Spesifikasi, Harga & Fitur Model AI
Bandingkan 636 model AI dari 324 provider. Context window, pricing, reasoning, tool calling, dan multimodal — semua di satu tempat.
Qwen3 235B-A22B Thinking 2507
alibaba · qwen
Updated large open Qwen3 MoE thinking model for reasoning, math, coding, and tool use
Qwen3 30B A3B
alibaba · qwen
Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning
Qwen2.5-VL 72B Instruct
alibaba · qwen-vl
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.6 27B
alibaba · qwen
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.5 9B Base
alibaba · qwen
Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning
Qwen Max
alibaba · qwen-max
Flagship Qwen model for complex reasoning, coding, and agentic workflows
Qwen3 Reranker 8B
alibaba · qwen-reranker
Multilingual query-document reranking model supporting more than 100 languages
Qwen3.5 122B-A10B
alibaba · qwen
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen-Image-2.1
alibaba · qwen-image
Unified text-to-image generation and image editing model with native RGBA transparency and reference-image editing
Qwen-VL Max
alibaba · qwen-vl-max
Qwen vision-language model for visual reasoning, documents, and agent tasks
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
Qwen3.5 4B
alibaba · qwen
Small Qwen3.5 multimodal model for low-cost chat, reasoning, and tool use
Qwen3.5 Plus
alibaba · qwen-plus
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3 Max Preview
alibaba · qwen-max
Flagship Qwen model for complex reasoning, coding, and agentic workflows
Qwen3.6 Flash
alibaba · qwen-flash
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.5 Flash
alibaba · qwen-flash
Qwen vision-language model for visual reasoning, documents, and agent tasks
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
Qwen2.5-Coder-0.5B
alibaba · qwen-coder
Tiny open Qwen code model for lightweight completion and on-device coding
Qwen3 Coder Flash
alibaba · qwen-coder-flash
Qwen coding model for software agents, repository edits, and code reasoning
Qwen3 Omni 30B A3B Thinking
alibaba · qwen-omni
Multimodal reasoning model accepting text, images, video, and audio with text output
Qwen Plus
alibaba · qwen-plus
Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen3 30B-A3B Instruct 2507
alibaba · qwen
Updated compact Qwen3 MoE instruct model for multilingual chat, coding, and tool use
Qwen3.8 Flash
alibaba · qwen-flash
Qwen vision-language model for visual reasoning, documents, and agent tasks
QwQ 32B
alibaba · qwq
Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving
Qwen3-Next 80B-A3B (Thinking)
alibaba · qwen
Efficient Qwen thinking model for local reasoning, math, and coding agents
Qwen3.5 35B-A3B Base
alibaba · qwen
Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning
Qwen3.5 35B-A3B
alibaba · qwen
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen-VL Plus
alibaba · qwen-vl-plus
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.5 2B
alibaba · qwen
Compact Qwen3.5 multimodal model for fast chat, reasoning, and tool use
Qwen3.8 Max
alibaba · qwen-max
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
Qwen3.8 Max Preview
alibaba · qwen-max
Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows
Qwen3.5 27B
alibaba · qwen
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.5 9B
alibaba · qwen
Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen3 Coder Next
alibaba · qwen-coder
Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use
Qwen3 Coder Plus
alibaba · qwen-coder-plus
Hosted Qwen coder for software agents, repo edits, and long-context code
Qwen3.8 Omni Flash
alibaba · qwen-omni-flash
Qwen omni model for text, vision, audio, and multimodal agent tasks
QwQ Plus
alibaba · qwq
Qwen reasoning model for deliberate problem solving, math, and coding
Qwen3 VL 30B A3B Instruct
alibaba · qwen-vl
Open vision-language MoE model for image and video understanding, documents, and visual agents
Qwen2.5 7B Instruct
alibaba · qwen
Small open Qwen2.5 instruction model for chat, structured output, and tool use
Qwen3-VL Plus
alibaba · qwen-vl-plus
Qwen vision-language model for visual reasoning, documents, and agent tasks
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
Qwen3.5 0.8B
alibaba · qwen
Smallest Qwen3.5 multimodal model for on-device chat, reasoning, and tool use
Qwen3.5 397B-A17B
alibaba · qwen
Large open Qwen multimodal MoE for visual agents and long technical tasks
Qwen3 Max
alibaba · qwen-max
Flagship Qwen3 model for coding agents, complex reasoning, and tool use
Qwen3-Next 80B-A3B Instruct
alibaba · qwen
Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen4 Max
alibaba · qwen-max
Flagship multimodal model for coding, office productivity, frontend design, and complex agentic tasks
Qwen3-Coder 480B-A35B Instruct
alibaba · qwen-coder
Open Qwen coding heavyweight for repository reasoning and agentic engineering
Qwen3-Coder 30B-A3B Instruct
alibaba · qwen-coder
Smaller Qwen coder for efficient local agents and repo-level fixes
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
Qwen3 VL 235B A22B Instruct
alibaba · qwen-vl
Qwen vision-language instruct model for visual reasoning, documents, and agent tasks
Qwen3 235B-A22B Instruct 2507
alibaba · qwen
Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use
Qwen3 32B
alibaba · qwen
Dense open Qwen model for self-hosted chat, reasoning, and coding
Qwen3.7 Max
alibaba · qwen-max
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
Qwen3.8 27B
alibaba · qwen
Dense 27B vision-language model for coding, agent tasks, and image and video understanding
Qwen3 VL Flash (Alibaba Cloud)
alibaba · qwen-vl-flash
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.6 35B-A3B
alibaba · qwen
Open multimodal Qwen MoE for local agents that need vision, audio, and code
Qwen-Omni Turbo
alibaba · qwen-omni
Qwen omni model for text, vision, audio, and multimodal agent tasks
Qwen Turbo
alibaba · qwen-turbo
Efficient Qwen model for fast chat, extraction, and high-volume workloads
Qwen Flash
alibaba · qwen-flash
Efficient Qwen model for fast chat, extraction, and high-volume workloads
Qwen3 8B
alibaba · qwen
Dense 8B Qwen3 model with switchable thinking for chat, reasoning, and tool use
Qwen3 VL 235B A22B Thinking
alibaba · qwen-vl
Qwen vision-language thinking model for visual reasoning, documents, and agent tasks
Qwen3 Embedding 8B
alibaba · qwen-embedding
Multilingual text embedding model for retrieval, code search, classification, and clustering
Qwen3 235B-A22B
alibaba · qwen
Large open Qwen MoE for multilingual reasoning, coding, and tool use
Qwen3.7 Flash
alibaba · qwen-flash
Lightweight multimodal Qwen model for high-throughput text, image, and video tasks
Qwen3.7 Plus
alibaba · qwen-plus
Multimodal Qwen workhorse for long-context agents, visual inputs, and coding
Qwen3.6 Max Preview
alibaba · qwen-max
Flagship Qwen model for complex reasoning, coding, and agentic workflows
Qwen MT Plus
alibaba · qwen-mt-plus
Flagship Qwen translation model with terminology control and support for 92 languages
Qwen3.6 Plus
alibaba · qwen-plus
Earlier Qwen multimodal workhorse for million-token agent and document tasks
Qwen2.5-Coder-32B-Instruct
alibaba · qwen-coder
Open coding-focused Qwen model for code generation, repair, and repository reasoning
Phi-4-mini
microsoft · phi-mini
Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks
WizardLM 2 8x22B
microsoft · wizardlm
Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks
MAI-Code-1.1-Flash
microsoft · mai-code-flash
Microsoft coding model with native vision support, optimized for fast and efficient software development
MAI Code 2 Flash
microsoft · mai-code-flash
Microsoft's lightweight coding model for explanations, targeted edits and routine fixes at high volume
MAI-Code-1-Flash
microsoft · mai-code-flash
Microsoft coding model built for fast, efficient assistance in everyday developer workflows
Phi-4-multimodal-instruct
microsoft · phi
Compact Microsoft multimodal model for text, image, and speech understanding
MAI Code 2
microsoft · mai-code
Microsoft's larger agentic coding model for debugging, multi-file changes and repository-wide reasoning
Sarvam-M
sarvam · sarvam
Hybrid-reasoning multilingual model for Indian languages built on Mistral Small
Sarvam 30B
sarvam · sarvam
Efficient Indian-language reasoning model for chat, coding, and multilingual work
Sarvam 105B
sarvam · sarvam
Flagship Indian-language reasoning model for enterprise multilingual applications
Aion-3.0-Mini
aion-labs · aion-mini
Efficient model for low-latency assistance, extraction, and routine automation
Aion-3.0
aion-labs · aion
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Aion-2.0
aion-labs · aion
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Aion-RP 1.0 (8B)
aion-labs · aion-rp
Open Llama instruction model for multilingual chat, reasoning, and coding
MiMo-V2.5-TTS
xiaomi · mimo-tts
Speech generation model for controllable voice, narration, and audio delivery
MiMo-V2.5-Pro-UltraSpeed
xiaomi · mimo-pro
MiMo pro model for strong multimodal reasoning and agent execution
MiMo-V2-TTS
xiaomi · mimo-tts
Speech generation model for controllable voice, narration, and audio delivery
MiMo-V2.6-Pro-UltraSpeed
xiaomi · mimo-pro
MiMo pro model for strong multimodal reasoning and agent execution
MiMo-V2.5-TTS-VoiceClone
xiaomi · mimo-tts
Speech generation model for controllable voice, narration, and audio delivery
MiMo-V2.5-TTS-VoiceDesign
xiaomi · mimo-tts
Speech generation model for controllable voice, narration, and audio delivery
MiMo-V2.6-Pro
xiaomi · mimo-pro
Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution
MiMo-V2-Omni
xiaomi · mimo-omni
MiMo omni model for text, image, video, audio, and agents
MiMo-V2.6-Flash
xiaomi · mimo-flash
MiMo Flash model for multimodal coding agents and long-context automation
MiMo-V2.5
xiaomi · mimo
Open MiMo model for multimodal coding agents and long-context automation
MiMo-V2-Pro
xiaomi · mimo-pro
Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks
MiMo-V2-Flash
xiaomi · mimo-flash
MiMo flash model for fast multimodal assistance and agent workflows
MiMo-V2.5-Pro
xiaomi · mimo-pro
Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution
Dracarys Llama 3.1 70B Instruct
abacusai · dracarys
Abacus.AI coding fine-tune of Llama 3.1 70B Instruct
Magnum v4 72B
anthracite-org · magnum
Open-weight instruction model for adaptable chat and self-hosted production workloads
Sonar Reasoning Pro
perplexity · sonar-reasoning-pro
Web-grounded Sonar for multi-step research questions that need cited reasoning
Sonar Deep Research
perplexity · sonar-deep-research
Sonar search model for autonomous research and citation-backed long-form reports
Sonar
perplexity · sonar
Fast web-grounded Sonar for current answers, citations, and lightweight retrieval
Sonar Pro
perplexity · sonar-pro
Deeper Sonar search model with broader retrieval and stronger synthesis
MythoMax L2 13B
gryphe · mythomax
Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay
Trinity Large Thinking
arcee-ai · trinity-large
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
Trinity Nano Preview
arcee-ai · trinity-nano
Experimental chat-tuned 6B MoE model with 1B active parameters for low-resource chat and instruction following
Trinity Mini
arcee-ai · trinity-mini
Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads
Trinity Large Preview
arcee-ai · trinity-large
Lightly post-trained 398B MoE chat model for creative work, long-context prompts, and tool-using agents
Mercury Edit 2
inception · mercury-edit
Code editing dLLM for autocomplete (FIM) and next-edit suggestions
Mercury 2.5
inception · mercury
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Mercury 2
inception · mercury
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Mercury 3
inception · mercury
Inception's diffusion reasoning model for chat, multi-step problem solving, and tool use
Apodex 1.1 Mini
apodex · apodex-mini
Open-weight 35B MoE model for long-horizon research, forecasting, and tool-assisted work
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
Ling 3.0 Flash VL
inclusionai · ling-flash
Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents
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
Ling 3.0 Flash
inclusionai · ling-flash
Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents
Ling 3.1 Flash
inclusionai · ling-flash
Efficient model for low-latency assistance, extraction, and routine automation
Ling 3.0 Flash Sante
inclusionai · ling-flash
Health and medicine specialization of Ling 3.0 Flash for medical reasoning and evidence-based retrieval
Ling 3.0 Flash Fin
inclusionai · ling-flash
Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution
Perceptron Mk1.5
perceptron · perceptron-mk
Image, video, and audio understanding with visual grounding, reasoning, and function calling
Perceptron Mk1
perceptron · perceptron-mk
Multimodal reasoning model for visual analysis, planning, and tool use
Hermes 3 70B Instruct
nousresearch · hermes
Open Llama instruction model for multilingual chat, reasoning, and coding
Hermes 2 Pro Llama 3 8B
nousresearch · hermes
Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue
Hermes 3 405B Instruct
nousresearch · hermes
Open Llama instruction model for multilingual chat, reasoning, and coding
Hermes 4 405B
nousresearch · hermes
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
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
Nemotron 3.5 Content Safety
nvidia · nemotron-safety
Safety model for policy screening, moderation, and risk-aware routing workflows
Nemotron Nano 12B v2 VL
nvidia · nemotron-nano
Nemotron multimodal model for visual reasoning and agentic AI workflows
Nemotron 3 Nano 30B A3B
nvidia · nemotron-nano
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
Nemotron 3 Super 120B A12B
nvidia · nemotron-super
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
Nemotron Content Safety Reasoning 4B
nvidia · nemotron-safety
Safety model for policy screening, moderation, and risk-aware routing workflows
Nemotron 3 Ultra 550B A55B
nvidia · nemotron-ultra
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Llama 3.1 Nemotron 70B Instruct
nvidia · nemotron
Nemotron model for efficient reasoning, coding, and specialized AI agents
Nemotron 3.5 Lightning 30B A3B
nvidia · nemotron-lightning
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
Llama Nemotron Embed 1B v2
nvidia · nemotron-embed
Multilingual text embedding model for retrieval and question answering pipelines
Llama 3.3 Nemotron Super 49B v1
nvidia · nemotron-super
Nemotron model for efficient reasoning, coding, and specialized AI agents
Nemotron VoiceChat
nvidia · nemotron-voice
Nemotron multimodal model for visual reasoning and agentic AI workflows
Nemotron Nano 9B v2
nvidia · nemotron-nano
Compact Nemotron model for efficient reasoning and deployable AI agents
Llama Nemotron Embed VL 1B v2
nvidia · nemotron-embed
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Llama 3.1 Nemotron Safety Guard 8B v3
nvidia · nemotron-safety
Safety model for policy screening, moderation, and risk-aware routing workflows
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
Llama 3.1 Nemotron Ultra 253B
nvidia · nemotron-ultra
Flagship Nemotron model for high-throughput reasoning and complex agents
Nemotron Cascade 2 30B A3B
nvidia · nemotron-cascade
Nemotron model for efficient reasoning, coding, and specialized AI agents
Llama 3.3 Nemotron Super 49B v1.5
nvidia · nemotron-super
Nemotron model for efficient reasoning, coding, and specialized AI agents
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
Llama Nemotron Rerank VL 1B v2
nvidia · nemotron-rerank
Reranking model for improving retrieval quality in search and recommendation systems
Nemotron 3 Nano Omni 30B A3B Reasoning
nvidia · nemotron-nano
Open Nemotron omni model combining reasoning with text, vision, and audio
Mistral Nemotron
nvidia · nemotron
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Nemotron Mini 4B Instruct
nvidia · nemotron-mini
Compact Nemotron model for efficient reasoning and deployable AI agents
Nemotron 3 Content Safety
nvidia · nemotron-safety
Safety model for policy screening, moderation, and risk-aware routing workflows
Morph V3 Fast
morph · morph-fast
Efficient model for low-latency assistance, extraction, and routine automation
Morph V3 Large
morph · morph-large
Flagship model for demanding analysis, coding, and production agent workflows
Llama 3 8B Lunaris
sao10k · lunaris
Open Llama instruction model for multilingual chat, reasoning, and coding
Llama 3.1 Euryale 70B v2.2
sao10k · euryale
Open Llama instruction model for multilingual chat, reasoning, and coding
Llama 3.3 Euryale 70B
sao10k · euryale
Open Llama instruction model for multilingual chat, reasoning, and coding
LongCat-2.0
meituan · longcat
Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window
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
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
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
Toast 1
mixedbread · toast
Specialized search model for knowledge-intensive questions, multi-step retrieval, and evidence synthesis
SOLAR 10.7B Instruct v1.0
upstage · solar
Upstage depth-upscaled 10.7B instruction model for single-turn chat
Solar Pro 3
upstage · solar-pro
Flagship model for demanding analysis, coding, and production agent workflows
Solar Pro 2
upstage · solar-pro
Flagship model for demanding analysis, coding, and production agent workflows
Solar Mini 4
upstage · solar-mini
Upstage's compact, cost-efficient model for agentic use
Solar Pro 4
upstage · solar-pro
Upstage's flagship model, specialized for agentic use
Rnj-1 Instruct
essentialai · rnj
Open 8B Essential AI model for code, STEM reasoning, and agentic tool use
Inkling Small
thinkingmachines · inkling-small
Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio
Inkling
thinkingmachines · inkling
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
Inkling 2 Small
thinkingmachines · inkling-small
Multimodal MoE reasoning model (594B total, 17B active) for agentic coding, vision, and knowledge work
Seed 1.6 Vision
bytedance-seed · seed
ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks
Seed Evolving
bytedance-seed · seed
Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities
Seed 1.6
bytedance-seed · seed
ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks
Seed 2.1 Pro
bytedance-seed · seed-pro
Flagship ByteDance Seed 2.1 model for complex multimodal reasoning, coding, and agents
Seed 2.0 Pro
bytedance-seed · seed-pro
Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows
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
Seed 1.6 Flash
bytedance-seed · seed-flash
Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use
Seed 2.0 Lite
bytedance-seed · seed-lite
Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation
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.
Seed 2.0 Mini
bytedance-seed · seed-mini
Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks
Seed 2.0 Code
bytedance-seed · seed-code
ByteDance Seed coding model for multimodal software engineering and long-running agents
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.
Seed Character
bytedance-seed · seed
ByteDance Seed model optimized for character-driven dialogue and consistent conversational behavior
Seed 1.8
bytedance-seed · seed
ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows
Seed-OSS-36B-Instruct
bytedance-seed · seed-oss
Open ByteDance Seed model for long-context reasoning, tool use, and agents
Seed 2.1 Turbo
bytedance-seed · seed-turbo
Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows
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.
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
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.
Weaver (alpha)
mancer · weaver
General-purpose chat model for instruction following, writing, and analysis
Gemma 4 31B IT
google · gemma
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
Nano Banana 2.1
google · nano-banana
Image model for prompt-driven generation, multi-turn editing, and visual design workflows
Gemini 3 Flash Preview
google · gemini-flash
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
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
Gemma 2 2B IT
google · gemma
Small open Gemma 2 instruction model for lightweight chat and on-device use
Gemini Omni Flash Preview
google · gemini-omni-flash
Video generation and editing model for fast, conversational text- and image-to-video workflows
Gemini 3.1 Flash Lite
google · gemini-flash-lite
Low-latency Gemini model for high-volume multimodal and agent workloads
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
Gemini 2.5 Flash
google · gemini-flash
Fast Gemini workhorse for multimodal apps where latency and price matter
Deep Research Max Preview
google · gemini-deep-research-max
Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports
Gemini 3.6 Flash
google · gemini-flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Gemini 3.7 Flash
google · gemini-flash
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
Veo 3.1 Lite Preview
google · veo-lite
Video model for prompt-guided generation, editing, and motion workflows
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
Lyria 3 Clip Preview
google · lyria-clip
Music generation model for short 30-second clips, loops, and previews from text or image prompts
Nano Banana 2 Lite
google · nano-banana-lite
Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing
Lyria 3 Pro Preview
google · lyria-pro
Music generation model for full-length songs from text or images with vocals and structure
Gemini Embedding 2
google · gemini-embedding
Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space
DiffusionGemma 26B A4B IT
google · gemma-diffusion
Gemma 4 based discrete text diffusion model for fast chat, reasoning, and tool use
Gemma 2 27B
google · gemma
Open Gemma instruction model for efficient chat and self-hosted deployments
Nano Banana 2
google · nano-banana
Image model for prompt-driven generation, editing, and visual design workflows
Gemini 2.5 Flash Preview 05-20
google · gemini-flash
Preview snapshot of Gemini 2.5 Flash with controllable thinking budgets
Gemma 4 26B A4B IT
google · gemma
Open Gemma instruction model for efficient chat and self-hosted deployments
Gemini 3.5 Flash Lite
google · gemini-flash-lite
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Gemini 3.1 Flash TTS Preview
google · gemini-tts-flash
Low-latency speech generation with steerable prompts and expressive audio tags
Veo 3.1 Fast Preview
google · veo
Video model for prompt-guided generation, editing, and motion workflows
Nano Banana
google · nano-banana
Nano Banana image model for fast generation, edits, and character-consistent assets
Gemini 2.5 Flash TTS
google · gemini-tts-flash
Speech generation model for controllable voice, narration, and audio delivery
Gemini 3.5 Flash
google · gemini-flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Gemma 4 E2B IT
google · gemma
Open Gemma instruction model for efficient chat and self-hosted deployments
Gemini Omni 1.1 Flash
google · gemini-omni-flash
Video generation and editing model for scene extension, frame interpolation, and reference-guided multimodal control
Gemini 2.5 Pro
google · gemini-pro
Google's proven reasoning model for coding, math, and multimodal analysis
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
Gemini 3.1 Flash Lite Preview
google · gemini-flash-lite
Low-latency Gemini model for high-volume multimodal and agent workloads
Nano Banana Pro
google · nano-banana-pro
Nano Banana Pro for higher-fidelity image generation and design-heavy edits
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
Gemini 2.5 Pro TTS
google · gemini-tts-pro
Speech generation model for controllable voice, narration, and audio delivery
Gemini 2.0 Flash-Lite
google · gemini-flash-lite
Low-latency Gemini model for high-volume multimodal and agent workloads
Gemini 3.5 Transcribe Live
google · gemini-transcribe
Speech transcription model for accurate audio-to-text and captioning workflows
Gemini Embedding 001
google · gemini-embedding
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Gemini 4 Argon
google · gemini
Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents
Gemini 2.5 Flash-Lite
google · gemini-flash-lite
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents
Gemini 3.1 Pro Preview
google · gemini-pro
Reasoning-first Gemini preview for agentic coding and complex problem solving
Gemma 3n E2B IT
google · gemma
Efficient on-device Gemma 3n model for text, image, and audio understanding
Gemma 4 E4B IT
google · gemma
Open Gemma instruction model for efficient chat and self-hosted deployments
Gemma 4 12B IT
google · gemma
Compact Gemma 4 instruction model for open, self-hosted chat and reasoning
Gemma 3n E4B IT
google · gemma
Efficient on-device Gemma 3n model for text, image, and audio understanding
Gemini 3.1 Pro Preview Custom Tools
google · gemini-pro
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
Gemini Flash-Lite Latest
google · gemini-flash-lite
Fast Gemini model balancing multimodal reasoning, tool use, and cost
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
Gemini Flash Latest
google · gemini-flash
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
Gemini 2.0 Flash
google · gemini-flash
Earlier Gemini Flash workhorse for responsive multimodal apps and tool use
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
Gemini 3.5 Live Translate Preview
google · gemini-live-translate
Low-latency audio-to-audio model for real-time speech translation across 70+ languages
Gemini 2.5 Computer Use Preview
google · gemini-computer-use
Specialized Gemini 2.5 model for browser-control agents that automate UI tasks
Gemma 3 4B IT
google · gemma
Open multimodal Gemma instruction model for efficient text generation and image understanding
Gemini 2.5 Pro Preview 06-05
google · gemini-pro
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
Nano Banana 2 Preview
google · nano-banana
Image model for prompt-driven generation, editing, and visual design workflows
Gemini Deep Research Preview
google · gemini-deep-research
Agentic model for autonomous multi-step research, synthesis, and cited reports
Gemini 3 Pro Preview
google · gemini-pro
Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts
Nano Banana Pro Preview
google · nano-banana-pro
Nano Banana Pro for higher-fidelity image generation and design-heavy edits
Gemma 3 12B IT
google · gemma
Open multimodal Gemma instruction model for multilingual text generation and image understanding
Veo 3.1 Preview
google · veo
Video model for prompt-guided generation, editing, and motion workflows
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
Gemma 3 27B IT
google · gemma
Largest open Gemma 3 instruction model for multilingual text generation and visual understanding
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
Reka Flash 3
rekaai · reka
Efficient model for low-latency assistance, extraction, and routine automation
Reka Edge
rekaai · reka
Multimodal model for analyzing text, images, documents, and rich media
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.
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.
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.
Macaron V1 Tall
mindlab · macaron-tall
Qwen3.6-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI
Macaron V1 Venti
mindlab · macaron-venti
GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI
BGE M3
baai · bge
Multilingual embedding model combining dense, sparse, and multi-vector retrieval
BGE Multilingual Gemma2
baai · bge
Multilingual Gemma 2 based embedding model for retrieval and semantic search
BGE Reranker V2 M3
baai · bge-reranker
Lightweight multilingual cross-encoder that scores query-document relevance
Baichuan M2 32B
baichuan · baichuan-m
Open medical model trained for clinical reasoning and patient interaction with on, off, and auto thinking modes
Beam 1.0 501B A23B
reflection · beam
Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows
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.
GPT-5 Chat (latest)
openai · gpt
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
o4-mini-deep-research
openai · o-deep-research-mini
Research model for long-horizon investigation, synthesis, and analytical reports
o3
openai · o
Deliberate o-series reasoner for hard math, coding, and multi-step analysis
GPT-4.1 mini
openai · gpt-mini
Affordable GPT-4.1 lane for fast coding help and structured extraction
GPT-5 Nano
openai · gpt-nano
Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs
GPT-3.5-turbo
openai · gpt
Compact GPT model for low-latency assistance and high-volume workloads
GPT-5.6 Terra
openai · gpt-terra
Balanced GPT-5.6 model for capable, cost-efficient everyday work
GPT-5.1 Chat
openai · gpt
Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations
GPT Image 2.5 Flare
openai · gpt-image
Image model for prompt-driven generation, editing, and visual design workflows
GPT-5.6 Sol
openai · gpt-sol
Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
GPT-5.2 Chat
openai · gpt
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
GPT-Image-1
openai · gpt-image
OpenAI image model for production generation, edits, and brand-safe visual workflows
GPT-6 Cyber
openai · gpt
Cybersecurity model for finding and validating exploitable vulnerabilities in authorized security research
GPT-5 Mini
openai · gpt-mini
Small GPT-5 for responsive agents, coding help, and everyday automation
GPT-6.1 Terra
openai · gpt-terra
Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.
GPT-5-Codex
openai · gpt-codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
GPT-5.4
openai · gpt
Agent-ready GPT for coding and computer-use workflows at a lower cost
GPT-5 Image
openai · gpt-image
Image model for prompt-driven generation, editing, and visual design workflows
GPT OSS Safeguard 120B
openai · gpt-oss-safeguard
Safety model for policy screening, moderation, and risk-aware routing workflows
GPT-5
openai · gpt
Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
GPT-5.4 mini
openai · gpt-mini
Strong small GPT for coding subagents, quick tool use, and high-volume work
GPT-5.3 Codex
openai · gpt-codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
GPT-5.5
openai · gpt
Default frontier GPT for coding, computer use, research, and knowledge work
GPT-4o (2024-08-06)
openai · gpt
GPT model for general reasoning, writing, coding, and tool-assisted tasks
o1
openai · o
O-series reasoning model for hard analysis, math, coding, and planning
GPT-6.1 Sol
openai · gpt-sol
Near-Astra performance for complex coding, computer use, and professional work at a lower cost.
GPT-5.3 Codex Spark
openai · gpt-codex-spark
Coding-optimized GPT model for repository edits, reviews, and agentic software work
GPT-6 Luna
openai · gpt-luna
OpenAI's most efficient model for focused, high-volume tasks
GPT-6.2 Astra
openai · gpt-astra
A frontier reasoning model for coding, computer use, and professional work such as slides, spreadsheets, and documents.
GPT-4o
openai · gpt
Omni-era GPT for multimodal chat, practical coding, and general assistants
GPT-6 Astra (Fast)
openai · gpt-astra
Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.
o3-pro
openai · o-pro
High-effort o3 tier for difficult technical reasoning and careful answers
GPT-4.1 nano
openai · gpt-nano
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks
GPT-5.2 Pro
openai · gpt-pro
Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows
GPT-5.1 Codex Max
openai · gpt-codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
GPT-5.5 Pro
openai · gpt-pro
Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding
GPT-5.4 nano
openai · gpt-nano
Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation
GPT OSS Safeguard 20B
openai · gpt-oss-safeguard
Safety model for policy screening, moderation, and risk-aware routing workflows
GPT-5.4 Pro
openai · gpt-pro
More exact GPT-5.4 tier for demanding professional reasoning and agent tasks
GPT-6.2 Sol
openai · gpt-sol
An efficient reasoning model for everyday work, multistep agentic workflows, and coding.
GPT-4o (2024-11-20)
openai · gpt
GPT model for general reasoning, writing, coding, and tool-assisted tasks
GPT OSS 120B
openai · gpt-oss
Open GPT reasoning model for self-hosted agents and controllable deployments
GPT OSS 20B
openai · gpt-oss
Open GPT reasoning model for self-hosted agents and controllable deployments
GPT-5.2
openai · gpt
Reliable GPT generation for broad coding, writing, and tool-assisted product work
GPT-5.1 Codex
openai · gpt-codex
Codex GPT for repository edits, code review, and practical software agents
GPT-6 Sol
openai · gpt-sol
OpenAI model for complex coding and agentic workflows
GPT-4o mini
openai · gpt-mini
Small omni GPT for cheap multimodal assistance and production-scale traffic
GPT-5 Image Mini
openai · gpt-image-mini
Image model for prompt-driven generation, editing, and visual design workflows
o1-pro
openai · o-pro
O-series reasoning model for hard analysis, math, coding, and planning
Whisper Large v3 Turbo
openai · whisper
Speech transcription model for accurate audio-to-text and captioning workflows
GPT-5.4 Image 2
openai · gpt-image
Image model for prompt-driven generation, editing, and visual design workflows
GPT-5.1 Codex mini
openai · gpt-codex-mini
Coding-optimized GPT model for repository edits, reviews, and agentic software work
GPT-5.5 Instant
openai · gpt
Compact GPT model for low-latency assistance and high-volume workloads
o3-mini
openai · o-mini
Smaller o-series reasoner for economical coding, math, and planning tasks
GPT-5 Pro
openai · gpt-pro
Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning
GPT-4o (2024-05-13)
openai · gpt
GPT model for general reasoning, writing, coding, and tool-assisted tasks
o3-deep-research
openai · o-deep-research
Research model for long-horizon investigation, synthesis, and analytical reports
GPT-Image-1.5
openai · gpt-image
Image model for prompt-driven generation, editing, and visual design workflows
GPT-Realtime-2.1
openai · gpt-realtime
Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior
GPT Realtime Whisper
openai · whisper
Streaming speech-to-text model for low-latency transcript deltas from live audio
o4-mini
openai · o-mini
Fast o-series model for compact reasoning, coding, and tool use
GPT-4 Turbo
openai · gpt
Compact GPT model for low-latency assistance and high-volume workloads
GPT-5.6 Cyber
openai · gpt
Cybersecurity model for authorized vulnerability research and security testing
GPT-5.3 Chat (latest)
openai · gpt
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
GPT-4
openai · gpt
GPT model for general reasoning, writing, coding, and tool-assisted tasks
GPT-4.1
openai · gpt
Long-lived GPT workhorse for coding, instruction following, and production apps
GPT-5.6 Luna
openai · gpt-luna
Cost-efficient GPT-5.6 model for fast, high-volume workloads
GPT-Image-2
openai · gpt-image
Image model for prompt-driven generation, editing, and visual design workflows
GPT-5.2 Codex
openai · gpt-codex
Code-specialist GPT for repository edits, reviews, and long-running software agents
Whisper 3 Large
openai · whisper
Open Whisper checkpoint for robust multilingual transcription and captioning
GPT Image 2.5 Sunburst
openai · gpt-image
Image model for prompt-driven generation, editing, and visual design workflows
GPT-5.1
openai · gpt
Sharper GPT-5 generation for coding, product work, and tool-assisted tasks
CoBuddy
baidu · cobuddy
Baidu Qianfan model optimized for code generation and tool-using coding agents
ERNIE 4.5 21B A3B
baidu · ernie
Open ERNIE text MoE with 21B total and 3B active parameters
ERNIE 4.5 300B A47B
baidu · ernie
Open ERNIE text MoE with 300B total and 47B active parameters
ERNIE 4.5 VL 424B A47B
baidu · ernie
Multimodal reasoning model for visual analysis, planning, and tool use
ALLaM-2-7b
sdaia · allam
ALLaM-2-7b instruction tuned model by SDAIA
Trendyol Asure 12B
trendyol · asure
Turkish-language multimodal instruct model built on Gemma 3 12B for e-commerce text, chat, and image-text tasks
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
GLM-4.5-Flash
zhipuai · glm-flash
Efficient GLM model for fast reasoning, coding, and agent workflows
GLM-4.6V-Flash
zhipuai · glmv-flash
Lightweight GLM vision model for visual reasoning, documents, and multimodal agents
GLM-4.7-FlashX
zhipuai · glm-flash
Efficient GLM model for fast reasoning, coding, and agent workflows
GLM-4.5V
zhipuai · glmv
GLM vision model for visual reasoning, documents, and multimodal agents
GLM-5-Turbo
zhipuai · glm-turbo
Faster GLM-5 lane for coding agents that need lower latency
GLM-4.7-Flash
zhipuai · glm-flash
Budget GLM lane for fast coding help, routing, and everyday automation
GLM-5.2
zhipuai · glm
Open flagship GLM for long-horizon coding agents and million-token context work
GLM-5
zhipuai · glm
General GLM flagship for coding, analysis, and tool-heavy engineering workflows
GLM-4.5
zhipuai · glm
Hybrid-reasoning GLM release that made the 4.5 line broadly useful
GLM-5.3
zhipuai · glm
Flagship GLM model for long-horizon coding, agents, and complex project delivery
GLM-5.3-Flash
zhipuai · glm-flash
Native multimodal GLM model for efficient coding and long-horizon agent tasks
GLM-4.5-Air
zhipuai · glm-air
Lighter GLM-4.5 variant for fast coding assistance and cheaper agents
GLM-5.1
zhipuai · glm
Strong GLM coding model for agentic engineering, terminals, and repository generation
GLM-5V-Turbo
zhipuai · glmv-turbo
Fast GLM vision model for screenshots, documents, and multimodal agent tasks
GLM-4.6
zhipuai · glm
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
GLM-4.6V
zhipuai · glmv
GLM vision model for visual reasoning, documents, and multimodal agents
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.
GLM-4.7
zhipuai · glm
Mature GLM model for dependable coding, reasoning, and structured agent tasks
AutoGLM Phone 9B Multilingual
zhipuai · autoglm
Multilingual visual model for operating smartphone interfaces and mobile agents
Step 3.5 Flash
stepfun · step-flash
StepFun flash lane for quick multimodal reasoning and coding assistance
Step 3.5 Flash 2603
stepfun · step-flash
StepFun flash model for efficient multimodal reasoning, coding, and tool use
Step 3.7 Flash
stepfun · step-flash
Newer StepFun flash model for faster agents, coding, and multimodal prompts
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
Jamba Large
ai21 · jamba-large
AI21's hybrid SSM-Transformer long-context model for enterprise agents and grounded generation
Jamba Mini
ai21 · jamba-mini
AI21's efficient, lightweight hybrid SSM-Transformer model for a wide range of tasks
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
MiniCPM-V 4.7 1B
openbmb · minicpm-v
Compact MiniCPM-V model for single-image, multi-image and video understanding
MiniCPM-V 4.7 35B-A3B
openbmb · minicpm-v
First MoE MiniCPM-V model for single-image, multi-image and video understanding
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
PaddleOCR VL
paddlepaddle · paddleocr
Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts
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.
Llama-3.2-1B
meta · llama
Compact open Llama base model for lightweight and on-device use
Llama-3.1-70B-Instruct
meta · llama
Open Llama instruction model for multilingual chat, reasoning, and coding
Llama 3.2 1B Instruct
meta · llama
Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants
Llama 4 Scout 17B Instruct
meta · llama
Open Llama with long-context vision for efficient multimodal agents
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.
Llama 4 Maverick 17B Instruct
meta · llama
Open multimodal Llama for strong reasoning with efficient everyday serving
Llama Prompt Guard 2 86M
meta · llama-prompt-guard
86M-parameter (mDeBERTa-base) multilingual classifier that detects prompt injection and jailbreak attempts
Llama-3.2-11B-Vision-Instruct
meta · llama
Open multimodal Llama model for image understanding, captioning, and visual QA
Llama 3.2 3B Instruct
meta · llama
Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval
Llama-3.1-8B-Instruct
meta · llama
Compact open Llama model for lightweight chat, drafting, and self-hosting
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.
Llama-3.3-70B-Instruct
meta · llama
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
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.
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.
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.
Llama Prompt Guard 2 22M
meta · llama-prompt-guard
22M-parameter (DeBERTa-xsmall) English classifier that detects prompt injection and jailbreak attempts
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.
Llama-3.2-3B
meta · llama
Small open Llama base model for lightweight text generation and self-hosting
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.
Llama-Guard-3-8B
meta · llama-guard
Llama 3.1-based safety classifier for moderating prompts and model responses
Llama Guard 4 12B
meta · llama-guard
Multimodal Llama 4-based safety classifier for moderating prompts and responses
Llama-3.2-90B-Vision-Instruct
meta · llama
Large open multimodal Llama model for image reasoning, document QA, and captioning
Mistral Nemo
mistral · mistral-nemo
Efficient Mistral-NVIDIA open model for multilingual chat and local deployment
Devstral Medium
mistral · devstral-medium
Mistral coding agent model for repository tasks and software engineering workflows
Ministral 3 3B 2512
mistral · ministral
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
Mistral Large
mistral · mistral-large
Flagship Mistral model for advanced reasoning, coding, and multilingual work
Saba
mistral · mistral
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Pixtral Large (latest)
mistral · pixtral-large
Mistral's larger vision model for document-heavy image understanding and chat
Magistral Small
mistral · magistral-small
Open Mistral reasoning model for transparent step-by-step problem solving
Pixtral Large (25.02)
mistral · pixtral-large
Mistral vision-language model for image understanding and multimodal chat
Ministral 14B
mistral · ministral
Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use
Devstral 2
mistral · devstral
Mistral's coding-agent model for repository work, terminal tasks, and software fixes
Mistral Small 3.2
mistral · mistral-small
Efficient Mistral model for fast chat, extraction, and production assistants
Codestral 25.08
mistral · codestral
Mistral code model for low-latency completion, fill-in-the-middle, and code generation
Devstral Small 2
mistral · devstral-small
Compact multimodal coding model for repository exploration, file editing, and software agents
Mistral Medium 3.1
mistral · mistral-medium
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Mistral Small 3.2 24B
mistral · mistral-small
Efficient Mistral model for fast chat, extraction, and production assistants
Mistral Medium 3.5
mistral · mistral-medium
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Voxtral Mini 3B 2507
mistral · voxtral-mini
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use
Mistral Small 3.1 24B
mistral · mistral-small
Efficient Mistral model for fast chat, extraction, and production assistants
Devstral Small
mistral · devstral-small
Mistral coding agent model for repository tasks and software engineering workflows
Voxtral Small (latest)
mistral · voxtral-small
Instruct model with native audio input for speech understanding and tool use
Ministral 3B
mistral · ministral
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
Pixtral 12B
mistral · pixtral
Mistral vision-language model for image understanding and multimodal chat
Mistral Medium 3
mistral · mistral-medium
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Magistral Small 1.2
mistral · magistral-small
Open multimodal reasoning model for transparent analysis of text and images
Mistral Small 3
mistral · mistral-small
Efficient Mistral model for fast chat, extraction, and production assistants
Ministral 3 8B 2512
mistral · ministral
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
Mistral Medium 3.5
mistral · mistral-medium
Balanced Mistral model for enterprise assistants, multilingual work, and tools
Ministral 3 8B
mistral · ministral
Compact open vision-language model for edge deployment, instruction following, and tool use
Codestral-22B-v0.1
mistral · codestral
Open Mistral code model for fill-in-the-middle and 80+ programming languages
Mixtral 8x22B Instruct
mistral · mixtral
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Mistral Large 3
mistral · mistral-large
Mistral's largest general model for enterprise agents, coding, and multilingual reasoning
Codestral (latest)
mistral · codestral
Mistral code model for completions, refactors, and developer IDE workflows
Mistral Small (latest)
mistral · mistral-small
Efficient Mistral model for fast chat, extraction, and production assistants
Mistral 7B Instruct v0.3
mistral · mistral
Open 7B Mistral instruction model with function calling
Voxtral Small 24B 2507
mistral · voxtral-small
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use
Mixtral 8x7B Instruct v0.1
mistral · mixtral
Open sparse mixture-of-experts Mistral instruction model
Mistral Embed
mistral · mistral-embed
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Ministral 3 14B
mistral · ministral
Open vision-language model for efficient local deployment, instruction following, and tool use
Mistral Large 2407
mistral · mistral-large
Flagship Mistral model for advanced reasoning, coding, and multilingual work
Devstral 2 (latest)
mistral · devstral-medium
Mistral coding agent model for repository tasks and software engineering workflows
Mistral Medium (latest)
mistral · mistral-medium
Balanced Mistral model for enterprise assistants, multilingual work, and tools
Mistral Large 2.1
mistral · mistral-large
Flagship Mistral model for advanced reasoning, coding, and multilingual work
Mistral Small 3.1 24B
mistral · mistral-small
Efficient multimodal model for instruction following, coding, reasoning, and function calling
Mistral Large (latest)
mistral · mistral-large
Flagship Mistral model for advanced reasoning, coding, and multilingual work
Magistral Medium (latest)
mistral · magistral-medium
Mistral reasoning model for transparent analysis, math, and complex decisions
Ministral 8B Instruct
mistral · ministral
Efficient open Mistral edge model for on-device chat and function calling
Mistral Medium 3
mistral · mistral-medium
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Ministral 3 14B 2512
mistral · ministral
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
Mistral Small 4
mistral · mistral-small
Fast Mistral production model for chat, extraction, and cost-sensitive agents
Ministral 3 3B
mistral · ministral
Compact open vision-language model for edge deployment, instruction following, and tool use
Mistral Large 4
mistral · mistral-large
Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work
Claude Haiku 5.5
anthropic · claude-haiku
Fast Claude model for responsive assistance, classification, and lightweight agents
Claude Opus 4.5
anthropic · claude-opus
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Claude Opus 4 (latest)
anthropic · claude-opus
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Claude Opus 5.5
anthropic · claude-opus
Claude model for long-running agentic coding and knowledge work
Claude Opus 4.1
anthropic · claude-opus
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Claude Haiku 3.5
anthropic · claude-haiku
Fast Claude model for responsive assistance, classification, and lightweight agents
Claude Haiku 3
anthropic · claude-haiku
Legacy model retained for compatibility with older integrations
Claude Sonnet 4 (latest)
anthropic · claude-sonnet
Balanced Claude model for coding, analysis, agent workflows, and cost control
Claude Opus 5
anthropic · claude-opus
Strongest Claude Opus model for coding, agents, and professional work
Claude Opus 4.1 (latest)
anthropic · claude-opus
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Claude Sonnet 4.5
anthropic · claude-sonnet
Balanced Claude model for coding, analysis, agent workflows, and cost control
Claude Sonnet 4.5 (latest)
anthropic · claude-sonnet
Balanced Claude model for coding, analysis, agent workflows, and cost control
Claude Sonnet 5.5
anthropic · claude-sonnet
Fast Claude model for everyday coding, agents, and knowledge work
Claude Sonnet 4
anthropic · claude-sonnet
Balanced Claude model for coding, analysis, agent workflows, and cost control
Claude Sonnet 4.6
anthropic · claude-sonnet
Claude workhorse for coding agents, careful analysis, and production cost control
Claude Fable 5.1
anthropic · claude-fable
Claude model for demanding reasoning and long-horizon agentic work
Claude Sonnet 3.7
anthropic · claude-sonnet
Balanced Claude model for coding, analysis, agent workflows, and cost control
Claude Opus 4.5 (latest)
anthropic · claude-opus
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Claude Haiku 4.5
anthropic · claude-haiku
Fast Claude model for responsive assistance, classification, and lightweight agents
Claude Haiku 4.5 (latest)
anthropic · claude-haiku
Fast Claude lane for lightweight agents, office tasks, and responsive chat
Claude Opus 4.7
anthropic · claude-opus
Stronger Opus tier for advanced software work and high-stakes reasoning
Claude Sonnet 3.5 v2
anthropic · claude-sonnet
Balanced Claude model for coding, analysis, agent workflows, and cost control
Claude Sonnet 5
anthropic · claude-sonnet
Everyday Claude agent model for coding, planning, browsing, and general work
Claude Fable 5
anthropic · claude-fable
Claude model for creative writing, analysis, and controlled agent workflows
Claude Opus 4.6
anthropic · claude-opus
High-end Claude for difficult coding, planning, and slower expert reasoning
Claude Fable 5.2
anthropic · claude-fable
Claude model for demanding reasoning and long-horizon agentic work
Claude Mythos 5
anthropic · claude-mythos
Restricted Claude model for advanced cybersecurity and biology research workflows
Claude Mythos 5.1
anthropic · claude-mythos
Restricted Claude model for advanced cybersecurity and biology research workflows
Claude Opus 4.8
anthropic · claude-opus
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents
Claude Opus 4
anthropic · claude-opus
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Palmyra X5
writer · palmyra
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Palmyra X4
writer · palmyra
Enterprise language model for workflow automation, coding, data analysis, and tool use
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
Pareto
unbiased · pareto
Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer
Pareto 26.10
unbiased · pareto
Blended multimodal model that selects frontier and open models for each request and blends their outputs into one answer
Nova Pro 1.0
amazon · nova-pro
Flagship model for demanding analysis, coding, and production agent workflows
Nova Micro
amazon · nova-micro
Efficient model for low-latency assistance, extraction, and routine automation
Nova 2 Lite
amazon · nova-lite
Multimodal reasoning model for visual analysis, planning, and tool use
Nova Pro
amazon · nova-pro
Flagship model for demanding analysis, coding, and production agent workflows
Nova Premier
amazon · nova-premier
Multimodal model for complex analysis, long-context understanding, tool use, and model distillation
Nova Lite 1.0
amazon · nova-lite
Efficient model for low-latency assistance, extraction, and routine automation
Nova Lite
amazon · nova-lite
Efficient model for low-latency assistance, extraction, and routine automation
Nova 2 Lite
amazon · nova-lite
Multimodal reasoning model for visual analysis, planning, and tool use
Nova Micro 1.0
amazon · nova-micro
Efficient model for low-latency assistance, extraction, and routine automation
Granite-4.0-H-Micro
ibm · granite-micro
Compact open-weight hybrid Granite model for lightweight enterprise chat and tool calling
Granite 4.2 8B
ibm · granite
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Granite-4.0-H-Small
ibm · granite-small
Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads
Nex-N2-Pro
nex-agi · nex-n-pro
Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows
Uncensored
cognitivecomputations · dolphin
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Orpheus V1 English
canopylabs · orpheus
Expressive English text-to-speech model with bracketed vocal directions
Orpheus Arabic Saudi
canopylabs · orpheus
Expressive Saudi Arabic text-to-speech model with bracketed vocal directions
DeepSeek V4 Pro 0423
deepseek · deepseek-pro
DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes
DeepSeek V3.2
deepseek · deepseek
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
DeepSeek V4.1 Flash
deepseek · deepseek-flash
DeepSeek V4.1 Flash model for reasoning and agentic coding
DeepSeek OCR 2
deepseek · deepseek-ocr
High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes
DeepSeek V4 Flash
deepseek · deepseek-flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
DeepSeek V4 Flash 0731
deepseek · deepseek-flash
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
DeepSeek Reasoner
deepseek · deepseek
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
DeepSeek-V3
deepseek · deepseek
Open DeepSeek MoE chat model for coding, math, and general reasoning
DeepSeek-R1
deepseek · deepseek-r
Classic open reasoning model for transparent math, coding, and deliberate problem solving
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
DeepSeek V3 0324
deepseek · deepseek
March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding
DeepSeek V4 Flash 0423
deepseek · deepseek-flash
Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads
DeepSeek R1 0528 Qwen3 8B
deepseek · deepseek-r
DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning
DeepSeek R1 0528
deepseek · deepseek-r
May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning
DeepSeek Chat
deepseek · deepseek
DeepSeek chat model for instruction following, coding, and analysis
DeepSeek V4 Pro
deepseek · deepseek-pro
Open MoE flagship with million-token context for coding and long agent runs
DeepSeek V4 Pro 0813
deepseek · deepseek-pro
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
DeepSeek-V3.1
deepseek · deepseek
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes
DeepSeek V3 0324
deepseek · deepseek
DeepSeek chat model for instruction following, coding, and analysis
DeepSeek V4 Flash Vision Exp
deepseek · deepseek-flash
Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work
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
DeepSeek V3.1
deepseek · deepseek
DeepSeek chat model for instruction following, coding, and analysis
Grok 4.3
xai · grok
xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk
X-Ai/Grok-4-Fast-Reasoning
xai · grok
Fast Grok model for responsive chat, reasoning, and tool-assisted work
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
Grok Voice Transcribe 2.0
xai · grok-transcribe
Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming
Grok 4.1 Fast (Reasoning)
xai · grok
xAI's fast agentic tool-calling model with a 2M context window and built-in reasoning
Grok 4.5
xai · grok
xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk
Grok Imagine Video 1.5 Lite
xai · grok-imagine-video-lite
Cost-efficient video model for text-to-video and image-to-video generation
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
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.
x-AI/Grok-Code-Fast 1
xai · grok-code
Fast Grok model for responsive chat, reasoning, and tool-assisted work
Grok 4.7
xai · grok
xAI's frontier model for long-running agents, coding, knowledge work, and visual projects
Grok Imagine Image
xai · grok-imagine-image
Image model for prompt-driven generation, editing, and visual design workflows
Grok Imagine Image 2.0
xai · grok-imagine-image
Image model for prompt-driven generation, editing, and visual design workflows
X-Ai/Grok-4-Fast-Non-Reasoning
xai · grok
Fast Grok model for responsive chat, reasoning, and tool-assisted work
Grok 4.6
xai · grok
xAI's frontier model for long-running agents, coding, knowledge work, and visual projects
Grok 4.20 (Reasoning)
xai · grok
Reasoning Grok for document-heavy analysis and long-horizon tool use
Grok 4.20 (Non-Reasoning)
xai · grok
Grok model for agentic tool use, reasoning, coding, and live assistance
Grok Build 0.1
xai · grok-build
Fast Grok coding model tuned for agentic engineering and iterative edits
Grok Imagine Image Quality
xai · grok-imagine-image
Higher-fidelity Grok Imagine image model for prompt-driven generation, editing, and visual design workflows
LFM2 24B A2B
liquid · lfm
Efficient open Liquid MoE instruct model for on-device chat and tool calling
Aya Expanse 32B
cohere · aya
Open multilingual model optimized for generation across 23 languages
Command R7B Arabic
cohere · command-r
Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge
North Mini Code
cohere · north-mini
Cohere coding model for practical software engineering and agentic edits
Command A Vision
cohere · command-a
Cohere vision model for multilingual document analysis, OCR, and image understanding
Aya Vision 32B
cohere · aya-vision
Open multilingual vision model for OCR, visual reasoning, and image question answering
Tiny Aya Fire
cohere · aya-tiny
Compact multilingual model specialized for South Asian languages
Tiny Aya Earth
cohere · aya-tiny
Compact multilingual model specialized for West Asian and African languages
Tiny Aya Water
cohere · aya-tiny
Compact multilingual model specialized for European and Asia-Pacific languages
Command A
cohere · command-a
Cohere command model for multilingual enterprise agents, tools, and chat
Tiny Aya Global
cohere · aya-tiny
Compact multilingual model balanced across 70 languages and regions
Aya Vision 8B
cohere · aya-vision
Compact open multilingual vision model for OCR and visual question answering
Aya Expanse 8B
cohere · aya
Compact open multilingual model optimized for generation across 23 languages
North Small Translate
cohere · north-small
Open-weight translation model for more than 50 languages and locale variants
Command R7B
cohere · command-r
Cohere retrieval model for long-context chat and enterprise RAG workflows
Command A Reasoning
cohere · command-a
Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows
Command A Translate
cohere · command-a
Translation model for multilingual conversion, localization, and cross-language workflows
Command A
cohere · command-a
Cohere command model for multilingual enterprise agents, tools, and chat
Command A Plus
cohere · command-a-plus
Cohere's stronger command model for multilingual agents and enterprise workflows
Command R+
cohere · command-r-plus
Cohere's RAG workhorse for long-context enterprise search and tool use
Command R
cohere · command-r
Cohere retrieval model for long-context chat and enterprise RAG workflows
Schematron V2 Small
inference-net · schematron-small
Efficient model for low-latency assistance, extraction, and routine automation
Schematron V2 Turbo
inference-net · schematron-turbo
Efficient model for low-latency assistance, extraction, and routine automation
Gemma-SEA-LION-v4-27B-IT
aisingapore · sea-lion
Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following
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
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.
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.
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.
Ornith 1.0 9B
deepreinforce · ornith
Open coding-reasoning model for repository tasks and self-improving agents
Ornith 1.0 31B
deepreinforce · ornith
Open coding-reasoning model for repository tasks and self-improving agents
Ornith 1.5 35B A3B
deepreinforce · ornith
Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding
Ornith 1.0 35B
deepreinforce · ornith
Large coding-reasoning model for agentic software tasks and RL search
Ornith 1.5 122B
deepreinforce · ornith
Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding
Ornith 1.0 397B
deepreinforce · ornith
Large coding-reasoning model for agentic software tasks and RL search
Arrow 2 Telos
quiverai · arrow
High-fidelity SVG generation model for complex vector work and long-context refinement
Arrow 2
quiverai · arrow
Fast SVG generation model for creation, vectorization, editing, and animation
FLUX.1 Kontext [dev]
black-forest-labs · flux-kontext-dev
Open-weight FLUX.1 Kontext model for instruction-based image editing
FLUX.1 [schnell]
black-forest-labs · flux-schnell
Fast few-step FLUX.1 text-to-image model under Apache 2.0
FLUX.1 [dev]
black-forest-labs · flux-dev
Open-weight FLUX.1 text-to-image model for high-quality guidance-distilled generation
Laguna M.1
poolside · laguna-m
Poolside's open-weight model for agentic coding and long-horizon work
Laguna XS 2.1
poolside · laguna-xs
Agentic coding model from Poolside in the XS size class for local deployment
Laguna S 2.1
poolside · laguna-s
Agentic coding model from Poolside in the XS size class for local deployment
Laguna XS.2
poolside · laguna-xs
Agentic coding model from Poolside in the XS size class for local deployment
Fugu
sakana · fugu
Multi-agent model for routing expert agents across complex analytical tasks
Fugu Ultra
sakana · fugu-ultra
Quality-first multi-agent model for hard research, analysis, and competitions
Sakana Namazu
sakana · sakana-namazu
Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows
Fugu Max
sakana · fugu-max
Multi-agent model for routing expert agents across complex analytical tasks
Fugu Ultra v2
sakana · fugu-ultra
Quality-first multi-agent model for hard research, analysis, and competitions
Kimi K3
moonshotai · kimi
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Kimi K2 Instruct 0905
moonshotai · kimi
September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding
Kimi K2.8 Preview
moonshotai · kimi
Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code
Kimi K2 Thinking
moonshotai · kimi
Thinking Kimi model for slower research passes, planning, and hard technical questions
Kimi K2 0711
moonshotai · kimi
Kimi model for long-context chat, coding, and agentic reasoning
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
Kimi K2.7 Code Highspeed
moonshotai · kimi-code
Lower-latency Kimi Code variant for interactive edits and coding-agent loops
Kimi K2.7 Code
moonshotai · kimi-code
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking
Kimi K2.6
moonshotai · kimi
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
Kimi K2 Instruct
moonshotai · kimi
Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents
Kimi K2 Thinking Turbo
moonshotai · kimi
Kimi reasoning model for long-horizon research, planning, and tool use
Kimi K2.5
moonshotai · kimi
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
Flint
recursive · flint
Open-weight mixture-of-experts model with about 2.5B active parameters for local coding agents
Cydonia 24B V4.1
thedrummer · cydonia
Open-weight instruction model for adaptable chat and self-hosted production workloads
Skyfall 36B V2
thedrummer · skyfall
Open-weight instruction model for adaptable chat and self-hosted production workloads
UnslopNemo 12B
thedrummer · unslopnemo
Open-weight instruction model for adaptable chat and self-hosted production workloads
MiniMax-M3
minimax · minimax-m
MiniMax multimodal model for long-context coding, perception, and agent planning
MiniMax M1 80K
minimax · minimax-m
Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget
MiniMax-M2.5
minimax · minimax-m
Prior MiniMax coding model for agent workflows, office edits, and automation
MiniMax Text 01 (MiniMax)
minimax · minimax
MiniMax model for chat, coding, office work, and agentic tasks
MiniMax-M2 Her
minimax · minimax-m
MiniMax M2 variant tuned for conversational and character-driven agent interactions
MiniMax-M2.7-highspeed
minimax · minimax-m
Low-latency M2.7 variant for interactive coding plans and agent loops
MiniMax-M2
minimax · minimax-m
Efficient open MiniMax model built for coding agents and tool-heavy workflows
MiniMax-M2.1
minimax · minimax-m
Earlier MiniMax agent model for practical coding and productivity tasks
MiniMax-M2.5-highspeed
minimax · minimax-m
High-speed MiniMax model for low-latency coding and agent workflows
MiniMax-M3.1-Flash-Preview
minimax · minimax-m-flash
Frontier multimodal coding model with 1M context window and tunable thinking depth
MiniMax-M3.1-Flash
minimax · minimax-m-flash
Frontier multimodal coding model with 1M context window and tunable thinking depth
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
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.
MiniMax-M2.7
minimax · minimax-m
Open MiniMax flagship for coding agents, office automation, and complex environments
Hy3
tencent · hy
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Hy4
tencent · hy
A next-generation multimodal productivity model with significantly enhanced Agent and complex task execution capabilities.
Hy3 preview
tencent · hy
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Hy-MT2-1.8B
tencent · hy-mt
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Hy4 preview
tencent · hy
A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.
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.
Hy-MT2-30B-A3B
tencent · hy-mt
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Hy-MT2-7B
tencent · hy-mt
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Restyler 1
meragpt · restyler
meraGPT model that rewrites machine-written prose so it reads as if a person wrote it, keeping its structure
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
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
Viv Fast
vivgrid · viv
Fast coding model
Relace Apply 3
relace · relace-apply
General-purpose chat model for instruction following, writing, and analysis
Relace Search
relace · relace-search
Tool-capable chat model for instruction following and agentic application workflows
ReMM SLERP 13B
undi95 · remm
Open-weight instruction model for adaptable chat and self-hosted production workloads