16K ctx · 4K outAttachmentsOpen
openai

GPT-4o

openai · gpt

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

TextImagePDFText
128K ctx · 16K outToolsAttachmentsStructured
💰Harga:
Input Rp 22.345/1MOutput Rp 89.377/1M
🏷️ Termurah: Cloudflare AI Gateway
openai

GPT-Image-1.5

openai · gpt-image

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

TextImageTextImage
0 ctx · 0 outAttachments
💰Harga:
Input Rp 89.377/1MOutput Rp 572.007/1M
🏷️ Termurah: Vercel AI Gateway
openai

GPT-5.3 Chat (latest)

openai · gpt

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

TextImageText
128K ctx · 16K outToolsAttachmentsStructured
💰Harga:
Input Rp 31.282/1MOutput Rp 250.253/1M
🏷️ Termurah: Cloudflare AI Gateway
openai

GPT-5 Nano

openai · gpt-nano

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 805/1MOutput Rp 6.436/1M
🏷️ Termurah: Poe
openai

GPT-4o mini

openai · gpt-mini

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

TextImagePDFText
128K ctx · 16K outToolsAttachmentsStructured
💰Harga:
Input Rp 1.341/1MOutput Rp 5.363/1M
🏷️ Termurah: Cloudflare AI Gateway
openai

GPT-3.5-turbo

openai · gpt

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

TextText
16K ctx · 4K out
💰Harga:
Input Rp 8.044/1MOutput Rp 25.026/1M
🏷️ Termurah: Poe
openai

o1-pro

openai · o-pro

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

TextImageText
200K ctx · 100K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 2.502.529/1MOutput Rp 9.652.610/1M
🏷️ Termurah: Poe
openai

Whisper 3 Large

openai · whisper

Open Whisper checkpoint for robust multilingual transcription and captioning

AudioText
448 ctx · 4K outOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
openai

GPT-5.5 Pro

openai · gpt-pro

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

TextImagePDFText
1.1M ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 487.506/1MOutput Rp 2.925.034/1M
🏷️ Termurah: Poe
openai

GPT-4 Turbo

openai · gpt

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

TextImageText
128K ctx · 4K outToolsAttachments
💰Harga:
Input Rp 160.877/1MOutput Rp 482.631/1M
🏷️ Termurah: Poe
openai

GPT-4

openai · gpt

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

TextText
8K ctx · 8K outToolsAttachments
💰Harga:
Input Rp 536.257/1MOutput Rp 1.072.513/1M
🏷️ Termurah: Kilo Gateway
openai

GPT-5 Chat (latest)

openai · gpt-codex

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

TextImageText
400K ctx · 128K outReasoningAttachmentsStructured
💰Harga:
Input Rp 22.345/1MOutput Rp 178.753/1M
🏷️ Termurah: Merge Gateway
openai

GPT-5.6 Sol

openai · gpt-sol

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

TextImagePDFText
1.1M ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 44.689/1MOutput Rp 268.129/1M
🏷️ Termurah: Vercel AI Gateway
openai

o3-pro

openai · o-pro

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

TextImageText
200K ctx · 100K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 321.754/1MOutput Rp 1.287.015/1M
🏷️ Termurah: Poe
openai

o3-deep-research

openai · o

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

TextImageText
200K ctx · 100K outReasoningToolsAttachments
💰Harga:
Input Rp 160.877/1MOutput Rp 643.508/1M
🏷️ Termurah: Poe
openai

GPT-5.4 Pro

openai · gpt-pro

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

TextImageText
1.1M ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 482.631/1MOutput Rp 2.860.033/1M
🏷️ Termurah: Poe
openai

GPT-5

openai · gpt

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 19.663/1MOutput Rp 160.877/1M
🏷️ Termurah: Poe
openai

GPT-5.1 Codex mini

openai · gpt-codex

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 3.933/1MOutput Rp 32.176/1M
🏷️ Termurah: Poe
openai

GPT-5-Codex

openai · gpt-codex

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

TextImageText
400K ctx · 128K outReasoningToolsStructured
💰Harga:
Input Rp 19.663/1MOutput Rp 160.877/1M
🏷️ Termurah: Poe
openai

GPT-5 Mini

openai · gpt-mini

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 3.933/1MOutput Rp 32.176/1M
🏷️ Termurah: Poe
openai

GPT-5.6 Luna

openai · gpt-luna

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

TextImagePDFText
1.1M ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 1.788/1MOutput Rp 10.726/1M
🏷️ Termurah: NanoGPT
openai

GPT-5.3 Codex

openai · gpt-codex

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

TextImagePDFText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 28.601/1MOutput Rp 232.378/1M
🏷️ Termurah: Poe
openai

GPT OSS 120B

openai · gpt-oss

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

TextText
131K ctx · 33K outReasoningToolsStructuredOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
openai

GPT-5.3 Codex Spark

openai · gpt-codex-spark

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

TextImagePDFText
128K ctx · 32K outReasoningToolsAttachmentsStructured
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Poe
openai

GPT-4.1 nano

openai · gpt-nano

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

TextImageText
1.0M ctx · 33K outToolsAttachmentsStructured
💰Harga:
Input Rp 1.609/1MOutput Rp 6.436/1M
🏷️ Termurah: Poe
openai

o1

openai · o

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

TextImagePDFText
200K ctx · 100K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 250.253/1MOutput Rp 965.261/1M
🏷️ Termurah: Poe
openai

GPT-5.2

openai · gpt

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 28.601/1MOutput Rp 232.378/1M
🏷️ Termurah: Poe
openai

GPT-Image-1

openai · gpt-image

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

TextImageImage
0 ctx · 0 outAttachments
💰Harga:
Input Rp 89.377/1MOutput Rp 715.009/1M
🏷️ Termurah: Vercel AI Gateway
openai

GPT-Realtime-2.1

openai · gpt

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

TextAudioImageTextAudio
128K ctx · 32K outReasoningToolsAttachments
💰Harga:
Input Rp 71.501/1MOutput Rp 429.005/1M
🏷️ Termurah: Vercel AI Gateway
openai

GPT-5.4 mini

openai · gpt-mini

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 12.156/1MOutput Rp 71.501/1M
🏷️ Termurah: Poe
openai

GPT-4o (2024-05-13)

openai · gpt

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

TextImageText
128K ctx · 4K outToolsAttachmentsStructured
💰Harga:
Input Rp 89.377/1MOutput Rp 268.129/1M
🏷️ Termurah: Kilo Gateway
openai

o3

openai · o

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

TextImagePDFText
200K ctx · 100K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 32.176/1MOutput Rp 128.702/1M
🏷️ Termurah: Poe
openai

o4-mini-deep-research

openai · o-mini

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

TextImageText
200K ctx · 100K outReasoningToolsAttachments
💰Harga:
Input Rp 32.176/1MOutput Rp 128.702/1M
🏷️ Termurah: Poe
openai

GPT-5 Pro

openai · gpt-pro

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

TextImageText
400K ctx · 272K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 250.253/1MOutput Rp 1.966.273/1M
🏷️ Termurah: Poe
openai

GPT-5.5

openai · gpt

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

TextImagePDFText
1.1M ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 81.252/1MOutput Rp 487.506/1M
🏷️ Termurah: Poe
openai

GPT-5.5 Instant

openai ·

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

TextImagePDFText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 89.377/1MOutput Rp 536.257/1M
🏷️ Termurah: ZenMux
openai

GPT-5.2 Codex

openai · gpt-codex

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

TextImagePDFText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 28.601/1MOutput Rp 232.378/1M
🏷️ Termurah: Poe
openai

GPT-4.1

openai · gpt

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

TextImagePDFText
1.0M ctx · 33K outToolsAttachmentsStructured
💰Harga:
Input Rp 32.176/1MOutput Rp 128.702/1M
🏷️ Termurah: Poe
openai

GPT-4o (2024-08-06)

openai · gpt

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

TextImageText
128K ctx · 16K outToolsAttachmentsStructured
💰Harga:
Input Rp 44.689/1MOutput Rp 178.753/1M
🏷️ Termurah: Kilo Gateway
openai

GPT-5.6 Terra

openai · gpt-terra

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

TextImagePDFText
1.1M ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 17.876/1MOutput Rp 107.252/1M
🏷️ Termurah: NanoGPT
openai

o4-mini

openai · o-mini

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

TextImageText
200K ctx · 100K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 17.697/1MOutput Rp 71.501/1M
🏷️ Termurah: Poe
openai

GPT-5.4

openai · gpt

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

TextImagePDFText
1.1M ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 39.326/1MOutput Rp 250.253/1M
🏷️ Termurah: Poe
openai

o3-mini

openai · o-mini

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

TextText
200K ctx · 100K outReasoningToolsStructured
💰Harga:
Input Rp 17.697/1MOutput Rp 71.501/1M
🏷️ Termurah: Poe
openai

GPT-4o (2024-11-20)

openai · gpt

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

TextImageText
128K ctx · 16K outToolsAttachmentsStructured
💰Harga:
Input Rp 44.689/1MOutput Rp 178.753/1M
🏷️ Termurah: Kilo Gateway
openai

GPT OSS Safeguard 120B

openai · gpt-oss

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

TextText
131K ctx · 33K outReasoningToolsStructuredOpen
💰Harga:
Input Rp 2.682/1MOutput Rp 10.726/1M
🏷️ Termurah: Merge Gateway
openai

GPT Realtime Whisper

openai · whisper

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

AudioText
0 ctx · 0 out
openai

GPT-5.2 Chat

openai · gpt-codex

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

TextImageText
128K ctx · 16K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 31.282/1MOutput Rp 250.253/1M
🏷️ Termurah: Cloudflare AI Gateway
openai

GPT-5.2 Pro

openai · gpt-pro

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

TextImageText
400K ctx · 128K outReasoningToolsAttachments
💰Harga:
Input Rp 339.629/1MOutput Rp 2.681.281/1M
🏷️ Termurah: Poe
openai

GPT-5.1 Chat

openai · gpt-codex

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

TextImageText
128K ctx · 16K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 22.345/1MOutput Rp 178.753/1M
🏷️ Termurah: Merge Gateway
openai

GPT-Image-2

openai · gpt-image

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

TextImageImage
0 ctx · 0 outAttachments
💰Harga:
Input Rp 89.377/1MOutput Rp 536.257/1M
🏷️ Termurah: Vercel AI Gateway
openai

GPT-5.1 Codex Max

openai · gpt-codex

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 19.663/1MOutput Rp 160.877/1M
🏷️ Termurah: Poe
openai

GPT-5.1 Codex

openai · gpt-codex

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 19.663/1MOutput Rp 160.877/1M
🏷️ Termurah: Poe
openai

GPT-4.1 mini

openai · gpt-mini

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

TextImagePDFText
1.0M ctx · 33K outToolsAttachmentsStructured
💰Harga:
Input Rp 6.436/1MOutput Rp 25.026/1M
🏷️ Termurah: Poe
openai

GPT OSS 20B

openai · gpt-oss

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

TextText
131K ctx · 33K outReasoningToolsStructuredOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: LMStudio
openai

Whisper Large v3 Turbo

openai · whisper

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

AudioText
448 ctx · 448 outOpen
💰Harga:
Input Rp 42/1MOutput Rp 42/1M
🏷️ Termurah: evroc
openai

GPT-5.4 nano

openai · gpt-nano

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 3.218/1MOutput Rp 19.663/1M
🏷️ Termurah: Poe
openai

GPT-5.1

openai · gpt

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

TextImageText
400K ctx · 128K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 19.663/1MOutput Rp 160.877/1M
🏷️ Termurah: Poe
xai

Grok 4.6

xai · grok

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

TextImageText
500K ctx · 500K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 26.813/1MOutput Rp 80.439/1M
🏷️ Termurah: Merge Gateway
xai

Grok 4.5

xai · grok

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

TextImageText
500K ctx · 500K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 35.751/1MOutput Rp 107.252/1M
🏷️ Termurah: Eden AI
xai

Grok 4.20 (Non-Reasoning)

xai · grok

Grok model for agentic tool use, reasoning, coding, and live assistance

TextImagePDFText
1M ctx · 30K outToolsAttachmentsStructured
💰Harga:
Input Rp 22.345/1MOutput Rp 44.689/1M
🏷️ Termurah: Eden AI
xai

Grok Imagine Video 1.5

xai · grok

Video model for image-to-video generation, editing, and extension workflows

TextImageVideoVideo
1K ctx · 0 outAttachments
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

TextImageText
2M ctx · 30K outToolsAttachmentsStructured
xai

Grok 4.20 (Reasoning)

xai · grok

Reasoning Grok for document-heavy analysis and long-horizon tool use

TextImagePDFText
1M ctx · 30K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 22.345/1MOutput Rp 44.689/1M
🏷️ Termurah: Eden AI
xai

Grok Imagine Image 2.0

xai · grok

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

TextImageImage
8K ctx · 0 outAttachments
xai

Grok Build 0.1

xai · grok-build

Fast Grok coding model tuned for agentic engineering and iterative edits

TextImagePDFText
256K ctx · 256K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 17.876/1MOutput Rp 35.751/1M
🏷️ Termurah: Eden AI
xai

Grok 4.3

xai · grok

xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk

TextImagePDFText
1M ctx · 30K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 22.345/1MOutput Rp 44.689/1M
🏷️ Termurah: Eden AI
meituan

LongCat-2.0

meituan · longcat

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

TextText
1M ctx · 131K outReasoningTools
💰Harga:
Input Rp 5.363/1MOutput Rp 21.451/1M
🏷️ Termurah: OpenRouter
swiss-ai

Apertus 70B

swiss-ai ·

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.

TextText
66K ctx · 8K outToolsOpen
swiss-ai

Apertus 8B

swiss-ai ·

Fully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant.

TextText
66K ctx · 8K outToolsOpen
stepfun

Step 3.5 Flash 2603

stepfun ·

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

TextText
256K ctx · 256K outReasoningToolsOpen
stepfun

Step 3.5 Flash

stepfun ·

StepFun flash lane for quick multimodal reasoning and coding assistance

TextText
256K ctx · 256K outReasoningToolsOpen
💰Harga:
Input Rp 1.609/1MOutput Rp 5.363/1M
🏷️ Termurah: Vercel AI Gateway
stepfun

Step 3.7 Flash

stepfun ·

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

TextImageVideoText
256K ctx · 256K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 3.397/1MOutput Rp 20.378/1M
🏷️ Termurah: Ambient
sarvam

Sarvam 105B

sarvam · sarvam

Flagship Indian-language reasoning model for enterprise multilingual applications

TextText
131K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 716/1MOutput Rp 2.861/1M
🏷️ Termurah: FastRouter
sarvam

Sarvam 30B

sarvam · sarvam

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

TextText
128K ctx · 128K outReasoningToolsOpen
💰Harga:
Input Rp 358/1MOutput Rp 1.788/1M
🏷️ Termurah: FastRouter
trendyol

Trendyol Asure 12B

trendyol · gemma

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

TextImageText
131K ctx · undefined outAttachmentsOpen
deepreinforce

Ornith 1.0 35B

deepreinforce · ornith

Large coding-reasoning model for agentic software tasks and RL search

TextImageText
262K ctx · undefined outReasoningToolsAttachmentsOpen
deepreinforce

Ornith 1.0 397B

deepreinforce · ornith

Large coding-reasoning model for agentic software tasks and RL search

TextImageText
262K ctx · undefined outReasoningToolsAttachmentsOpen
deepreinforce

Ornith 1.0 31B

deepreinforce · ornith

Open coding-reasoning model for repository tasks and self-improving agents

TextImageText
262K ctx · undefined outReasoningToolsAttachmentsOpen
deepreinforce

Ornith 1.0 9B

deepreinforce · ornith

Open coding-reasoning model for repository tasks and self-improving agents

TextImageText
262K ctx · undefined outReasoningToolsAttachmentsOpen
xiaomi

MiMo-V2.5-Pro-UltraSpeed

xiaomi · mimo

MiMo pro model for strong multimodal reasoning and agent execution

TextText
1.0M ctx · 131K outReasoningToolsOpen
xiaomi

MiMo-V2.5

xiaomi · mimo

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

TextImageAudioVideoText
1.0M ctx · 131K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 2.503/1MOutput Rp 5.006/1M
🏷️ Termurah: Kilo Gateway
xiaomi

MiMo-V2-Pro

xiaomi · mimo

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

TextText
1.0M ctx · 131K outReasoningTools
💰Harga:
Input Rp 17.876/1MOutput Rp 53.626/1M
🏷️ Termurah: ZenMux
xiaomi

MiMo-V2-Omni

xiaomi · mimo

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

TextImageAudioVideoPDFText
262K ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 7.151/1MOutput Rp 35.751/1M
🏷️ Termurah: ZenMux
xiaomi

MiMo-V2-Flash

xiaomi · mimo

MiMo flash model for fast multimodal assistance and agent workflows

TextText
262K ctx · 66K outReasoningToolsOpen
💰Harga:
Input Rp 1.788/1MOutput Rp 5.363/1M
🏷️ Termurah: ZenMux
xiaomi

MiMo-V2.5-Pro

xiaomi · mimo

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

TextText
1.0M ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 7.776/1MOutput Rp 15.552/1M
🏷️ Termurah: Kilo Gateway
alibaba

Qwen3-VL Plus

alibaba · qwen

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

TextImageText
262K ctx · 33K outReasoningTools
alibaba

Qwen3.8 Max Preview

alibaba · qwen

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

TextImageVideoText
1M ctx · 131K outReasoningToolsAttachments
alibaba

Qwen3-Coder 30B-A3B Instruct

alibaba · qwen

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

TextText
262K ctx · 66K outToolsOpen
alibaba

Qwen3.7 Max

alibaba · qwen

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

TextText
1M ctx · 66K outReasoningTools
💰Harga:
Input Rp 44.689/1MOutput Rp 134.065/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen Turbo

alibaba · qwen

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

TextText
1M ctx · 16K outReasoningTools
alibaba

Qwen-Omni Turbo

alibaba · qwen

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

TextImageAudioVideoTextAudio
33K ctx · 2K outTools
alibaba

Qwen-VL Max

alibaba · qwen

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

TextImageText
131K ctx · 8K outTools
alibaba

Qwen3 32B

alibaba · qwen

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

TextText
131K ctx · 16K outReasoningToolsOpen
alibaba

Qwen3 235B-A22B

alibaba · qwen

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

TextText
131K ctx · 16K outReasoningToolsOpen
alibaba

Qwen Max

alibaba · qwen

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

TextText
33K ctx · 8K outTools
alibaba

Qwen3.5 35B-A3B

alibaba · qwen

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

TextImageVideoAudioText
262K ctx · 66K outReasoningToolsAttachmentsStructuredOpen
alibaba

Qwen3 VL 235B A22B Thinking

alibaba · qwen

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

TextImageText
131K ctx · 33K outReasoningToolsAttachmentsStructuredOpen
alibaba

Qwen3 30B A3B

alibaba · qwen

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

TextText
131K ctx · 16K outReasoningToolsOpen
alibaba

Qwen3.5 397B-A17B

alibaba · qwen

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

TextImageVideoAudioText
262K ctx · 66K outReasoningToolsAttachmentsStructuredOpen
alibaba

Qwen3.5 Flash

alibaba · qwen

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

TextImageVideoText
1M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 1.788/1MOutput Rp 7.151/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen2.5-Coder-0.5B

alibaba · qwen

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

TextText
33K ctx · 8K outOpen
alibaba

Qwen Plus

alibaba · qwen

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

TextText
1M ctx · 33K outReasoningTools
alibaba

Qwen3 Coder Next

alibaba · qwen

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

TextText
262K ctx · 66K outToolsStructuredOpen
💰Harga:
Input Rp 8.938/1MOutput Rp 21.451/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.5 Plus

alibaba · qwen

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

TextImageVideoText
1M ctx · 66K outReasoningTools
💰Harga:
Input Rp 7.151/1MOutput Rp 42.901/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen2.5-VL 72B Instruct

alibaba · qwen

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

TextImageText
131K ctx · 8K outToolsOpen
alibaba

Qwen3 Coder Flash

alibaba · qwen

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

TextText
1M ctx · 66K outTools
alibaba

Qwen3.6 Max Preview

alibaba · qwen

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

TextText
262K ctx · 66K outReasoningTools
alibaba

Qwen3.8 Max

alibaba · qwen

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

TextImageVideoPDFText
1M ctx · 131K outReasoningToolsAttachments
💰Harga:
Input Rp 35.751/1MOutput Rp 107.252/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.7 Plus

alibaba · qwen

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

TextImageVideoText
1M ctx · 64K outReasoningToolsAttachments
💰Harga:
Input Rp 7.151/1MOutput Rp 28.601/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

QwQ 32B

alibaba · qwen

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

TextText
131K ctx · 8K outReasoningToolsOpen
alibaba

Qwen3.7 Flash

alibaba · qwen

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

TextImageVideoText
1M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 537/1MOutput Rp 2.324/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3-Next 80B-A3B (Thinking)

alibaba · qwen

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

TextText
131K ctx · 33K outReasoningToolsOpen
💰Harga:
Input Rp 2.682/1MOutput Rp 21.451/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3-Coder 480B-A35B Instruct

alibaba · qwen

Open Qwen coding heavyweight for repository reasoning and agentic engineering

TextText
262K ctx · 66K outToolsOpen
alibaba

Qwen2.5-Coder-32B-Instruct

alibaba · qwen

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

TextText
131K ctx · 8K outToolsOpen
alibaba

Qwen Flash

alibaba · qwen

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

TextText
1M ctx · 33K outReasoningTools
alibaba

Qwen3 Max

alibaba · qwen

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

TextText
262K ctx · 66K outTools
💰Harga:
Input Rp 21.451/1MOutput Rp 107.252/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.6 35B-A3B

alibaba · qwen

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

TextImageVideoAudioText
262K ctx · 66K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 3.397/1MOutput Rp 8.581/1M
🏷️ Termurah: Zenifra
alibaba

Qwen3 235B-A22B Instruct 2507

alibaba · qwen

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

TextText
262K ctx · 16K outToolsOpen
alibaba

Qwen3.6 27B

alibaba · qwen

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

TextImageVideoAudioText
262K ctx · 66K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 3.629/1MOutput Rp 40.041/1M
🏷️ Termurah: NanoGPT
alibaba

Qwen3-Next 80B-A3B Instruct

alibaba · qwen

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

TextText
131K ctx · 33K outToolsOpen
💰Harga:
Input Rp 2.682/1MOutput Rp 21.451/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.8 27B

alibaba · qwen

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

TextImageVideoText
262K ctx · 33K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 1.788/1MOutput Rp 7.151/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.6 Plus

alibaba · qwen

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

TextImageVideoText
1M ctx · 66K outReasoningToolsAttachments
💰Harga:
Input Rp 8.938/1MOutput Rp 53.626/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3.5 9B

alibaba · qwen

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

TextImageVideoText
262K ctx · 66K outReasoningToolsAttachmentsStructuredOpen
alibaba

Qwen3.5 27B

alibaba · qwen

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

TextImageVideoAudioText
262K ctx · 66K outReasoningToolsAttachmentsStructuredOpen
alibaba

QwQ Plus

alibaba · qwen

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

TextText
131K ctx · 8K outReasoningTools
alibaba

Qwen3.5 122B-A10B

alibaba · qwen

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

TextImageVideoAudioText
262K ctx · 66K outReasoningToolsAttachmentsStructuredOpen
alibaba

Qwen3 Coder Plus

alibaba · qwen

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

TextText
1.0M ctx · 66K outTools
💰Harga:
Input Rp 17.876/1MOutput Rp 89.377/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen3 VL 235B A22B Instruct

alibaba · qwen

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

TextImageText
131K ctx · 33K outToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 7.151/1MOutput Rp 28.601/1M
🏷️ Termurah: Vercel AI Gateway
alibaba

Qwen-VL Plus

alibaba · qwen

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

TextImageText
131K ctx · 8K outTools
alibaba

Qwen3.6 Flash

alibaba · qwen3.6

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

TextImageVideoText
1M ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 3.397/1MOutput Rp 20.736/1M
🏷️ Termurah: NanoGPT
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

TextText
262K ctx · 131K outReasoningToolsStructuredOpen
💰Harga:
Input Rp 35.751/1MOutput Rp 107.252/1M
🏷️ Termurah: Vercel AI Gateway
sakana

Fugu

sakana · fugu

Multi-agent model for routing expert agents across complex analytical tasks

TextImageText
1M ctx · undefined outReasoningToolsAttachmentsStructured
sakana

Sakana Namazu

sakana · sakana-namazu

Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows

TextImagePDFText
262K ctx · 66K outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 16.982/1MOutput Rp 71.501/1M
🏷️ Termurah: Kilo Gateway
sakana

Fugu Ultra

sakana · fugu

Quality-first multi-agent model for hard research, analysis, and competitions

TextImageText
1M ctx · undefined outReasoningToolsAttachmentsStructured
💰Harga:
Input Rp 89.377/1MOutput Rp 536.257/1M
🏷️ Termurah: Pioneer
perplexity

Sonar Deep Research

perplexity · sonar

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

TextText
128K ctx · 33K outReasoning
💰Harga:
Input Rp 35.751/1MOutput Rp 143.002/1M
🏷️ Termurah: Kilo Gateway
perplexity

Sonar

perplexity · sonar

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

TextText
128K ctx · 4K out
💰Harga:
Input Rp 17.876/1MOutput Rp 17.876/1M
🏷️ Termurah: Kilo Gateway
perplexity

Sonar Reasoning Pro

perplexity · sonar-reasoning

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

TextImageText
128K ctx · 4K outReasoningAttachments
💰Harga:
Input Rp 35.751/1MOutput Rp 143.002/1M
🏷️ Termurah: Kilo Gateway
perplexity

Sonar Pro

perplexity · sonar-pro

Deeper Sonar search model with broader retrieval and stronger synthesis

TextImageText
200K ctx · 8K outAttachments
💰Harga:
Input Rp 53.626/1MOutput Rp 268.129/1M
🏷️ Termurah: Kilo Gateway
zhipuai

GLM-4.6

zhipuai · glm

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

TextText
205K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-4.5-Flash

zhipuai · glm-flash

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

TextText
131K ctx · 98K outReasoningTools
zhipuai

GLM-5V-Turbo

zhipuai · glm

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

TextImageVideoPDFText
200K ctx · 131K outReasoningToolsAttachments
zhipuai

GLM-4.7

zhipuai · glm

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

TextText
205K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-4.5V

zhipuai · glm

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

TextImageVideoText
64K ctx · 16K outReasoningToolsAttachmentsOpen
zhipuai

GLM-4.7-FlashX

zhipuai · glm-flash

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

TextText
200K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-5

zhipuai · glm

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

TextText
205K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-5-Turbo

zhipuai · glm

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

TextText
200K ctx · 131K outReasoningToolsStructured
zhipuai

GLM-5.3

zhipuai · glm

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

TextText
1M ctx · 131K outReasoningToolsStructured
zhipuai

GLM-5.2

zhipuai · glm

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

TextText
1M ctx · 131K outReasoningToolsStructuredOpen
zhipuai

GLM-4.6V

zhipuai · glm

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

TextImageVideoText
128K ctx · 33K outReasoningToolsAttachmentsOpen
zhipuai

GLM-4.5-Air

zhipuai · glm-air

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

TextText
131K ctx · 98K outReasoningToolsOpen
zhipuai

GLM-5.1

zhipuai · glm

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

TextText
200K ctx · 131K outReasoningToolsStructuredOpen
zhipuai

GLM-4.7-Flash

zhipuai · glm-flash

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

TextText
200K ctx · 131K outReasoningToolsOpen
zhipuai

GLM-4.5

zhipuai · glm

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

TextText
131K ctx · 98K outReasoningToolsOpen
ibm

Granite-4.0-H-Micro

ibm · granite

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

TextText
131K ctx · 131K outToolsStructuredOpen
ibm

Granite-4.0-H-Small

ibm · granite

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

TextText
131K ctx · 131K outToolsStructuredOpen
💰Harga:
Input Rp 1.137/1MOutput Rp 4.737/1M
🏷️ Termurah: watsonx.ai
thinkingmachines

Inkling Small

thinkingmachines · ling

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

TextImageAudioText
1.0M ctx · 1.0M outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 8.044/1MOutput Rp 21.451/1M
🏷️ Termurah: Kilo Gateway
thinkingmachines

Inkling

thinkingmachines · ling

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

TextImageAudioText
1.0M ctx · 1.0M outReasoningToolsAttachmentsOpen
💰Harga:
Input Gratis/1MOutput Gratis/1M
🏷️ Termurah: Nvidia
mistral

Magistral Small

mistral · magistral

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

TextText
131K ctx · 8K outReasoningToolsOpen
mistral

Mistral Small (latest)

mistral · mistral-small

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

TextImageText
256K ctx · 256K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 1.073/1MOutput Rp 3.218/1M
🏷️ Termurah: Eden AI
mistral

Devstral Medium

mistral · devstral

Mistral coding agent model for repository tasks and software engineering workflows

TextText
128K ctx · 128K outTools
💰Harga:
Input Rp 7.151/1MOutput Rp 35.751/1M
🏷️ Termurah: Merge Gateway
mistral

Mistral Small 3.1 24B

mistral · mistral-small

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

TextImageText
128K ctx · 16K outToolsAttachmentsStructuredOpen
mistral

Mistral Large 2.1

mistral · mistral-large

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

TextText
131K ctx · 16K outToolsOpen
💰Harga:
Input Rp 35.751/1MOutput Rp 107.252/1M
🏷️ Termurah: Merge Gateway
mistral

Mistral Nemo

mistral · mistral-nemo

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

TextText
128K ctx · 128K outToolsOpen
💰Harga:
Input Rp 2.682/1MOutput Rp 2.682/1M
🏷️ Termurah: Vercel AI Gateway
mistral

Mistral Large (latest)

mistral · mistral-large

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

TextImageText
262K ctx · 262K outToolsAttachmentsOpen
💰Harga:
Input Rp 8.938/1MOutput Rp 26.813/1M
🏷️ Termurah: Merge Gateway
mistral

Ministral 8B Instruct

mistral · ministral

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

TextText
131K ctx · 8K outToolsOpen
mistral

Devstral Small

mistral · devstral

Mistral coding agent model for repository tasks and software engineering workflows

TextText
128K ctx · 128K outToolsOpen
💰Harga:
Input Rp 1.788/1MOutput Rp 5.363/1M
🏷️ Termurah: Merge Gateway
mistral

Devstral 2

mistral · devstral

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

TextText
262K ctx · 262K outToolsOpen
💰Harga:
Input Rp 7.151/1MOutput Rp 35.751/1M
🏷️ Termurah: Eden AI
mistral

Mistral Small 4

mistral · mistral-small

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

TextImageText
256K ctx · 256K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 2.682/1MOutput Rp 10.726/1M
🏷️ Termurah: Eden AI
mistral

Mistral Small 3.2

mistral · mistral-small

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

TextImageText
128K ctx · 16K outToolsOpen
mistral

Pixtral Large (latest)

mistral · pixtral

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

TextImageText
128K ctx · 128K outToolsAttachmentsOpen
💰Harga:
Input Rp 35.751/1MOutput Rp 107.252/1M
🏷️ Termurah: Merge Gateway
mistral

Mistral Large 3

mistral · mistral-large

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

TextImageText
262K ctx · 262K outToolsAttachmentsOpen
💰Harga:
Input Rp 8.938/1MOutput Rp 26.813/1M
🏷️ Termurah: Eden AI
mistral

Mistral Medium 3.5

mistral · mistral-medium

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

TextImageText
262K ctx · 262K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 26.813/1MOutput Rp 134.065/1M
🏷️ Termurah: Eden AI
mistral

Mistral Medium 3

mistral · mistral-medium

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

TextImageText
131K ctx · 131K outToolsAttachments
💰Harga:
Input Rp 7.151/1MOutput Rp 35.751/1M
🏷️ Termurah: Eden AI
mistral

Devstral 2 (latest)

mistral · devstral

Mistral coding agent model for repository tasks and software engineering workflows

TextText
262K ctx · 262K outToolsOpen
💰Harga:
Input Rp 7.151/1MOutput Rp 35.751/1M
🏷️ Termurah: Eden AI
mistral

Pixtral 12B

mistral · pixtral

Mistral vision-language model for image understanding and multimodal chat

TextImageText
128K ctx · 128K outToolsAttachmentsOpen
💰Harga:
Input Rp 2.682/1MOutput Rp 2.682/1M
🏷️ Termurah: Vercel AI Gateway
mistral

Voxtral Small (latest)

mistral · voxtral

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

TextAudioText
32K ctx · 32K outToolsAttachmentsOpen
💰Harga:
Input Rp 1.788/1MOutput Rp 5.363/1M
🏷️ Termurah: LLMTR
mistral

Codestral-22B-v0.1

mistral · codestral

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

TextText
33K ctx · 8K outOpen
mistral

Codestral (latest)

mistral · codestral

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

TextText
256K ctx · 4K outToolsOpen
💰Harga:
Input Rp 5.363/1MOutput Rp 16.088/1M
🏷️ Termurah: Merge Gateway
mistral

Magistral Medium (latest)

mistral · magistral-medium

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

TextText
128K ctx · 16K outReasoningTools
💰Harga:
Input Rp 35.751/1MOutput Rp 89.377/1M
🏷️ Termurah: Eden AI
mistral

Mistral Medium (latest)

mistral · mistral-medium

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

TextImageText
262K ctx · 262K outReasoningToolsAttachmentsStructuredOpen
💰Harga:
Input Rp 7.151/1MOutput Rp 35.751/1M
🏷️ Termurah: Merge Gateway
upstage

Solar Pro 2

upstage · solar-pro

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

TextText
66K ctx · 8K outReasoningTools
💰Harga:
Input Rp 2.682/1MOutput Rp 10.726/1M
🏷️ Termurah: LLMTR
upstage

Solar Pro 4

upstage · solar-pro

Upstage's flagship model, specialized for agentic use

TextText
524K ctx · 131K outReasoningToolsStructured
💰Harga:
Input Rp 537/1MOutput Rp 2.146/1M
🏷️ Termurah: LLMTR
upstage

Solar Pro 3

upstage · solar-pro

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

TextText
131K ctx · 8K outReasoningTools
💰Harga:
Input Rp 2.682/1MOutput Rp 10.726/1M
🏷️ Termurah: LLMTR
minimax

MiniMax-M2.7

minimax · minimax

Open MiniMax flagship for coding agents, office automation, and complex environments

TextText
205K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 5.363/1MOutput Rp 21.451/1M
🏷️ Termurah: Eden AI
minimax

MiniMax-M2.7-highspeed

minimax · minimax

Low-latency M2.7 variant for interactive coding plans and agent loops

TextText
205K ctx · 131K outReasoningToolsOpen
minimax

MiniMax-M2.1

minimax · minimax

Earlier MiniMax agent model for practical coding and productivity tasks

TextText
205K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 5.363/1MOutput Rp 21.451/1M
🏷️ Termurah: Eden AI
minimax

MiniMax-M2

minimax · minimax

Efficient open MiniMax model built for coding agents and tool-heavy workflows

TextText
197K ctx · 128K outReasoningToolsOpen
💰Harga:
Input Rp 5.363/1MOutput Rp 21.451/1M
🏷️ Termurah: Eden AI
minimax

MiniMax-M2.5-highspeed

minimax · minimax

High-speed MiniMax model for low-latency coding and agent workflows

TextText
205K ctx · 131K outReasoningToolsOpen
minimax

MiniMax-M3

minimax · minimax

MiniMax multimodal model for long-context coding, perception, and agent planning

TextImageVideoText
512K ctx · 128K outReasoningToolsAttachmentsOpen
💰Harga:
Input Rp 5.363/1MOutput Rp 21.451/1M
🏷️ Termurah: Eden AI
minimax

MiniMax-M2 Her

minimax · minimax

MiniMax M2 variant tuned for conversational and character-driven agent interactions

TextText
200K ctx · 131K outReasoningTools
minimax

MiniMax-M2.5

minimax · minimax

Prior MiniMax coding model for agent workflows, office edits, and automation

TextText
205K ctx · 131K outReasoningToolsOpen
💰Harga:
Input Rp 5.363/1MOutput Rp 21.451/1M
🏷️ Termurah: Eden AI