inference-providers

Models

99 models, rendered from the emitted catalog. Open a model for its facts and every provider offering.

99 models · 34 providers · 366 offerings

ModelLabFamilyReleasedAA IndexReasoningContextOutputOpen weightsProvidersOfferings
Qwen3.7 Flashalibabaqwen32026-07-27—effort none–max (med)1,000,000—no
1

OpenRouterqwen/qwen3.7-flash

1
Qwen3.7 Maxalibabaqwen32026-05-20—adaptive1,000,00016,384no
2

NEAR AI Cloudqwen/qwen3.7-max

OpenCode Goqwen3.7-max

2
Qwen3.7 Plusalibabaqwen32026-06-0239v4.1.1effort none–max (med) / toggle1,048,57665,536no
4

Alibaba Model Studio (DashScope)×2qwen3.7-plus

OpenCode Goqwen3.7-plus

OpenRouterqwen/qwen3.7-plus

Qwen Coding Planqwen3.7-plus

5
Qwen3.8 2.4T A95Balibabaqwen32026-08-12—effort low–xhigh (xhigh)1,048,576—yes
1

OpenRouterqwen/qwen3.8-2.4t-a95b

1
Qwen3.8 27Balibabaqwen32026-08-1452v4.1.1effort none–max (med) / toggle / adaptive262,14465,536yes
5

Hetzner Inference (Experiments)Qwen/Qwen3.8-27B

IO Intelligence (io.net)Qwen/Qwen3.8-27B

NEAR AI CloudQwen/Qwen3.8-27B

OpenRouterqwen/qwen3.8-27b

Synthetic×2hf:Qwen/Qwen3.8-27B syn:small:vision

6
Qwen3.8 Flashalibabaqwen2026-08-26—effort none–max (med) / toggle1,000,000—yes
2

OpenCode Goqwen3.8-flash

OpenRouterqwen/qwen3.8-flash

2
Qwen3.8 Maxalibabaqwen32026-08-0358v4.1.1effort minimal–xhigh (xhigh) / toggle1,048,576—no
3

Alibaba Model Studio (DashScope)qwen3.8-max

OpenCode Goqwen3.8-max

OpenRouterqwen/qwen3.8-max-0902

3
OLMo 3 32B Thinkallenaiolmo2025-11-20—effort low–max (high) / always-on65,536—yes
2

OpenCode Zenolmo-3-32b-think

OpenRouterallenai/olmo-3-32b-think

2
Nova 2 Liteamazonnova2025-12-02—effort low–high (low)1,000,000—no
1

OpenRouteramazon/nova-2-lite-v1

1
Claude Fable 5anthropicclaude2026-06-0962v4.1.1effort low–max (high) / adaptive1,000,000128,000no
5

Anthropicclaude-fable-5

AWS Bedrockanthropic.claude-fable-5

NEAR AI Cloudanthropic/claude-fable-5

OpenCode Zenclaude-fable-5

OpenRouteranthropic/claude-fable-5

5
Claude Fable 5.1anthropicclaude2026-09-01—effort low–max (high) / adaptive1,000,000128,000no
3

NEAR AI Cloudanthropic/claude-fable-5-1

OpenCode Zenclaude-fable-5-1

OpenRouteranthropic/claude-fable-5.1

3
Claude Haiku 4.5anthropicclaude2025-10-0130v4.1.1effort none–max (high) / budget 1k+ / adaptive200,00064,000no
5

Anthropicclaude-haiku-4-5

AWS Bedrockanthropic.claude-haiku-4-5-20251001-v1:0

NEAR AI Cloudanthropic/claude-haiku-4-5

OpenCode Zenclaude-haiku-4-5

OpenRouteranthropic/claude-haiku-4.5

5
Claude Opus 4.6anthropicclaude2026-02-04—effort low–max (high) / adaptive1,000,00032,768no
3

NEAR AI Cloudanthropic/claude-opus-4-6

OpenCode Zenclaude-opus-4-6

OpenRouteranthropic/claude-opus-4.6

3
Claude Opus 4.7anthropicclaude2026-04-16—effort low–max (high) / adaptive1,000,00032,768no
3

NEAR AI Cloudanthropic/claude-opus-4-7

OpenCode Zenclaude-opus-4-7

OpenRouteranthropic/claude-opus-4.7

3
Claude Opus 4.8anthropicclaude2026-05-27—effort low–max (high) / adaptive1,000,000—no
3

NEAR AI Cloudanthropic/claude-opus-4-8

OpenCode Zenclaude-opus-4-8

OpenRouter×2anthropic/claude-opus-4.8-fast anthropic/claude-opus-4.8

4
Claude Opus 5anthropicclaude2026-07-2463v4.1.1effort none–max (high) / adaptive1,000,000128,000no
5

Anthropicclaude-opus-5

AWS Bedrockanthropic.claude-opus-5

NEAR AI Cloudanthropic/claude-opus-5

OpenCode Zenclaude-opus-5

OpenRouteranthropic/claude-opus-5

5
Claude Sonnet 5anthropicclaude2026-06-3055v4.1.1effort none–max (high) / adaptive1,000,000128,000no
5

Anthropicclaude-sonnet-5

AWS Bedrockanthropic.claude-sonnet-5

NEAR AI Cloudanthropic/claude-sonnet-5

OpenCode Zenclaude-sonnet-5

OpenRouteranthropic/claude-sonnet-5

5
ERNIE 4.5 VL 424B A47Bbaiduernie2025-06-30—effort none–max (med)123,000—yes
1

OpenRouterbaidu/ernie-4.5-vl-424b-a47b

1
Seed 2.0 Codebytedanceseed2026-02-14—effort none–max (med)262,144—no
1

OpenRouterbytedance-seed/seed-2.0-code

1
Seed 2.0 Litebytedanceseed2026-02-14—effort none–max (med)262,144—no
1

OpenRouterbytedance-seed/seed-2.0-lite

1
Seed 2.0 Minibytedanceseed2026-02-14—effort none–max (med)262,144—no
1

OpenRouterbytedance-seed/seed-2.0-mini

1
Seed 2.1 Turbobytedanceseed2026-06-23—effort none–max (med)262,144—no
1

OpenRouterbytedance-seed/seed-2-1-turbo

1
Command A Reasoning (08-2025)coherecommand2025-08-21—effort none–high (high)262,14432,768yes
1

Coherecommand-a-reasoning-08-2025

1
Command A+ (05-2026)coherecommand2026-05-2023v4.1.1—131,07265,536yes
1

Coherecommand-a-plus-05-2026

1
DeepSeek V4 Flashdeepseekdeepseek-v42026-07-3152v4.1.1effort none–max (high) / toggle1,310,720384,000no
8

Basetendeepseek-ai/DeepSeek-V4-Flash-0731

DeepSeek×2deepseek-v4-flash

IO Intelligence (io.net)deepseek-ai/DeepSeek-V4-Flash

NEAR AI Clouddeepseek-ai/DeepSeek-V4-Flash

Ollama Clouddeepseek-v4-flash:0731

OpenCode Godeepseek-v4-flash

OpenCode Zendeepseek-v4-flash

OpenRouter×2deepseek/deepseek-v4-flash-0731 deepseek/deepseek-v4-flash

10
DeepSeek V4 Prodeepseekdeepseek-v42026-08-1353v4.1.1effort none–max (med) / toggle / adaptive1,048,576384,000no
9

Alibaba Token Plandeepseek-v4-pro

DeepSeek×2deepseek-v4-pro

Fireworks AIdeepseek-v4-pro

IO Intelligence (io.net)deepseek-ai/DeepSeek-V4-Pro

NVIDIA NIM APIdeepseek-ai/deepseek-v4-pro

Ollama Clouddeepseek-v4-pro:0813

OpenCode Godeepseek-v4-pro

OpenCode Zendeepseek-v4-pro

OpenRouter×2deepseek/deepseek-v4-pro-0813 deepseek/deepseek-v4-pro

11
Gemini 3 Flashgooglegemini2025-12-17—effort none–max (med)1,048,57665,536no
3

Google Gemini APIgemini-3-flash-preview

OpenCode Zengemini-3-flash

OpenRoutergoogle/gemini-3-flash-preview

3
Gemini 3 Progooglegemini2025-11-1841v4.1.1effort low–high (high)1,048,57665,536no
2

Google Gemini APIgemini-3-pro-preview

Google Vertex AIgemini-3-pro-preview

2
Gemini 3.1 Progooglegemini2026-02-19—effort none–max (med)1,048,57665,536no
3

Google Gemini APIgemini-3.1-pro-preview

OpenCode Zengemini-3.1-pro

OpenRoutergoogle/gemini-3.1-pro-preview

3
Gemini 3.5 Flashgooglegemini2026-05-19—effort minimal–high (med) / adaptive1,048,5768,192no
3

NEAR AI Cloudgoogle/gemini-3.5-flash

OpenCode Zengemini-3.5-flash

OpenRoutergoogle/gemini-3.5-flash

3
Gemini 3.5 Flash-Litegooglegemini2026-07-2137v4.1.1effort none–max (med)1,048,57665,536no
4

Google Gemini APIgemini-3.5-flash-lite

Google Vertex AIgemini-3.5-flash-lite

OpenCode Zengemini-3.5-flash-lite

OpenRoutergoogle/gemini-3.5-flash-lite

4
Gemini 3.6 Flashgooglegemini2026-07-2152v4.1.1effort none–max (med)1,048,57665,536no
4

Google Gemini APIgemini-3.6-flash

Google Vertex AIgemini-3.6-flash

OpenCode Zengemini-3.6-flash

OpenRoutergoogle/gemini-3.6-flash

4
Gemini 3.7 Flashgooglegemini2026-08-1356v4.1.1effort none–max (med)1,048,57665,536no
4

Google Gemini APIgemini-3.7-flash

Google Vertex AIgemini-3.7-flash

OpenCode Zengemini-3.7-flash

OpenRoutergoogle/gemini-3.7-flash

4
Gemini 3.8 Flashgooglegemini2026-09-03—effort none–max (med)1,048,576—no
3

NEAR AI Cloudgoogle/gemini-3.8-flash

OpenCode Zengemini-3.8-flash

OpenRoutergoogle/gemini-3.8-flash

3
Gemma 4googlegemma2026-03-3130v4.1.1effort none–max (med) / adaptive262,1448,192yes
6

Google Gemini APIgemma-4-31b-it

IO Intelligence (io.net)google/gemma-4-26b-a4b-it

NEAR AI Cloudgoogle/gemma-4-31B-it

NVIDIA NIM APIgoogle/gemma-4-31b-it

Ollama Cloudgemma4:31b

OpenRouter×2google/gemma-4-26b-a4b-it google/gemma-4-31b-it

7
Granite 4.1 8Bibmgranite2026-04-29——131,072—yes
1

OpenRouteribm-granite/granite-4.1-8b

1
Granite 4.2 8Bibmgranite2026-08-07—effort none–max (med)131,072—yes
1

OpenRouteribm-granite/granite-4.2-8b

1
Mercury 2inceptionmercury2026-03-04—effort low–high (high)128,000—no
1

OpenRouterinception/mercury-2

1
Ling 3.0 Flashinclusionailing2026-07-23—effort none–max (med)262,144—yes
1

OpenRouterinclusionai/ling-3.0-flash

1
KAT-Coder Pro v2.5kwaipilotkat2026-07-10——262,144—no
1

OpenRouterkwaipilot/kat-coder-pro-v2.5

1
LFM2.5-2.6Bliquidlfm2026-08-11—effort low–high (high)65,536—yes
1

OpenRouterliquid/lfm-2.5-2.6b:free

1
LongCat 2.0meituanlongcat2026-06-30—effort none–max (med) / toggle1,048,756—yes
3

OpenCode Golongcat-2.0

OpenCode Zenlongcat-2.0

OpenRoutermeituan/longcat-2.0

3
Llama 3.3 70Bmetallama2024-12-06——131,072—yes
3

IO Intelligence (io.net)meta-llama/Llama-3.3-70B-Instruct

NVIDIA NIM APImeta/llama-3.3-70b-instruct

OpenRoutermeta-llama/llama-3.3-70b-instruct

3
Llama 4 Maverickmetallama2025-04-2714v4.1.1effort none–max (med)1,048,576—yes
2

IO Intelligence (io.net)meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

OpenRoutermeta-llama/llama-4-maverick

2
Muse Glimmer 30Bmetamuse-glimmer2026-08-1035v4.1.1effort none–max (high)131,072—yes
2

NVIDIA NIM APImeta/muse-glimmer-30b

OpenRoutermeta/muse-glimmer-30b

2
Muse Spark 1.2metamuse-spark2026-08-0557v4.1.1effort minimal–max (med)1,048,576131,072no
4

Meta Model API×3muse-spark-1.2 muse-spark-1.2-contributor

OpenCode Go×2muse-spark-1.2-contributor muse-spark-1.2

OpenCode Zenmuse-spark-1.2

OpenRoutermeta/muse-spark-1.2

7
Muse Spark 1.3metamuse-spark2026-09-02—effort low–max (med)1,048,576—no
3

OpenCode Gomuse-spark-1.3-contributor

OpenCode Zen×2muse-spark-1.3-contributor-free muse-spark-1.3

OpenRouter×2meta/muse-spark-1.3-contributor meta/muse-spark-1.3

5
Phi-4 Mini Flash Reasoningmicrosoftphi—————yes—0
MiniMax M2.5minimaxminimax-m2026-02-12—effort low–max (med) / always-on204,800—yes
6

IO Intelligence (io.net)MiniMaxAI/MiniMax-M2.5

MiniMaxMiniMax-M2.5

MiniMax Token PlanMiniMax-M2.5

OpenCode Gominimax-m2.5

OpenCode Zenminimax-m2.5

OpenRouterminimax/minimax-m2.5

6
MiniMax M2.7minimaxminimax-m—39v4.1.1effort none–max (high) / always-on262,10065,536yes
5

IO Intelligence (io.net)MiniMaxAI/MiniMax-M2.7

Ollama Cloudminimax-m2.7

OpenCode Gominimax-m2.7

OpenCode Zenminimax-m2.7

OpenRouterminimax/minimax-m2.7

5
MiniMax M3minimaxminimax-m2026-06-0145v4.1.1effort none–max (med) / toggle1,000,000—no
7

MiniMaxMiniMax-M3

MiniMax Token PlanMiniMax-M3

NVIDIA NIM APIminimaxai/minimax-m3

Ollama Cloudminimax-m3

OpenCode Gominimax-m3

OpenCode Zenminimax-m3

OpenRouterminimax/minimax-m3

7
Mistral Large 3mistralmistral-large2025-12-0216v4.1.1—262,144—yes
2

Ollama Cloudmistral-large-3:675b

OpenRoutermistralai/mistral-large-2512

2
Mistral Medium 3.5mistralmistral-medium2026-04-2830v4.1.1effort none–max (med)256,000——
2

Mistralmistral-medium-3.5

OpenRoutermistralai/mistral-medium-3-5

2
Mistral Small (latest)mistralmistral-small2026-03-16—effort none–high (none)256,000——
1

Mistralmistral-small-latest

1
Kimi K2.5moonshotkimi2026-01-27—effort none–max (med) / toggle262,144—no
5

IO Intelligence (io.net)moonshotai/Kimi-K2.5

Moonshot Kimikimi-k2.5

OpenCode Gokimi-k2.5

OpenCode Zenkimi-k2.5

OpenRoutermoonshotai/kimi-k2.5

5
Kimi K2.6moonshotkimi2026-04-2045v4.1.1effort none–max (med) / toggle262,1448,192no
9

Fireworks AIkimi-k2p6

IO Intelligence (io.net)moonshotai/Kimi-K2.6

Moonshot Kimikimi-k2.6

NEAR AI Cloudmoonshotai/kimi-k2.6

NVIDIA NIM APImoonshotai/kimi-k2.6

Ollama Cloudkimi-k2.6

OpenCode Gokimi-k2.6

OpenCode Zenkimi-k2.6

OpenRoutermoonshotai/kimi-k2.6

9
Kimi K2.7 Codemoonshotkimi2026-06-1243v4.1.1effort none–max (high) / toggle262,144—no
8

Alibaba Token Plankimi-k2.7-code

IO Intelligence (io.net)moonshotai/Kimi-K2.7-Code

Kimi for Coding×2kimi-for-coding-highspeed kimi-for-coding

Moonshot Kimi×3kimi-k2.7-code kimi-k2.7-code-highspeed

Ollama Cloudkimi-k2.7-code

OpenCode Gokimi-k2.7-code

OpenCode Zenkimi-k2.7-code

OpenRoutermoonshotai/kimi-k2.7-code

11
Kimi K3moonshotkimi2026-07-2260v4.1.1effort none–max (high) / toggle / adaptive / always-on1,048,57665,535no
11

Basetenmoonshotai/Kimi-K3

IO Intelligence (io.net)moonshotai/Kimi-K3

Kimi for Coding×2k3-256k k3

Moonshot Kimikimi-k3

NEAR AI Cloudmoonshotai/kimi-k3

NVIDIA NIM APImoonshotai/kimi-k3

Ollama Cloudkimi-k3

OpenCode Gokimi-k3

OpenCode Zenkimi-k3

OpenRoutermoonshotai/kimi-k3

Synthetic×2hf:moonshotai/Kimi-K3 syn:large:vision

13
Motif-3motifmotif2026-08-1347v4.1.1———yes—0
Nex N2 Mininex-aginex2026-06-24—effort none–max (med)262,144—yes
1

OpenRouternex-agi/nex-n2-mini

1
Nex N2 Pronex-aginex2026-06-08—effort none–max (med)262,144—yes
1

OpenRouternex-agi/nex-n2-pro

1
Nex N2.5 Mininex-aginex2026-09-08—effort none–max (med)262,144—no
1

OpenRouternex-agi/nex-n2.5-mini:free

1
Nex N2.5 Pronex-aginex2026-09-08—effort none–max (med)262,144—no
1

OpenRouternex-agi/nex-n2.5-pro:free

1
Nemotron 3 Nano 30B A3Bnvidianemotron2025-12-15—effort none–max (med)262,144—yes
1

OpenRouternvidia/nemotron-3-nano-30b-a3b

1
Nemotron 3 Supernvidianemotron2026-03-11—effort none–max (med) / toggle1,000,000—yes
4

NVIDIA NIM APInvidia/nemotron-3-super-120b-a12b

Ollama Cloudnemotron-3-super

OpenRouternvidia/nemotron-3-super-120b-a12b

Synthetichf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4

4
Nemotron 3 Ultranvidianemotron2026-06-0438v4.1.1effort none–max (med) / toggle1,000,000—yes
4

NVIDIA NIM APInvidia/nemotron-3-ultra-550b-a55b

Ollama Cloudnemotron-3-ultra

OpenCode Zennemotron-3-ultra-free

OpenRouternvidia/nemotron-3-ultra-550b-a55b

4
Nemotron 3.5 Lightningnvidianemotron2026-08-1124v4.1.1effort none–max (med) / toggle1,000,000—yes
3

NVIDIA NIM APInvidia/nemotron-3.5-lightning-30b-a3b

OpenCode Zennemotron-3.5-lightning-free

OpenRouternvidia/nemotron-3.5-lightning

3
GPT-5openaigpt2025-08-0735v4.1.1effort minimal–max (med)400,000128,000no
4

NEAR AI Cloudopenai/gpt-5

OpenAI×2gpt-5

OpenCode Zengpt-5

OpenRouteropenai/gpt-5

5
GPT-5.1openaigpt2025-11-1337v4.1.1effort none–max (med)400,000128,000no
4

NEAR AI Cloudopenai/gpt-5.1

OpenAI×2gpt-5.1

OpenCode Zengpt-5.1

OpenRouteropenai/gpt-5.1

5
GPT-5.4openaigpt2026-03-05—effort none–xhigh (none)1,050,00016,384no
3

NEAR AI Cloudopenai/gpt-5.4

OpenCode Zen×2gpt-5.4-pro gpt-5.4

OpenRouter×2openai/gpt-5.4-pro openai/gpt-5.4

5
GPT-5.4 miniopenaigpt2026-03-17—effort none–xhigh (none)400,00016,384no
3

NEAR AI Cloudopenai/gpt-5.4-mini

OpenCode Zengpt-5.4-mini

OpenRouteropenai/gpt-5.4-mini

3
GPT-5.4 nanoopenaigpt2026-03-17—effort none–xhigh (none)400,00016,384no
3

NEAR AI Cloudopenai/gpt-5.4-nano

OpenCode Zengpt-5.4-nano

OpenRouteropenai/gpt-5.4-nano

3
GPT-5.5openaigpt2026-04-23—effort none–max (med)1,050,000128,000no
4

NEAR AI Cloudopenai/gpt-5.5

OpenAI×2gpt-5.5

OpenCode Zen×2gpt-5.5-pro gpt-5.5

OpenRouter×2openai/gpt-5.5-pro openai/gpt-5.5

7
GPT-5.6openaigpt2026-06-2561v4.1.1effort none–max (med)1,050,000128,000no
6

Azure AI Foundrygpt-5.6

NEAR AI Cloud×2openai/gpt-5.6-luna openai/gpt-5.6-sol

OpenAI×5gpt-5.6 gpt-5.6-luna gpt-5.6-sol gpt-5.6-terra

OpenCode Gogpt-5.6-luna

OpenCode Zen×3gpt-5.6-luna gpt-5.6-sol gpt-5.6-terra

OpenRouter×6openai/gpt-5.6-luna-pro openai/gpt-5.6-luna openai/gpt-5.6-sol-pro openai/gpt-5.6-sol openai/gpt-5.6-terra-pro openai/gpt-5.6-terra

18
GPT-6 Astraopenaigpt2026-09-03—effort low–max (med)1,050,000128,000no
3

NEAR AI Cloudopenai/gpt-6-astra

OpenCode Zengpt-6-astra

OpenRouter×2openai/gpt-6-astra-pro openai/gpt-6-astra

4
GPT-OSS 120Bopenaigpt-oss2025-08-0524v4.1.1effort none–max (med) / toggle / adaptive131,072—yes
8

Basetenopenai/gpt-oss-120b

Fireworks AIgpt-oss-120b

IO Intelligence (io.net)openai/gpt-oss-120b

NEAR AI Cloudopenai/gpt-oss-120b

NVIDIA NIM APIopenai/gpt-oss-120b

Ollama Cloudgpt-oss:120b

OpenRouteropenai/gpt-oss-120b

Synthetichf:openai/gpt-oss-120b

8
GPT-OSS 20Bopenaigpt-oss2025-08-0515v4.1.1effort none–max (med) / toggle131,072—yes
4

IO Intelligence (io.net)openai/gpt-oss-20b

NVIDIA NIM APIopenai/gpt-oss-20b

Ollama Cloudgpt-oss:20b

OpenRouteropenai/gpt-oss-20b

4
o3openaio2025-04-1631v4.1.1effort low–max (med)200,000100,000no
3

NEAR AI Cloudopenai/o3

OpenAI×2o3

OpenRouteropenai/o3

4
Laguna S 2.1poolsidelaguna——effort none–max (med) / adaptive1,048,576—yes
2

OpenRouterpoolside/laguna-s-2.1

poolsidepoolside/laguna-s-2.1

2
Laguna XS 2.1poolsidelaguna——effort none–max (med) / adaptive262,144—yes
3

NVIDIA NIM APIpoolside/laguna-xs-2.1

OpenRouterpoolside/laguna-xs-2.1

poolsidepoolside/laguna-xs-2.1

3
Fugu Ultrasakanafugu2026-06-24—effort none–max (med)1,000,000—no
1

OpenRoutersakana/fugu-ultra

1
Step-3.5 Flashstepfunstep2026-01-2927v4.1.1effort minimal–xhigh (med) / adaptive262,144—yes
2

OpenRouterstepfun/step-3.5-flash

StepFunstep-3.5-flash

2
Step-3.7 Flashstepfunstep—31v4.1.1effort low–high (med)262,144—yes
3

NVIDIA NIM APIstepfun-ai/step-3.7-flash

OpenRouterstepfun/step-3.7-flash

StepFunstep-3.7-flash

3
Hy3tencenthy32026-07-0642v4.1.1effort none–high (high) / adaptive262,144131,072yes
2

OpenCode Go×2hy3-preview hy3

OpenRoutertencent/hy3

3
Hy4 Previewtencenthy42026-08-28—effort none–high (high)——yes
1

OpenCode Gohy4-preview

1
Inklingthinkingmachinesinkling2026-07-1542v4.1.1effort none–max (med)1,048,57632,768no
2

Basetenthinkingmachines/inkling

OpenRouterthinkingmachines/inkling

2
Inkling Smallthinkingmachinesinkling2026-07-2941v4.1.1effort none–max (med)1,048,57632,768no
2

Basetenthinkingmachines/inkling-small

OpenRouterthinkingmachines/inkling-small

2
Solar Pro 4upstagesolar2026-08-10—adaptive524,288—no
1

OpenRouterupstage/solar-pro4

1
Grok 4.5xaigrok2026-07-1656v4.1.1effort low–max (high)500,000—no
4

OpenCode Gogrok-4.5

OpenCode Zengrok-4.5

OpenRouterx-ai/grok-4.5

xAI×2grok-4.5

5
Grok 4.6xaigrok2026-08-1261v4.1.1effort low–max (high)500,000—no
4

OpenCode Gogrok-4.6

OpenCode Zengrok-4.6

OpenRouterx-ai/grok-4.6

xAI×2grok-4.6

5
MiMo V2.5xiaomimimo2026-04-2338v4.1.1effort none–max (med) / adaptive1,048,576—yes
4

IO Intelligence (io.net)XiaomiMiMo/MiMo-V2.5

OpenCode Gomimo-v2.5

OpenRouterxiaomi/mimo-v2.5

Xiaomi MiMomimo-v2.5

4
MiMo V2.5 Proxiaomimimo2026-04-2343v4.1.1effort none–max (med) / adaptive1,048,576—yes
3

OpenCode Gomimo-v2.5-pro

OpenRouterxiaomi/mimo-v2.5-pro

Xiaomi MiMomimo-v2.5-pro

3
GLM-4.6zaiglm2025-09-3029v4.1.1effort none–max (med) / toggle200,000—yes
4

IO Intelligence (io.net)zai-org/GLM-4.6

OpenRouterz-ai/glm-4.6

Z.aiglm-4.6

Z.ai GLM Coding Planglm-4.6

4
GLM-4.7zaiglm2025-12-2234v4.1.1effort none–max (med) / adaptive202,752128,000yes
3

Fireworks AIglm-4p7

IO Intelligence (io.net)zai-org/GLM-4.7

OpenRouterz-ai/glm-4.7

3
GLM-4.7 Flashzaiglm2026-01-19—effort none–max (med)202,752—yes
3

IO Intelligence (io.net)zai-org/GLM-4.7-Flash

OpenRouterz-ai/glm-4.7-flash

Synthetic×2hf:zai-org/GLM-4.7-Flash syn:small:text

4
GLM-5.1zaiglm2026-04-07—effort none–max (med) / toggle204,800131,072yes
6

IO Intelligence (io.net)zai-org/GLM-5.1

Ollama Cloudglm-5.1

OpenCode Goglm-5.1

OpenCode Zenglm-5.1

OpenRouterz-ai/glm-5.1

Z.aiglm-5.1

6
GLM-5.2zaiglm2026-06-1653v4.1.1effort none–max (med) / toggle / adaptive1,048,576131,072yes
9

Alibaba Token Planglm-5.2

Basetenzai-org/GLM-5.2

IO Intelligence (io.net)zai-org/GLM-5.2

NEAR AI Cloudz-ai/glm-5.2

Ollama Cloudglm-5.2

OpenCode Goglm-5.2

OpenCode Zenglm-5.2

OpenRouterz-ai/glm-5.2

Synthetic×2hf:zai-org/GLM-5.2 syn:large:text

10
GLM-5.3zaiglm2026-08-1860v4.1.1effort low–max (med) / always-on1,048,576131,072no
7

IO Intelligence (io.net)zai-org/GLM-5.3

Ollama Cloudglm-5.3

OpenCode Goglm-5.3

OpenCode Zenglm-5.3

OpenRouterz-ai/glm-5.3

Z.aiglm-5.3

Z.ai GLM Coding Planglm-5.3

7
GLM-5.3 Flashzaiglm2026-08-26—effort low–max (high) / toggle / always-on1,310,720131,072yes
7

IO Intelligence (io.net)zai-org/GLM-5.3-Flash

NEAR AI Cloudz-ai/glm-5.3-flash

Ollama Cloudglm-5.3-flash

OpenCode Goglm-5.3-flash

OpenCode Zenglm-5.3-flash

OpenRouterz-ai/glm-5.3-flash

Z.aiglm-5.3-flash

7

Unknown values are shown as —. Context and output limits are the maximum across the model's offerings that record limits. The Providers count is unique providers — open it for each provider's wire IDs; ×N marks a provider serving the model on N endpoints. AA Index is the Artificial Analysis Intelligence Index for the model's most capable configuration — see the model page for the scored variant.

Intelligence Index v4.1.1 scores by Artificial Analysis, accessed 2026-08-20 — methodology.