NanoGPT
Provider ID: nano-gpt
Details
SDK package@ai-sdk/openai-compatible
Models617
APIhttps://nano-gpt.com/api/v1
Links
Documentation
Auth: NANO_GPT_API_KEY
Models (617)
Tongyi DeepResearch 30B A3B
General-purpose chat model for instruction following, writing, and analysis
128,000 ctx
Baichuan M2 32B Medical
Compact GPT model for low-latency assistance and high-volume workloads
32,768 ctx
Baichuan 4 Air
Compact GPT model for low-latency assistance and high-volume workloads
32,768 ctx
Baichuan 4 Turbo
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
MS3.2 24B Magnum Diamond
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
16,384 ctx
EVA Llama 3.33 70B
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
EVA-LLaMA-3.33-70B-v0.1
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
EVA-Qwen2.5-32B-v0.2
Qwen instruction model for multilingual chat, reasoning, and tool use
16,384 ctx
EVA-Qwen2.5-72B-v0.2
Qwen instruction model for multilingual chat, reasoning, and tool use
16,384 ctx
Llama 3.05 Storybreaker Ministral 70b
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
16,384 ctx
Nemotron Tenyxchat Storybreaker 70b
Nemotron model for efficient reasoning, coding, and specialized AI agents
16,384 ctx
GLM 4.6 Derestricted v5
Compact GPT model for low-latency assistance and high-volume workloads
131,072 ctx
MN-LooseCannon-12B-v1
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
16,384 ctx
Gemma 4 31B Claude 4.6 Opus Reasoning Distilled
O-series reasoning model for hard analysis, math, coding, and planning
262,144 ctxreasoning
Gemma 4 31B Cognitive Unshackled
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B DarkIdol
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B Garnet V2
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B Gemopus
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B Musica v1
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B Queen
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B IT
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
MythoMax 13B
Open Llama instruction model for multilingual chat, reasoning, and coding
4,000 ctx
Mistral Nemo Inferor 12B
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
16,384 ctx
KAT Coder Air V1
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
KAT Coder Exp 72B 1010
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
K2-Think
Kimi reasoning model for long-horizon research, planning, and tool use
128,000 ctx
Llama 3.3 70B Wayfarer
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Magistral Small 2506
Compact GPT model for low-latency assistance and high-volume workloads
32,768 ctx
NemoMix 12B Unleashed
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
32,768 ctx
Llama 3.1 8B (decentralized)
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
MiniMax M1
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctx
MiniMax M2
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
MiniMax M1 80K
MiniMax model for chat, coding, office work, and agentic tasks
1,000,000 ctx
Lumimaid v0.2
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
DeepHermes-3 Mistral 24B (Preview)
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
128,000 ctx
Hermes 4 (Thinking)
General-purpose chat model for instruction following, writing, and analysis
128,000 ctx
Hermes 3 70B
Open Llama instruction model for multilingual chat, reasoning, and coding
65,536 ctx
Hermes 4 Large
Flagship model for demanding analysis, coding, and production agent workflows
128,000 ctx
Hermes 4 Large (Thinking)
Flagship model for demanding analysis, coding, and production agent workflows
128,000 ctx
Hermes 4 Medium
General-purpose chat model for instruction following, writing, and analysis
128,000 ctx
Qwen 2.5 32b EVA
Compact GPT model for low-latency assistance and high-volume workloads
24,576 ctx
Qwen3.5 27B Anko
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B BlueStar Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B BlueStar Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B BlueStar v2 Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B BlueStar v2 Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B BlueStar v3 Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B BlueStar v3 Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Infracelestial
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Marvin DPO V2 Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Marvin DPO V2 Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Marvin V2 Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Marvin V2 Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Musica v1
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B NaNovel Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B NaNovel Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Omega Evolution v2.0 Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Omega Evolution v2.0 Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Omega Evolution v2.2 Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Omega Evolution v2.2 Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Queen Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Queen Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B RpRMax v1
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Vivid Durian
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Writer Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Writer Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Writer V2 Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B Writer V2 Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B earica Derestricted
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Qwen3.5 27B earica Derestricted Lite
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Omega Directive 24B Unslop v2.0
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Llama-xLAM-2 70B fc-r
Open Llama instruction model for multilingual chat, reasoning, and coding
128,000 ctx
Sao10K Stheno 8b
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Llama 3.1 70B Euryale
Open Llama instruction model for multilingual chat, reasoning, and coding
20,480 ctx
Llama 3.1 70B Hanami
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Llama 3.3 70B Euryale
Open Llama instruction model for multilingual chat, reasoning, and coding
20,480 ctx
Llama 3.3 70B Cu Mai
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Steelskull Electra R1 70b
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
MS Evalebis 70b
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Evayale 70b
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Steelskull Nevoria 70b
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Steelskull Nevoria R1 70b
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
DeepSeek V3.1 TEE
DeepSeek chat model for instruction following, coding, and analysis
164,000 ctx
DeepSeek V3.2 TEE
DeepSeek chat model for instruction following, coding, and analysis
164,000 ctx
DeepSeek V4 Pro TEE
Flagship DeepSeek model for coding, reasoning, and agentic work
800,000 ctxreasoning
DeepSeek V4 Pro Thinking TEE
Flagship DeepSeek model for coding, reasoning, and agentic work
800,000 ctxreasoning
Gemma 3 27B TEE
Open Gemma instruction model for efficient chat and self-hosted deployments
131,072 ctx
Gemma 4 26B A4B Uncensored TEE
Open Gemma instruction model for efficient chat and self-hosted deployments
65,536 ctx
Gemma 4 31B IT TEE
Open Gemma instruction model for efficient chat and self-hosted deployments
262,144 ctxreasoning
Gemma 4 31B
Open Gemma instruction model for efficient chat and self-hosted deployments
262,144 ctx
Gemma 4 31B Thinking TEE
Open Gemma instruction model for efficient chat and self-hosted deployments
262,144 ctxreasoning
GLM 4.7 TEE
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
131,000 ctx
GLM 4.7 Flash TEE
Efficient GLM model for fast reasoning, coding, and agent workflows
203,000 ctx
GLM 5 TEE
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
203,000 ctx
GLM 5.1 TEE
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
202,752 ctx
GLM 5.1 Thinking TEE
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
202,752 ctxreasoning
GPT-OSS 120B TEE
Open-weight GPT model for self-hosted reasoning and instruction-following workloads
131,072 ctx
GPT-OSS 20B TEE
Open-weight GPT model for self-hosted reasoning and instruction-following workloads
131,072 ctx
Kimi K2.5 TEE
Kimi model for long-context chat, coding, and agentic reasoning
128,000 ctx
Kimi K2.5 Thinking TEE
Kimi reasoning model for long-horizon research, planning, and tool use
128,000 ctxreasoning
Kimi K2.6 TEE
Kimi multimodal agent model for visual understanding, coding, and planning
262,144 ctx
Llama 3.3 70B
Open Llama instruction model for multilingual chat, reasoning, and coding
128,000 ctx
MiniMax M2.5 TEE
MiniMax model for chat, coding, office work, and agentic tasks
196,608 ctxreasoning
Qwen2.5 VL 72B TEE
Qwen vision-language model for visual reasoning, documents, and agent tasks
65,536 ctx
Qwen3 30B A3B Instruct 2507 TEE
Qwen instruction model for multilingual chat, reasoning, and tool use
262,000 ctx
Qwen3.5 122B A10B TEE
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
262,144 ctxreasoning
Qwen3.5 27B TEE
Multimodal model for analyzing text, images, documents, and rich media
262,144 ctx
Qwen3.5 397B A17B TEE
Qwen instruction model for multilingual chat, reasoning, and tool use
258,048 ctx
Qwen3.6 35B A3B Uncensored TEE
Multimodal reasoning model for visual analysis, planning, and tool use
131,072 ctxreasoning
GLM 4 32B 0414
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
128,000 ctx
GLM 4 9B 0414
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
32,000 ctx
GLM Z1 32B 0414
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
128,000 ctx
GLM Z1 9B 0414
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
32,000 ctx
Anubis 70B v1
General-purpose chat model for instruction following, writing, and analysis
65,536 ctx
Anubis 70B v1.1
General-purpose chat model for instruction following, writing, and analysis
131,072 ctx
The Drummer Cydonia 24B v2
General-purpose chat model for instruction following, writing, and analysis
16,384 ctx
The Drummer Cydonia 24B v4
General-purpose chat model for instruction following, writing, and analysis
16,384 ctx
The Drummer Cydonia 24B v4.1
General-purpose chat model for instruction following, writing, and analysis
16,384 ctx
The Drummer Cydonia 24B v4.3
General-purpose chat model for instruction following, writing, and analysis
32,768 ctx
The Drummer Magidonia 24B v4.3
General-purpose chat model for instruction following, writing, and analysis
32,768 ctx
Rocinante 12b
General-purpose chat model for instruction following, writing, and analysis
16,384 ctx
TheDrummer Skyfall 31B v4.2
Multimodal model for analyzing text, images, documents, and rich media
131,072 ctx
UnslopNemo 12b v4
Multimodal model for analyzing text, images, documents, and rich media
32,768 ctx
TheDrummer Skyfall 36B V2
Multimodal model for analyzing text, images, documents, and rich media
64,000 ctx
QwenLong L1 32B
Qwen instruction model for multilingual chat, reasoning, and tool use
128,000 ctx
M-Prometheus 14B
General-purpose chat model for instruction following, writing, and analysis
32,768 ctx
Mistral Nemo Starcannon 12b v1
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
16,384 ctx
Llama 3.1 70B Dracarys 2
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Aion 1.0
Open Llama instruction model for multilingual chat, reasoning, and coding
65,536 ctx
Aion 1.0 mini (DeepSeek)
Fast DeepSeek model for efficient chat, coding help, and agent loops
131,072 ctx
AionLabs: Aion-2.0
General-purpose chat model for instruction following, writing, and analysis
131,072 ctx
AionLabs: Aion-2.5
General-purpose chat model for instruction following, writing, and analysis
131,072 ctx
Llama 3.1 8b (uncensored)
Open Llama instruction model for multilingual chat, reasoning, and coding
32,768 ctx
Qwen3.6 27B
Qwen vision-language model for visual reasoning, documents, and agent tasks
260,096 ctx
Qwen3.6 27B Thinking
Qwen vision-language model for visual reasoning, documents, and agent tasks
260,096 ctxreasoning
Qwen3.6 Flash
Qwen vision-language model for visual reasoning, documents, and agent tasks
991,800 ctx
Olmo 3 32B Think
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
128,000 ctxreasoning
Amazon Nova 2 Lite
Efficient model for low-latency assistance, extraction, and routine automation
1,000,000 ctx
Amazon Nova Lite 1.0
Efficient model for low-latency assistance, extraction, and routine automation
300,000 ctx
Amazon Nova Micro 1.0
Efficient model for low-latency assistance, extraction, and routine automation
128,000 ctx
Amazon Nova Pro 1.0
Flagship model for demanding analysis, coding, and production agent workflows
300,000 ctx
Magnum V2 72B
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Magnum v4 72B
Open Llama multimodal model for image understanding and text reasoning
16,384 ctx
Claude Haiku Latest
Fast Claude model for responsive assistance, classification, and lightweight agents
200,000 ctxreasoning
Claude 4.6 Opus
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude 4.6 Opus Thinking
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude 4.6 Opus Thinking Low
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude 4.6 Opus Thinking Max
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude 4.6 Opus Thinking Medium
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude 4.7 Opus
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude 4.7 Opus Thinking
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude Opus 4.8
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude Opus 4.8 Thinking
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude Opus Latest
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,000,000 ctxreasoning
Claude Sonnet 4.6
Balanced Claude model for coding, analysis, agent workflows, and cost control
1,000,000 ctx
Claude Sonnet 4.6 Thinking
Balanced Claude model for coding, analysis, agent workflows, and cost control
1,000,000 ctxreasoning
Claude Sonnet Latest
Balanced Claude model for coding, analysis, agent workflows, and cost control
1,000,000 ctxreasoning
Trinity Large Thinking
Flagship model for demanding analysis, coding, and production agent workflows
262,144 ctxreasoning
Trinity Mini
Efficient model for low-latency assistance, extraction, and routine automation
131,072 ctx
ASI1 Mini
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Auto model
Automatic model router for matching prompts to suitable backends and budgets
1,000,000 ctx
Auto model (Basic)
Automatic model router for matching prompts to suitable backends and budgets
1,000,000 ctx
Auto model (Premium)
Automatic model router for matching prompts to suitable backends and budgets
1,000,000 ctx
Auto model (Standard)
Automatic model router for matching prompts to suitable backends and budgets
1,000,000 ctx
Azure gpt-4-turbo
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Azure gpt-4o
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Azure gpt-4o-mini
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Azure o1
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctx
Azure o3-mini
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctx
ERNIE 4.5 VL 28B
Multimodal model for analyzing text, images, documents, and rich media
32,768 ctx
Kimi K2 0711 Instruct FP4
Kimi model for long-context chat, coding, and agentic reasoning
128,000 ctx
Brave (Answers)
Compact GPT model for low-latency assistance and high-volume workloads
8,192 ctx
Brave (Pro)
Compact GPT model for low-latency assistance and high-volume workloads
8,192 ctx
Brave (Research)
Compact GPT model for low-latency assistance and high-volume workloads
16,384 ctx
ByteDance Seed 2.0 Lite
Efficient model for low-latency assistance, extraction, and routine automation
262,144 ctx
Mistral Small 3.2 24b Instruct
Efficient Mistral model for fast chat, extraction, and production assistants
128,000 ctx
Claude 3.5 Haiku
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctx
Claude Haiku 4.5
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctx
Claude Haiku 4.5 Thinking
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4.1 Opus
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctx
Claude 4.1 Opus Thinking
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4.1 Opus Thinking (1K)
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4.1 Opus Thinking (32K)
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4.1 Opus Thinking (32K)
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4.1 Opus Thinking (8K)
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4 Opus
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctx
Claude 4.5 Opus
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4.5 Opus Thinking
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4 Opus Thinking
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4 Opus Thinking (1K)
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4 Opus Thinking (32K)
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4 Opus Thinking (32K)
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4 Opus Thinking (8K)
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctxreasoning
Claude 4 Sonnet
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctx
Claude Sonnet 4.5
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctx
Claude Sonnet 4.5 Thinking
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Claude 4 Sonnet Thinking
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Claude 4 Sonnet Thinking (1K)
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Claude 4 Sonnet Thinking (32K)
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Claude 4 Sonnet Thinking (64K)
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Claude 4 Sonnet Thinking (8K)
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Claw High
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Claw Low
Compact GPT model for low-latency assistance and high-volume workloads
1,048,576 ctxreasoning
Claw Medium
Compact GPT model for low-latency assistance and high-volume workloads
204,800 ctxreasoning
Dolphin 72b
Qwen instruction model for multilingual chat, reasoning, and tool use
8,192 ctx
Cohere: Command R
Cohere retrieval model for long-context chat and enterprise RAG workflows
128,000 ctx
Cohere: Command R+
Cohere retrieval model for long-context chat and enterprise RAG workflows
128,000 ctx
Cohere Command A+ (05/2026)
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctxreasoning
Cohere Command A (08/2025)
O-series reasoning model for hard analysis, math, coding, and planning
256,000 ctx
DeepClaude
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Cogito v1 Preview Qwen 32B
Qwen instruction model for multilingual chat, reasoning, and tool use
128,000 ctx
DeepSeek R1 0528
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
128,000 ctxreasoning
DeepSeek V3.1
DeepSeek chat model for instruction following, coding, and analysis
128,000 ctx
DeepSeek V3.1 Terminus
DeepSeek chat model for instruction following, coding, and analysis
128,000 ctx
DeepSeek V3.1 Terminus (Thinking)
DeepSeek chat model for instruction following, coding, and analysis
128,000 ctx
DeepSeek V3.1 Thinking
DeepSeek chat model for instruction following, coding, and analysis
128,000 ctx
DeepSeek V3.2 Exp
DeepSeek chat model for instruction following, coding, and analysis
163,840 ctx
DeepSeek V3.2 Exp Thinking
DeepSeek chat model for instruction following, coding, and analysis
163,840 ctxreasoning
DeepSeek V3/Deepseek Chat
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
128,000 ctx
DeepSeek V3/Chat Cheaper
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
128,000 ctx
DeepSeek Math V2
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
DeepSeek R1
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctxreasoning
DeepSeek R1 Fast
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
DeepSeek Reasoner
Compact GPT model for low-latency assistance and high-volume workloads
64,000 ctx
Deepseek R1 Cheaper
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
DeepSeek Chat 0324
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
128,000 ctx
DeepSeek Latest
DeepSeek chat model for instruction following, coding, and analysis
1,048,576 ctxreasoning
DeepSeek Prover v2 671B
Flagship DeepSeek model for coding, reasoning, and agentic work
160,000 ctx
DeepSeek V3.2
DeepSeek chat model for instruction following, coding, and analysis
163,000 ctx
DeepSeek V3.2 Speciale
DeepSeek chat model for instruction following, coding, and analysis
163,000 ctxreasoning
DeepSeek V3.2 Thinking
DeepSeek chat model for instruction following, coding, and analysis
163,000 ctxreasoning
DeepSeek V4 Flash
Fast DeepSeek model for efficient chat, coding help, and agent loops
1,048,576 ctxreasoning
DeepSeek V4 Flash (Thinking)
Fast DeepSeek model for efficient chat, coding help, and agent loops
1,048,576 ctxreasoning
DeepSeek V4 Pro
Flagship DeepSeek model for coding, reasoning, and agentic work
1,048,576 ctxreasoning
DeepSeek V4 Pro Cheaper
Flagship DeepSeek model for coding, reasoning, and agentic work
1,048,576 ctxreasoning
DeepSeek V4 Pro Cheaper (Thinking)
Flagship DeepSeek model for coding, reasoning, and agentic work
1,048,576 ctxreasoning
DeepSeek V4 Pro (Thinking)
Flagship DeepSeek model for coding, reasoning, and agentic work
1,048,576 ctxreasoning
DMind-1
GPT model for general reasoning, writing, coding, and tool-assisted tasks
32,768 ctx
DMind-1-Mini
Compact GPT model for low-latency assistance and high-volume workloads
32,768 ctx
Doubao 1.5 Thinking Pro
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Doubao 1.5 Thinking Pro Vision
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Doubao 1.5 Thinking Vision Pro
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Doubao 1.5 Pro 256k
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Doubao 1.5 Pro 32k
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
Doubao 1.5 Vision Pro 32k
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
Doubao Seed 1.6
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Doubao Seed 1.6 Flash
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Doubao Seed 1.6 Thinking
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Doubao Seed 1.8
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Doubao Seed 2.0 Code Preview
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Doubao Seed 2.0 Lite
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Doubao Seed 2.0 Mini
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Doubao Seed 2.0 Pro
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Ernie 4.5 8k Preview
Compact GPT model for low-latency assistance and high-volume workloads
8,000 ctx
Ernie 4.5 Turbo 128k
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Ernie 4.5 Turbo VL 32k
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
Ernie 5.0 Thinking Preview
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctxreasoning
ERNIE 5.1
Compact GPT model for low-latency assistance and high-volume workloads
119,000 ctx
ERNIE 5.1 Thinking
Compact GPT model for low-latency assistance and high-volume workloads
119,000 ctxreasoning
Ernie X1 32k
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
Ernie X1 32k
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
Ernie X1 Turbo 32k
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
ERNIE X1.1
Compact GPT model for low-latency assistance and high-volume workloads
64,000 ctx
RNJ-1 Instruct 8B
General-purpose chat model for instruction following, writing, and analysis
128,000 ctx
Exa (Answer)
Compact GPT model for low-latency assistance and high-volume workloads
4,096 ctx
Exa (Research)
Compact GPT model for low-latency assistance and high-volume workloads
8,192 ctx
Exa (Research Pro)
Compact GPT model for low-latency assistance and high-volume workloads
16,384 ctx
Llama 3 70B abliterated
Open Llama instruction model for multilingual chat, reasoning, and coding
8,192 ctx
Web Answer
Compact GPT model for low-latency assistance and high-volume workloads
32,768 ctx
Qwerky 72B
General-purpose chat model for instruction following, writing, and analysis
32,000 ctx
Gemini 2.0 Flash
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctx
Gemini Text + Image
Image model for prompt-driven generation, editing, and visual design workflows
32,767 ctx
Gemini 2.0 Flash Thinking 0121
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Gemini 2.0 Flash Thinking 1219
Compact GPT model for low-latency assistance and high-volume workloads
32,767 ctx
Gemini 2.0 Pro 0205
Compact GPT model for low-latency assistance and high-volume workloads
2,097,152 ctx
Gemini 2.0 Pro Reasoner
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Gemini 2.5 Flash
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Flash Lite
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Flash Lite Preview
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Flash Lite Preview (09/2025)
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Flash Lite Preview (09/2025) – Thinking
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Flash (No Thinking)
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctx
Gemini 2.5 Flash Preview
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Flash Preview Thinking
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Flash 0520
Compact GPT model for low-latency assistance and high-volume workloads
1,048,000 ctx
Gemini 2.5 Flash 0520 Thinking
Compact GPT model for low-latency assistance and high-volume workloads
1,048,000 ctxreasoning
Gemini 2.5 Flash Preview (09/2025)
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Flash Preview (09/2025) – Thinking
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Pro
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Pro Experimental 0325
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Pro Preview 0325
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Pro Preview 0506
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 2.5 Pro Preview 0605
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctxreasoning
Gemini 3 Pro Image
Image model for prompt-driven generation, editing, and visual design workflows
1,048,756 ctx
Gemini 2.0 Pro 1206
Compact GPT model for low-latency assistance and high-volume workloads
2,097,152 ctx
Gemma 4 31B Fabled
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B Garnet
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B K1 v5
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B Larkspur v0.5
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
Gemma 4 31B MeroMero
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctxreasoning
GLM-4
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GLM-4 Air
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GLM 4 Air 0111
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GLM-4 AirX
Compact GPT model for low-latency assistance and high-volume workloads
8,000 ctx
GLM-4 Flash
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GLM-4 Long
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctx
GLM-4 Plus
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GLM 4 Plus 0111
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GLM 4.1V Thinking Flash
Compact GPT model for low-latency assistance and high-volume workloads
64,000 ctx
GLM 4.1V Thinking FlashX
Compact GPT model for low-latency assistance and high-volume workloads
64,000 ctx
GLM Z1 Air
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
GLM Z1 AirX
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
GLM Zero Preview
Compact GPT model for low-latency assistance and high-volume workloads
8,000 ctx
Gemini 3 Flash (Preview)
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,756 ctxreasoning
Gemini 3 Flash Thinking
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,756 ctxreasoning
Gemini 3.1 Flash Lite
Low-latency Gemini model for high-volume multimodal and agent workloads
1,048,576 ctxreasoning
Gemini 3.1 Pro (Preview)
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
1,048,756 ctxreasoning
Gemini 3.1 Pro (Preview Custom Tools)
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
1,048,756 ctxreasoning
Gemini 3.1 Pro (Preview High)
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
1,048,756 ctxreasoning
Gemini 3.1 Pro (Preview Low)
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
1,048,756 ctxreasoning
Gemini 3.5 Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,576 ctxreasoning
Gemini 3.5 Flash Thinking
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,576 ctxreasoning
Gemini 1.5 Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
2,000,000 ctx
Gemini Flash Latest
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,576 ctxreasoning
Gemini Flash Lite Latest
Low-latency Gemini model for high-volume multimodal and agent workloads
1,048,576 ctxreasoning
Gemini Pro Latest
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
1,048,756 ctxreasoning
Gemma 4 26B A4B
Open Gemma instruction model for efficient chat and self-hosted deployments
262,144 ctxreasoning
Gemma 4 26B A4B Thinking
Open Gemma instruction model for efficient chat and self-hosted deployments
262,144 ctxreasoning
Gemma 4 31B
Open Gemma instruction model for efficient chat and self-hosted deployments
262,144 ctxreasoning
Gemma 4 31B Thinking
Open Gemma instruction model for efficient chat and self-hosted deployments
262,144 ctxreasoning
Hermes High
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Hermes Low
Compact GPT model for low-latency assistance and high-volume workloads
1,048,576 ctxreasoning
Hermes Medium
Compact GPT model for low-latency assistance and high-volume workloads
204,800 ctxreasoning
Holo3-35B-A3B
Compact GPT model for low-latency assistance and high-volume workloads
65,536 ctxreasoning
Holo3-35B-A3B Thinking
Compact GPT model for low-latency assistance and high-volume workloads
65,536 ctxreasoning
DeepSeek R1 Llama 70B Abliterated
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
16,384 ctxreasoning
DeepSeek R1 Qwen Abliterated
Qwen instruction model for multilingual chat, reasoning, and tool use
16,384 ctxreasoning
Llama 3.3 70B Instruct abliterated
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Qwen 2.5 32B Abliterated
Qwen instruction model for multilingual chat, reasoning, and tool use
32,768 ctx
Hunyuan Turbo S
Compact GPT model for low-latency assistance and high-volume workloads
24,000 ctx
Granite 4.1 8B
Tool-capable chat model for instruction following and agentic application workflows
131,072 ctx
Ling 2.6 1T
Tool-capable chat model for instruction following and agentic application workflows
262,144 ctx
Ling 2.6 Flash
Efficient model for low-latency assistance, extraction, and routine automation
262,144 ctx
Ring 2.6 1T
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
262,144 ctxreasoning
Mag Mell R1
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
16,384 ctx
Inflection 3 Pi
GPT model for general reasoning, writing, coding, and tool-assisted tasks
8,000 ctx
Inflection 3 Productivity
GPT model for general reasoning, writing, coding, and tool-assisted tasks
8,000 ctx
Jamba Large
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Jamba Large 1.6
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Jamba Large 1.7
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Jamba Mini
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Jamba Mini 1.6
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Jamba Mini 1.7
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Kimi K2 0711 Fast
Compact GPT model for low-latency assistance and high-volume workloads
131,072 ctx
Kimi Thinking Preview
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
KAT Coder Pro V2
Coding model for repository understanding, refactors, and agentic engineering tasks
256,000 ctx
Gemini LearnLM Experimental
Compact GPT model for low-latency assistance and high-volume workloads
32,767 ctx
LFM2 24B A2B
General-purpose chat model for instruction following, writing, and analysis
32,768 ctx
Manta Flash 1.0
Efficient model for low-latency assistance, extraction, and routine automation
16,384 ctx
Manta Mini 1.0
Efficient model for low-latency assistance, extraction, and routine automation
8,192 ctx
Manta Pro 1.0
Flagship model for demanding analysis, coding, and production agent workflows
32,768 ctx
Mercury 2
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctxreasoning
Llama 3.1 8b Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
131,072 ctx
Llama 3.2 3b Instruct
Open Llama multimodal model for image understanding and text reasoning
131,072 ctx
Llama 3.3 70b Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
131,072 ctx
Llama 4 Maverick
Open multimodal Llama model for strong reasoning and fast responses
1,048,576 ctx
Llama 4 Scout
Open multimodal Llama model for long-context analysis and efficient agents
328,000 ctx
WizardLM-2 8x22B
GPT model for general reasoning, writing, coding, and tool-assisted tasks
65,536 ctx
MiniMax 01
MiniMax multimodal coding model for long-context reasoning and agent tasks
1,000,192 ctx
MiniMax Latest
MiniMax multimodal coding model for long-context reasoning and agent tasks
512,000 ctxreasoning
MiniMax M2-her
MiniMax model for chat, coding, office work, and agentic tasks
65,532 ctx
MiniMax M2.1
MiniMax model for chat, coding, office work, and agentic tasks
200,000 ctxreasoning
MiniMax M2.5
MiniMax model for chat, coding, office work, and agentic tasks
204,800 ctxreasoning
MiniMax M2.7
MiniMax model for chat, coding, office work, and agentic tasks
204,800 ctxreasoning
MiniMax M2.7 Turbo
Efficient MiniMax model for quick assistance, coding, and routine automation
204,800 ctxreasoning
MiniMax M3
MiniMax multimodal coding model for long-context reasoning and agent tasks
512,000 ctx
MiniMax M3 Thinking
MiniMax multimodal coding model for long-context reasoning and agent tasks
512,000 ctxreasoning
MiroThinker 1.7 Deep Research
Research model for long-horizon investigation, synthesis, and analytical reports
262,144 ctxreasoning
MiroThinker 1.7 Deep Research Mini
Research model for long-horizon investigation, synthesis, and analytical reports
262,144 ctxreasoning
Mistral Code Agent Latest
Compact GPT model for low-latency assistance and high-volume workloads
262,144 ctx
Mistral Code Latest
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Mistral Small 31 24b Instruct
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Mistral Medium 3.5
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
256,000 ctxreasoning
Mistral Medium 3.5 Thinking
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
256,000 ctxreasoning
Mistral Devstral Small 2505
Mistral coding agent model for repository tasks and software engineering workflows
32,768 ctx
Mistral Nemo
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
16,384 ctx
Codestral 2508
Mistral coding model for code completion, generation, and developer workflows
256,000 ctx
Devstral 2 123B
Mistral coding agent model for repository tasks and software engineering workflows
262,144 ctx
Ministral 14B
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
262,144 ctx
Ministral 3 14B
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
262,144 ctx
Ministral 3B
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
131,072 ctx
Ministral 8B
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
262,144 ctx
Mistral Large 2411
Flagship Mistral model for advanced reasoning, coding, and multilingual work
128,000 ctx
Mistral Large 3 675B
Flagship Mistral model for advanced reasoning, coding, and multilingual work
262,144 ctx
Mistral Medium 3
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
131,072 ctx
Mistral Medium 3.1
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
131,072 ctx
Mistral Saba
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
32,000 ctx
Mistral Small 4 119B
Efficient Mistral model for fast chat, extraction, and production assistants
262,144 ctxreasoning
Mistral Small 4 119B Thinking
Efficient Mistral model for fast chat, extraction, and production assistants
262,144 ctxreasoning
Mixtral 8x22B
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
65,536 ctx
Mixtral 8x7B
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
32,768 ctx
Neural Daredevil 8B abliterated
Open Llama instruction model for multilingual chat, reasoning, and coding
8,192 ctx
Kimi K2 0905
Kimi model for long-context chat, coding, and agentic reasoning
256,000 ctx
Kimi K2 Instruct
Kimi model for long-context chat, coding, and agentic reasoning
256,000 ctx
Kimi K2 0711
Kimi model for long-context chat, coding, and agentic reasoning
128,000 ctx
Kimi K2 Thinking
Kimi reasoning model for long-horizon research, planning, and tool use
256,000 ctx
Kimi K2 Thinking Original
Kimi reasoning model for long-horizon research, planning, and tool use
256,000 ctxreasoning
Kimi K2 Thinking Turbo Original
Kimi reasoning model for long-horizon research, planning, and tool use
256,000 ctxreasoning
Kimi K2.5
Kimi multimodal agent model for visual understanding, coding, and planning
256,000 ctx
Kimi K2.5 Thinking
Kimi reasoning model for long-horizon research, planning, and tool use
256,000 ctxreasoning
Kimi K2.6
Kimi multimodal agent model for visual understanding, coding, and planning
256,000 ctx
Kimi K2.6 Thinking
Kimi reasoning model for long-horizon research, planning, and tool use
256,000 ctxreasoning
Kimi Latest
Kimi multimodal agent model for visual understanding, coding, and planning
256,000 ctxreasoning
Coding Router
Automatic model router for matching prompts to suitable backends and budgets
1,000,000 ctxreasoning
Coding Router High
Automatic model router for matching prompts to suitable backends and budgets
1,000,000 ctxreasoning
Coding Router Low
Automatic model router for matching prompts to suitable backends and budgets
1,000,000 ctxreasoning
Coding Router Max
Automatic model router for matching prompts to suitable backends and budgets
1,000,000 ctxreasoning
Coding Router Medium
Automatic model router for matching prompts to suitable backends and budgets
1,000,000 ctxreasoning
DeepSeek V3.1 Nex N1
DeepSeek chat model for instruction following, coding, and analysis
128,000 ctx
Llama 3.1 70B Celeste v0.1
Open Llama instruction model for multilingual chat, reasoning, and coding
16,384 ctx
Nvidia Nemotron 70b
Nemotron model for efficient reasoning, coding, and specialized AI agents
16,384 ctx
Nvidia Nemotron Super 49B
Nemotron model for efficient reasoning, coding, and specialized AI agents
128,000 ctx
Nvidia Nemotron Super 49B v1.5
Nemotron model for efficient reasoning, coding, and specialized AI agents
128,000 ctx
Nvidia Nemotron 3 Nano 30B
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
256,000 ctx
Nvidia Nemotron 3 Nano Omni
Open Nemotron omni model combining reasoning with text, vision, and audio
256,000 ctxreasoning
Nvidia Nemotron 3 Super 120B
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
262,144 ctxreasoning
Nvidia Nemotron 3 Super 120B Thinking
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
262,144 ctxreasoning
Nvidia Nemotron Nano 9B v2
Compact Nemotron model for efficient reasoning and deployable AI agents
128,000 ctx
GPT-3.5 Turbo
Compact GPT model for low-latency assistance and high-volume workloads
16,385 ctx
GPT-4 Turbo
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GPT-4 Turbo Preview
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GPT 4.1
GPT model for general reasoning, writing, coding, and tool-assisted tasks
1,047,576 ctx
GPT 4.1 Mini
Compact GPT model for low-latency assistance and high-volume workloads
1,047,576 ctx
GPT 4.1 Nano
Compact GPT model for low-latency assistance and high-volume workloads
1,047,576 ctx
GPT-4o
GPT model for general reasoning, writing, coding, and tool-assisted tasks
128,000 ctx
GPT-4o (2024-08-06)
GPT model for general reasoning, writing, coding, and tool-assisted tasks
128,000 ctx
GPT-4o (2024-11-20)
GPT model for general reasoning, writing, coding, and tool-assisted tasks
128,000 ctx
GPT-4o mini
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GPT-4o mini Search Preview
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GPT-4o Search Preview
GPT model for general reasoning, writing, coding, and tool-assisted tasks
128,000 ctx
GPT 5
GPT model for general reasoning, writing, coding, and tool-assisted tasks
400,000 ctxreasoning
GPT-5 Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
256,000 ctx
GPT 5 Mini
Compact GPT model for low-latency assistance and high-volume workloads
400,000 ctxreasoning
GPT 5 Nano
Compact GPT model for low-latency assistance and high-volume workloads
400,000 ctxreasoning
GPT 5 Pro
Frontier GPT model for professional reasoning, coding, and multimodal work
400,000 ctxreasoning
GPT 5.1
GPT model for general reasoning, writing, coding, and tool-assisted tasks
400,000 ctxreasoning
GPT-5.1 (2025-11-13)
GPT model for general reasoning, writing, coding, and tool-assisted tasks
1,000,000 ctx
GPT 5.1 Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT 5.1 Codex Max
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT 5.1 Codex Mini
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT 5.2
GPT model for general reasoning, writing, coding, and tool-assisted tasks
400,000 ctxreasoning
GPT 5.2 Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT 5.2 Pro
Frontier GPT model for professional reasoning, coding, and multimodal work
400,000 ctxreasoning
GPT 5.3 Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT 5.4
Frontier GPT model for professional reasoning, coding, and multimodal work
922,000 ctxreasoning
GPT 5.4 Mini
Compact GPT model for low-latency assistance and high-volume workloads
400,000 ctxreasoning
GPT 5.4 Nano
Compact GPT model for low-latency assistance and high-volume workloads
400,000 ctxreasoning
GPT 5.4 Pro
Frontier GPT model for professional reasoning, coding, and multimodal work
922,000 ctxreasoning
GPT 5.5
Frontier GPT model for professional reasoning, coding, and multimodal work
1,000,000 ctxreasoning
GPT Chat Latest
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
400,000 ctx
GPT Latest
GPT model for general reasoning, writing, coding, and tool-assisted tasks
1,000,000 ctxreasoning
GPT OSS 120B
Open-weight GPT model for self-hosted reasoning and instruction-following workloads
128,000 ctxreasoning
GPT OSS 20B
Open-weight GPT model for self-hosted reasoning and instruction-following workloads
128,000 ctxreasoning
GPT OSS Safeguard 20B
Safety model for policy screening, moderation, and risk-aware routing workflows
128,000 ctxreasoning
OpenAI o1
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
OpenAI o1-preview
O-series reasoning model for hard analysis, math, coding, and planning
128,000 ctxreasoning
OpenAI o1 Pro
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctx
OpenAI o3
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctx
OpenAI o3 Deep Research
Research model for long-horizon investigation, synthesis, and analytical reports
200,000 ctxreasoning
OpenAI o3-mini
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
OpenAI o3-mini (High)
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
OpenAI o3-mini (Low)
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
OpenAI o3-pro (2025-06-10)
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
OpenAI o4-mini
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
OpenAI o4-mini Deep Research
Research model for long-horizon investigation, synthesis, and analytical reports
200,000 ctxreasoning
OpenAI o4-mini high
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
OWL
Compact GPT model for low-latency assistance and high-volume workloads
1,048,756 ctx
OpenReasoning Nemotron 32B
Nemotron model for efficient reasoning, coding, and specialized AI agents
32,768 ctxreasoning
Perceptron Mk1
Multimodal reasoning model for visual analysis, planning, and tool use
32,768 ctxreasoning
Phi 4 Mini
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Phi 4 Multimodal
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Laguna M.1
Poolside's open-weight model for agentic coding and long-horizon work
262,144 ctxreasoning
Laguna XS.2
Agentic coding model from Poolside in the XS size class for local deployment
262,144 ctxreasoning
Qwen: QvQ Max
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Qwen 3.6 Plus
Compact GPT model for low-latency assistance and high-volume workloads
991,800 ctx
Qwen Long 10M
Compact GPT model for low-latency assistance and high-volume workloads
10,000,000 ctx
Qwen 2.5 Max
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
Qwen Plus
Compact GPT model for low-latency assistance and high-volume workloads
995,904 ctxreasoning
Qwen Turbo
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctx
Qwen 2.5 Coder 32b
Qwen coding model for software agents, repository edits, and code reasoning
32,000 ctx
Qwen 3 235b A22B 2507
Qwen instruction model for multilingual chat, reasoning, and tool use
256,000 ctx
Qwen 3 235b A22B 2507 (TEE)
Qwen instruction model for multilingual chat, reasoning, and tool use
256,000 ctx
Qwen 3 235b A22B 2507 Thinking
Qwen reasoning model for deliberate problem solving, math, and coding
256,000 ctx
Qwen 3 8B
Qwen instruction model for multilingual chat, reasoning, and tool use
41,000 ctx
Qwen3 Next 80B A3B (Instruct)
Qwen instruction model for multilingual chat, reasoning, and tool use
256,000 ctx
Qwen3 VL 235B A22B Instruct
Qwen vision-language model for visual reasoning, documents, and agent tasks
128,000 ctx
Qwen3.6 35B A3B
Qwen vision-language model for visual reasoning, documents, and agent tasks
262,144 ctx
Qwen3.6 35B A3B Thinking
Qwen vision-language model for visual reasoning, documents, and agent tasks
262,144 ctxreasoning
Qwen2.5 72B
Qwen instruction model for multilingual chat, reasoning, and tool use
131,072 ctx
Qwen 3 14b
Qwen instruction model for multilingual chat, reasoning, and tool use
41,000 ctx
Qwen 3 235b A22B
Qwen vision-language model for visual reasoning, documents, and agent tasks
41,000 ctx
Qwen3 30B A3B
Qwen instruction model for multilingual chat, reasoning, and tool use
41,000 ctx
Qwen 3 32b
Qwen vision-language model for visual reasoning, documents, and agent tasks
41,000 ctx
Qwen 3 Coder 480B
Qwen coding model for software agents, repository edits, and code reasoning
262,000 ctx
Qwen3 Coder Flash
Qwen coding model for software agents, repository edits, and code reasoning
128,000 ctx
Qwen3 Coder Next
Qwen coding model for software agents, repository edits, and code reasoning
262,144 ctx
Qwen3 Coder Plus
Qwen coding model for software agents, repository edits, and code reasoning
128,000 ctx
Qwen3 Max
Flagship Qwen model for complex reasoning, coding, and agentic workflows
256,000 ctx
Qwen3 Next 80B A3B (Thinking)
Qwen reasoning model for deliberate problem solving, math, and coding
256,000 ctx
Qwen3.5 397B A17B
Qwen vision-language model for visual reasoning, documents, and agent tasks
258,048 ctx
Qwen3.5 397B A17B Thinking
Qwen vision-language model for visual reasoning, documents, and agent tasks
258,048 ctxreasoning
Qwen3.5 9B
Qwen vision-language model for visual reasoning, documents, and agent tasks
256,000 ctxreasoning
Qwen3.5 Plus
Qwen vision-language model for visual reasoning, documents, and agent tasks
983,616 ctx
Qwen3.5 Plus Thinking
Qwen vision-language model for visual reasoning, documents, and agent tasks
983,616 ctxreasoning
Qwen QwQ 32B Preview
Qwen reasoning model for deliberate problem solving, math, and coding
32,768 ctx
Qwen25 VL 72b
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
Qwen3 30B A3B Instruct 2507
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Qwen3 Coder 30B A3B Instruct
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Qwen3 Max 2026-01-23
Compact GPT model for low-latency assistance and high-volume workloads
256,000 ctx
Qwen3 VL 235B A22B Instruct Original
Compact GPT model for low-latency assistance and high-volume workloads
32,768 ctx
Qwen3 VL 235B A22B Thinking
Compact GPT model for low-latency assistance and high-volume workloads
32,768 ctxreasoning
Qwen3.5 122B A10B
Compact GPT model for low-latency assistance and high-volume workloads
260,096 ctx
Qwen3.5 122B A10B Thinking
Compact GPT model for low-latency assistance and high-volume workloads
260,096 ctxreasoning
Qwen3.5 27B
Compact GPT model for low-latency assistance and high-volume workloads
260,096 ctx
Qwen3.5 27B Thinking
Compact GPT model for low-latency assistance and high-volume workloads
260,096 ctxreasoning
Qwen3.5 35B A3B
Compact GPT model for low-latency assistance and high-volume workloads
260,096 ctx
Qwen3.5 35B A3B Thinking
Compact GPT model for low-latency assistance and high-volume workloads
260,096 ctxreasoning
Qwen3.5 Flash
Compact GPT model for low-latency assistance and high-volume workloads
991,808 ctx
Qwen3.5 Flash Thinking
Compact GPT model for low-latency assistance and high-volume workloads
991,808 ctxreasoning
Qwen3.5 Omni Flash
Omni-modal model for text, vision, audio, and multimodal agent tasks
49,152 ctx
Qwen3.5 Omni Plus
Omni-modal model for text, vision, audio, and multimodal agent tasks
983,616 ctx
Qwen3.6 Max Preview
Compact GPT model for low-latency assistance and high-volume workloads
245,800 ctx
Qwen3.7 Max
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctx
Qwen3.7 Max Thinking
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctxreasoning
Qwen3.7 Plus
Compact GPT model for low-latency assistance and high-volume workloads
991,808 ctx
Qwen3.7 Plus Thinking
Compact GPT model for low-latency assistance and high-volume workloads
983,616 ctxreasoning
Qwen: QwQ 32B
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Sarvam 105B
Compact GPT model for low-latency assistance and high-volume workloads
131,072 ctxreasoning
Sarvam 30B
Compact GPT model for low-latency assistance and high-volume workloads
65,536 ctxreasoning
Shisa V2 Llama 3.3 70B
Open Llama instruction model for multilingual chat, reasoning, and coding
128,000 ctx
Shisa V2.1 Llama 3.3 70B
Open Llama instruction model for multilingual chat, reasoning, and coding
32,768 ctx
Perplexity Simple
Compact GPT model for low-latency assistance and high-volume workloads
127,000 ctx
Perplexity Deep Research
Research model for long-horizon investigation, synthesis, and analytical reports
60,000 ctx
Perplexity Pro
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctx
Perplexity Reasoning Pro
O-series reasoning model for hard analysis, math, coding, and planning
127,000 ctxreasoning
Grayline Qwen3 8B
Qwen instruction model for multilingual chat, reasoning, and tool use
16,384 ctx
Veiled Calla 12B
Open Llama instruction model for multilingual chat, reasoning, and coding
32,768 ctx
Amoral Gemma3 27B v2
Open Gemma instruction model for efficient chat and self-hosted deployments
32,768 ctx
Step-2 16k Exp
Compact GPT model for low-latency assistance and high-volume workloads
16,000 ctx
Step-2 Mini
Compact GPT model for low-latency assistance and high-volume workloads
8,000 ctx
Step-3
Compact GPT model for low-latency assistance and high-volume workloads
65,536 ctx
Step R1 V Mini
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Step 3.5 Flash
StepFun flash model for efficient multimodal reasoning, coding, and tool use
256,000 ctxreasoning
Step 3.5 Flash 2603
StepFun flash model for efficient multimodal reasoning, coding, and tool use
256,000 ctxreasoning
Step 3.7 Flash Thinking
StepFun flash model for efficient multimodal reasoning, coding, and tool use
256,000 ctxreasoning
Hunyuan MT 7B
Translation model for multilingual conversion, localization, and cross-language workflows
8,192 ctx
Tencent: Hy3 preview
Tencent Hy reasoning model for coding, instruction following, and agent tasks
262,144 ctx
ReMM SLERP 13B
Open Llama multimodal model for image understanding and text reasoning
6,144 ctx
Universal Summarizer
Compact GPT model for low-latency assistance and high-volume workloads
32,768 ctx
Gemma 3 12B IT
Open Gemma instruction model for efficient chat and self-hosted deployments
128,000 ctx
Gemma 3 27B IT
Open Gemma instruction model for efficient chat and self-hosted deployments
128,000 ctx
Gemma 3 4B IT
Open Gemma instruction model for efficient chat and self-hosted deployments
128,000 ctx
Solar Pro 3
Flagship model for demanding analysis, coding, and production agent workflows
128,000 ctx
v0 1.0 MD
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctx
v0 1.5 LG
Compact GPT model for low-latency assistance and high-volume workloads
1,000,000 ctx
v0 1.5 MD
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctx
Venice Uncensored
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
Venice Uncensored Web
Compact GPT model for low-latency assistance and high-volume workloads
80,000 ctx
Grok 4.20
Grok model for agentic tool use, reasoning, coding, and live assistance
2,000,000 ctxreasoning
Grok 4.20 Multi-Agent
Grok model for agentic tool use, reasoning, coding, and live assistance
2,000,000 ctxreasoning
Grok 4.3
Grok model for agentic tool use, reasoning, coding, and live assistance
1,000,000 ctxreasoning
Grok Build 0.1
Grok coding model for agentic engineering, edits, and codebase workflows
256,000 ctxreasoning
Grok Latest
Grok model for agentic tool use, reasoning, coding, and live assistance
1,000,000 ctxreasoning
MiMo V2 Flash
MiMo flash model for fast multimodal assistance and agent workflows
256,000 ctxreasoning
MiMo V2 Flash Original
MiMo flash model for fast multimodal assistance and agent workflows
256,000 ctxreasoning
MiMo V2 Flash (Thinking)
MiMo flash model for fast multimodal assistance and agent workflows
256,000 ctxreasoning
MiMo V2 Flash (Thinking) Original
MiMo flash model for fast multimodal assistance and agent workflows
256,000 ctxreasoning
MiMo V2 Omni
MiMo omni model for text, image, video, audio, and agents
262,144 ctxreasoning
MiMo V2 Pro
MiMo pro model for strong multimodal reasoning and agent execution
1,048,576 ctxreasoning
MiMo V2.5
MiMo omni model for text, image, video, audio, and agents
1,048,576 ctxreasoning
MiMo V2.5 Pro
MiMo pro model for strong multimodal reasoning and agent execution
1,048,576 ctxreasoning
Yi Large
Compact GPT model for low-latency assistance and high-volume workloads
32,000 ctx
Yi Lightning
Compact GPT model for low-latency assistance and high-volume workloads
12,000 ctx
Yi Medium 200k
Compact GPT model for low-latency assistance and high-volume workloads
200,000 ctx
GLM 4.5V
GLM vision model for visual reasoning, documents, and multimodal agents
64,000 ctxreasoning
GLM 4.5V Thinking
GLM vision model for visual reasoning, documents, and multimodal agents
64,000 ctxreasoning
GLM 4.6
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 4.6 Thinking
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 5 Turbo
Efficient GLM model for fast reasoning, coding, and agent workflows
202,800 ctx
GLM 5V Turbo
GLM vision model for visual reasoning, documents, and multimodal agents
202,800 ctx
GLM 5V Turbo Thinking
GLM vision model for visual reasoning, documents, and multimodal agents
202,800 ctxreasoning
GLM 4.5 Air
Efficient GLM model for fast reasoning, coding, and agent workflows
128,000 ctx
GLM 4.5 Air (Thinking)
Efficient GLM model for fast reasoning, coding, and agent workflows
128,000 ctxreasoning
GLM 4.5 (Thinking)
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
128,000 ctxreasoning
GLM 4.6 Turbo
Efficient GLM model for fast reasoning, coding, and agent workflows
200,000 ctx
GLM 4.6 Turbo (Thinking)
Efficient GLM model for fast reasoning, coding, and agent workflows
200,000 ctxreasoning
GLM 4.5
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
128,000 ctx
GLM 4.6 Original
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
256,000 ctxreasoning
GLM 4.6V
GLM vision model for visual reasoning, documents, and multimodal agents
128,000 ctx
GLM 4.6V Flash
GLM vision model for visual reasoning, documents, and multimodal agents
128,000 ctx
GLM 4.6V Original
GLM vision model for visual reasoning, documents, and multimodal agents
128,000 ctx
GLM 4.7
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 4.7 Flash
Efficient GLM model for fast reasoning, coding, and agent workflows
200,000 ctxreasoning
GLM 4.7 Flash Original
Efficient GLM model for fast reasoning, coding, and agent workflows
200,000 ctxreasoning
GLM 4.7 Flash Original Thinking
Efficient GLM model for fast reasoning, coding, and agent workflows
200,000 ctxreasoning
GLM 4.7 Flash Thinking
Efficient GLM model for fast reasoning, coding, and agent workflows
200,000 ctxreasoning
GLM 4.7 Original
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 4.7 Original Thinking
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 4.7 Thinking
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 5
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 5 Original
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 5 Original Thinking
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 5.1
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 5.1 Thinking
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM 5 Thinking
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
GLM Latest
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
200,000 ctxreasoning
Community Rating
—
No ratings yet
Sign in to rate