All AI Models

540 models across 53 providers. Click any model for detailed pricing, benchmarks, and speed data.

OpenAI

63 models
GPT-5.5 (xhigh)
$11.2571 t/s
GPT-5.5 (high)
$11.2572 t/s
GPT-5.4 (xhigh)
$5.63182 t/s
GPT-5.5 (medium)
$11.2571 t/s
GPT-5.3 Codex (xhigh)
$4.8192 t/s
GPT-5.5 (low)
$11.2567 t/s
GPT-5.2 (xhigh)
$4.8185 t/s
GPT-5.2 Codex (xhigh)
$4.81125 t/s
GPT-5.4 mini (xhigh)
$1.69178 t/s
GPT-5.4 (low)
$5.63108 t/s
GPT-5.4 nano (xhigh)
$0.46150 t/s
GPT-5.2 (medium)
$4.810 t/s
GPT-5.1 (high)
$3.4489 t/s
GPT-5 Codex (high)
$3.44169 t/s
GPT-5.5 (Non-reasoning)
$11.2565 t/s
GPT-5.1 Codex (high)
$3.44201 t/s
GPT-5 (high)
$3.44103 t/s
GPT-5 (medium)
$3.4488 t/s
GPT-5.5 Instant (May 2026)
$11.250 t/s
o3-pro
$35.0039 t/s
GPT-5 (low)
$3.4482 t/s
GPT-5 mini (medium)
$0.6996 t/s
GPT-5.1 Codex mini (high)
$0.69211 t/s
o3
$3.50126 t/s
GPT-5.4 nano (medium)
$0.46156 t/s
GPT-5.4 mini (medium)
$1.69168 t/s
GPT-5.5 Instant (June 2026)
$11.250 t/s
GPT-5.4 (Non-reasoning)
$5.63107 t/s
GPT-5.2 (Non-reasoning)
$4.8169 t/s
o4-mini (high)
$1.93157 t/s
GPT-5 mini (high)
$0.6994 t/s
gpt-oss-120b (high)
$0.26271 t/s
o1
$26.25125 t/s
GPT-5.1 (Non-reasoning)
$3.4493 t/s
GPT-5 nano (high)
$0.14148 t/s
GPT-4.1
$3.50119 t/s
o3-mini
$1.93232 t/s
GPT-5 nano (medium)
$0.14155 t/s
o1-pro
$262.500 t/s
gpt-oss-120b (low)
$0.26329 t/s
GPT-5.4 nano (Non-Reasoning)
$0.46162 t/s
GPT-5 (minimal)
$3.4476 t/s
o1-preview
$28.880 t/s
GPT-5.4 mini (Non-Reasoning)
$1.69162 t/s
o3-mini (high)
$1.93217 t/s
GPT-5 (ChatGPT)
$3.44171 t/s
gpt-oss-20b (high)
$0.09197 t/s
GPT-4.1 mini
$0.7070 t/s
gpt-oss-20b (low)
$0.10227 t/s
GPT-5 mini (minimal)
$0.69104 t/s
o1-mini
$0.000 t/s
GPT-4.5 (Preview)
$0.000 t/s
GPT-4o (March 2025, chatgpt-4o-latest)
$0.000 t/s
GPT-4o (Nov '24)
$4.38207 t/s
GPT-4o (Aug '24)
$4.38112 t/s
GPT-4.1 nano
$0.17166 t/s
GPT-4o (May '24)
$7.50101 t/s
GPT-4o (ChatGPT)
$0.000 t/s
GPT-5 nano (minimal)
$0.14156 t/s
GPT-4 Turbo
$15.0034 t/s
GPT-4
$37.5038 t/s
GPT-4o mini
$0.2673 t/s
GPT-3.5 Turbo
$0.75136 t/s

Anthropic

34 models
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
$20.0067 t/s
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
$10.0062 t/s
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
$10.0055 t/s
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
$4.0084 t/s
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
$6.0075 t/s
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
$10.0050 t/s
Claude Opus 4.7 (Non-reasoning, High Effort)
$10.0051 t/s
Claude Sonnet 5 (Non-reasoning, High Effort)
$4.000 t/s
Claude Opus 4.5 (Reasoning)
$10.0068 t/s
Claude Opus 4.6 (Non-reasoning, High Effort)
$10.0048 t/s
Claude 4.5 Sonnet (Reasoning)
$6.0057 t/s
Claude Sonnet 4.6 (Non-reasoning, High Effort)
$6.0055 t/s
Claude Opus 4.5 (Non-reasoning)
$10.0059 t/s
Claude Sonnet 4.6 (Non-reasoning, Low Effort)
$6.0056 t/s
Claude 4.1 Opus (Reasoning)
$30.0042 t/s
Claude 4 Opus (Reasoning)
$30.000 t/s
Claude 4.5 Haiku (Reasoning)
$2.00137 t/s
Claude 4.5 Sonnet (Non-reasoning)
$6.0054 t/s
Claude 4 Sonnet (Reasoning)
$6.000 t/s
Claude 4.1 Opus (Non-reasoning)
$30.0037 t/s
Claude 3.7 Sonnet (Reasoning)
$0.000 t/s
Claude 4 Sonnet (Non-reasoning)
$6.000 t/s
Claude 4 Opus (Non-reasoning)
$30.000 t/s
Claude 4.5 Haiku (Non-reasoning)
$2.00116 t/s
Claude 3.7 Sonnet (Non-reasoning)
$6.000 t/s
Claude 3.5 Haiku
$1.600 t/s
Claude 3 Opus
$30.000 t/s
Claude 3.5 Sonnet (Oct '24)
$6.000 t/s
Claude 3.5 Sonnet (June '24)
$6.000 t/s
Claude 3 Sonnet
$6.000 t/s
Claude 3 Haiku
$0.500 t/s
Claude 2.1
$0.000 t/s
Claude 2.0
$0.000 t/s
Claude Instant
$0.000 t/s

Google

56 models
Gemini 3.5 Flash (high)
$3.38243 t/s
Gemini 3.1 Pro Preview
$4.50130 t/s
Gemini 3.5 Flash (medium)
$3.38213 t/s
Gemini 3 Pro Preview (high)
$4.500 t/s
Gemini 3 Flash Preview (Reasoning)
$1.13209 t/s
Gemini 3.5 Flash (minimal)
$3.38214 t/s
Gemini 3 Pro Preview (low)
$4.500 t/s
Gemma 4 31B (Reasoning)
$0.0035 t/s
Gemini 3 Flash Preview (Non-reasoning)
$1.13207 t/s
Gemini 2.5 Pro
$3.44142 t/s
Gemma 4 26B A4B (Reasoning)
$0.200 t/s
Gemini 3.1 Flash-Lite
$0.56311 t/s
Gemma 4 31B (Non-reasoning)
$0.2053 t/s
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)
$0.000 t/s
Gemini 2.5 Pro Preview (Mar' 25)
$0.000 t/s
Gemini 2.5 Pro Preview (May' 25)
$3.440 t/s
Gemma 4 12B (Reasoning)
$0.15147 t/s
Gemma 4 26B A4B (Non-reasoning)
$0.2066 t/s
Gemini 2.5 Flash (Reasoning)
$0.85229 t/s
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)
$0.000 t/s
Gemini 2.5 Flash Preview (Reasoning)
$0.000 t/s
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
$0.170 t/s
Gemini 2.5 Flash (Non-reasoning)
$0.85211 t/s
DiffusionGemma 26B A4B
$0.000 t/s
Gemini 2.0 Flash Thinking Experimental (Jan '25)
$0.000 t/s
Gemma 4 12B (Non-reasoning)
$0.15154 t/s
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)
$0.170 t/s
Gemma 4 E4B (Reasoning)
$0.000 t/s
Gemini 2.0 Flash (Feb '25)
$0.260 t/s
Gemini 2.0 Pro Experimental (Feb '25)
$0.000 t/s
Gemini 2.5 Flash Preview (Non-reasoning)
$0.000 t/s
Gemini 2.5 Flash-Lite (Reasoning)
$0.17263 t/s
Gemini 2.0 Flash (experimental)
$0.000 t/s
Gemini 1.5 Pro (Sep '24)
$0.000 t/s
Gemma 4 E2B (Reasoning)
$0.000 t/s
Gemma 4 E4B (Non-reasoning)
$0.000 t/s
Gemini 2.0 Flash-Lite (Feb '25)
$0.000 t/s
Gemini 2.0 Flash-Lite (Preview)
$0.000 t/s
Gemini 1.5 Flash (Sep '24)
$0.000 t/s
Gemma 3 27B Instruct
$0.000 t/s
Gemini 2.5 Flash-Lite (Non-reasoning)
$0.17222 t/s
Gemini 2.0 Flash Thinking Experimental (Dec '24)
$0.000 t/s
Gemma 4 E2B (Non-reasoning)
$0.000 t/s
Gemini 1.5 Pro (May '24)
$0.000 t/s
Gemini 1.5 Flash-8B
$0.000 t/s
Gemma 3 12B Instruct
$0.000 t/s
Gemini 1.5 Flash (May '24)
$0.000 t/s
Gemma 3n E4B Instruct Preview (May '25)
$0.000 t/s
Gemini 1.0 Ultra
$0.000 t/s
PALM-2
$0.000 t/s
Gemini 1.0 Pro
$0.000 t/s
Gemma 3 270M
$0.000 t/s
Gemma 3n E4B Instruct
$0.0355 t/s
Gemma 3 4B Instruct
$0.000 t/s
Gemma 3n E2B Instruct
$0.000 t/s
Gemma 3 1B Instruct
$0.000 t/s

DeepSeek

31 models
DeepSeek V4 Pro (Reasoning, Max Effort)
$0.5460 t/s
DeepSeek V4 Pro (Reasoning, High Effort)
$0.5464 t/s
DeepSeek V4 Flash (Reasoning, Max Effort)
$0.17111 t/s
DeepSeek V4 Flash (Reasoning, High Effort)
$0.170 t/s
DeepSeek V3.2 (Reasoning)
$0.320 t/s
DeepSeek V4 Pro (Non-reasoning)
$0.5469 t/s
DeepSeek V4 Flash (Non-reasoning)
$0.17113 t/s
DeepSeek V3.1 Terminus (Reasoning)
$1.910 t/s
DeepSeek V3.2 Exp (Reasoning)
$0.320 t/s
DeepSeek V3.2 (Non-reasoning)
$0.320 t/s
DeepSeek V3.2 Speciale
$0.000 t/s
DeepSeek V3.1 Terminus (Non-reasoning)
$0.450 t/s
DeepSeek V3.2 Exp (Non-reasoning)
$0.320 t/s
DeepSeek V3.1 (Non-reasoning)
$0.840 t/s
DeepSeek V3.1 (Reasoning)
$0.860 t/s
DeepSeek R1 0528 (May '25)
$2.060 t/s
DeepSeek R1 (Jan '25)
$2.430 t/s
DeepSeek V3 0324
$1.210 t/s
DeepSeek V3 (Dec '24)
$0.520 t/s
DeepSeek R1 Distill Qwen 32B
$0.000 t/s
DeepSeek R1 0528 Qwen3 8B
$0.000 t/s
DeepSeek R1 Distill Llama 70B
$0.7932 t/s
DeepSeek R1 Distill Qwen 14B
$0.000 t/s
DeepSeek-V2.5 (Dec '24)
$0.000 t/s
DeepSeek-V2.5
$0.000 t/s
DeepSeek R1 Distill Llama 8B
$0.000 t/s
DeepSeek-Coder-V2
$0.000 t/s
DeepSeek R1 Distill Qwen 1.5B
$0.000 t/s
DeepSeek-V2-Chat
$0.000 t/s
DeepSeek Coder V2 Lite Instruct
$0.000 t/s
DeepSeek LLM 67B Chat (V1)
$0.000 t/s

Meta

17 models
Muse Spark
$0.000 t/s
Llama 4 Maverick
$0.47113 t/s
Llama 4 Scout
$0.29110 t/s
Llama 3.3 Instruct 70B
$0.6187 t/s
Llama 3.1 Instruct 405B
$3.6984 t/s
Llama 3.1 Instruct 8B
$0.08155 t/s
Llama 3.1 Instruct 70B
$0.5634 t/s
Llama 3.2 Instruct 90B (Vision)
$1.3861 t/s
Llama 2 Chat 7B
$0.10101 t/s
Llama 3.2 Instruct 3B
$0.1553 t/s
Llama 3 Instruct 70B
$1.1847 t/s
Llama 3.2 Instruct 11B (Vision)
$0.3481 t/s
Llama 2 Chat 70B
$0.000 t/s
Llama 2 Chat 13B
$0.000 t/s
Llama 65B
$0.000 t/s
Llama 3 Instruct 8B
$0.0780 t/s
Llama 3.2 Instruct 1B
$0.0587 t/s

Mistral

32 models
Mistral Medium 3.5
$3.0081 t/s
Mistral Small 4 (Reasoning)
$0.26168 t/s
Devstral 2
$0.0061 t/s
Magistral Medium 1.2
$2.7542 t/s
Devstral Small 2
$0.0071 t/s
Mistral Large 3
$0.7563 t/s
Mistral Small 3.1
$0.15163 t/s
Mistral Medium 3.1
$0.8090 t/s
Mistral Medium 3
$0.8045 t/s
Magistral Medium 1
$0.000 t/s
Mistral Small 4 (Non-reasoning)
$0.26165 t/s
Devstral Medium
$0.8079 t/s
Devstral Small (May '25)
$0.000 t/s
Magistral Small 1.2
$0.7583 t/s
Ministral 3 14B
$0.2073 t/s
Magistral Small 1
$0.000 t/s
Mistral Small 3.2
$0.15144 t/s
Devstral Small (Jul '25)
$0.1572 t/s
Mistral Large 2 (Nov '24)
$3.0058 t/s
Ministral 3 8B
$0.15100 t/s
Pixtral Large
$3.0057 t/s
Mistral Large 2 (Jul '24)
$3.000 t/s
Mistral Small 3
$0.15169 t/s
Ministral 3 3B
$0.10167 t/s
Mistral Saba
$0.000 t/s
Mistral Small (Sep '24)
$0.30173 t/s
Mixtral 8x22B Instruct
$0.000 t/s
Mistral Large (Feb '24)
$6.000 t/s
Mistral Small (Feb '24)
$1.50167 t/s
Mistral Medium
$4.09111 t/s
Mixtral 8x7B Instruct
$0.510 t/s
Mistral 7B Instruct
$0.2599 t/s

xAI

22 models
Grok Build 0.1 0616
$1.2545 t/s
Grok 4.3 (high)
$1.56130 t/s
Grok 4.20 0309 v2 (Reasoning)
$3.00165 t/s
Grok 4.20 0309 (Reasoning)
$3.000 t/s
Grok 4.3 (medium)
$1.56108 t/s
Grok 4.3 (low)
$1.56100 t/s
Grok 4
$11.000 t/s
Grok 4.1 Fast (Reasoning)
$0.000 t/s
Grok 4 Fast (Reasoning)
$0.280 t/s
Grok 4.3 (Non-reasoning)
$1.56110 t/s
Grok 3 mini Reasoning (high)
$0.3542 t/s
Grok 4.20 0309 (Non-reasoning)
$3.000 t/s
Grok 4.20 0309 v2 (Non-reasoning)
$3.00145 t/s
Grok Code Fast 1
$0.000 t/s
Grok 3
$8.000 t/s
Grok 4.1 Fast (Non-reasoning)
$0.000 t/s
Grok 4 Fast (Non-reasoning)
$0.280 t/s
Grok 3 Reasoning Beta
$0.000 t/s
Grok 2 (Dec '24)
$0.000 t/s
Grok Beta
$0.000 t/s
Grok-1
$0.000 t/s
Grok 4.5 (high)
$3.000 t/s

Alibaba / Qwen

81 models
Qwen3.7 Max
$3.75201 t/s
Qwen3.6 Max Preview
$2.9242 t/s
Qwen3.6 Plus
$1.1352 t/s
Qwen3.7 Plus
$0.5949 t/s
Qwen3.6 27B (Reasoning)
$1.3563 t/s
Qwen3.5 27B (Reasoning)
$0.8283 t/s
Qwen3.5 397B A17B (Reasoning)
$1.3550 t/s
Qwen3.5 122B A10B (Reasoning)
$1.10144 t/s
Qwen3.5 397B A17B (Non-reasoning)
$1.3550 t/s
Qwen3 Max Thinking
$2.400 t/s
Qwen3.6 35B A3B (Reasoning)
$0.56118 t/s
Qwen3.5 Omni Plus
$1.5056 t/s
Qwen3.6 27B (Non-reasoning)
$1.3559 t/s
Qwen3.5 35B A3B (Reasoning)
$0.69164 t/s
Qwen3.5 27B (Non-reasoning)
$0.8290 t/s
Qwen3.5 122B A10B (Non-reasoning)
$1.10165 t/s
Qwen3 Max Thinking (Preview)
$2.4058 t/s
Qwen3.6 35B A3B (Non-reasoning)
$0.84133 t/s
Qwen3 Max
$2.4050 t/s
Qwen3.5 35B A3B (Non-reasoning)
$0.69177 t/s
Qwen3.5 9B (Reasoning)
$0.1155 t/s
Qwen3 Coder Next
$0.5690 t/s
Qwen3 VL 235B A22B (Reasoning)
$2.6359 t/s
Qwen3.5 9B (Non-reasoning)
$0.000 t/s
Qwen3.5 4B (Reasoning)
$0.0632 t/s
Qwen3 235B A22B 2507 (Reasoning)
$2.6365 t/s
Qwen3 Max (Preview)
$2.4057 t/s
Qwen3.5 Omni Flash
$0.28246 t/s
Qwen3 235B A22B 2507 Instruct
$1.2370 t/s
Qwen3 Coder 480B A35B Instruct
$3.0070 t/s
Qwen3 VL 32B (Reasoning)
$2.6395 t/s
Qwen3 Next 80B A3B (Reasoning)
$1.88116 t/s
Qwen3.5 4B (Non-reasoning)
$0.0626 t/s
Qwen3 30B A3B 2507 (Reasoning)
$0.75142 t/s
Qwen3 VL 235B A22B Instruct
$1.2351 t/s
Qwen3 Next 80B A3B Instruct
$0.88188 t/s
Qwen3 Coder 30B A3B Instruct
$0.90105 t/s
Qwen3 235B A22B (Reasoning)
$2.6366 t/s
QwQ 32B
$0.7432 t/s
Qwen3 VL 30B A3B (Reasoning)
$0.75123 t/s
Qwen3 4B 2507 (Reasoning)
$0.000 t/s
Qwen3 32B (Reasoning)
$2.6397 t/s
Qwen3 VL 32B Instruct
$1.2371 t/s
Qwen3 235B A22B (Non-reasoning)
$1.2366 t/s
Qwen3 VL 8B (Reasoning)
$0.66132 t/s
Qwen3 14B (Reasoning)
$1.3162 t/s
Qwen2.5 Max
$2.800 t/s
Qwen3 VL 30B A3B Instruct
$0.35121 t/s
Qwen3 Omni 30B A3B (Reasoning)
$0.4397 t/s
Qwen2.5 Instruct 72B
$0.000 t/s
Qwen3 30B A3B (Reasoning)
$0.75112 t/s
QwQ 32B-Preview
$0.000 t/s
Qwen3 30B A3B 2507 Instruct
$0.35156 t/s
Qwen3 32B (Non-reasoning)
$1.23101 t/s
Qwen3 4B (Reasoning)
$0.400 t/s
Qwen3 VL 8B Instruct
$0.31142 t/s
Qwen3 8B (Reasoning)
$0.6665 t/s
Qwen3 VL 4B (Reasoning)
$0.000 t/s
Qwen3.5 2B (Reasoning)
$0.000 t/s
Qwen2.5 Instruct 32B
$0.000 t/s
Qwen2.5 Coder Instruct 32B
$0.000 t/s
Qwen3 4B 2507 Instruct
$0.000 t/s
Qwen3 14B (Non-reasoning)
$0.6161 t/s
Qwen3 30B A3B (Non-reasoning)
$0.35114 t/s
Qwen3 4B (Non-reasoning)
$0.190 t/s
Qwen2.5 Turbo
$0.09115 t/s
Qwen2 Instruct 72B
$0.000 t/s
Qwen3.5 2B (Non-reasoning)
$0.000 t/s
Qwen3.5 0.8B (Reasoning)
$0.000 t/s
Qwen3 Omni 30B A3B Instruct
$0.43108 t/s
Qwen3 8B (Non-reasoning)
$0.3163 t/s
Qwen2.5 Coder Instruct 7B
$0.000 t/s
Qwen3.5 0.8B (Non-reasoning)
$0.000 t/s
Qwen3 VL 4B Instruct
$0.000 t/s
Qwen1.5 Chat 110B
$0.000 t/s
Qwen Chat 72B
$0.000 t/s
Qwen3 1.7B (Reasoning)
$0.400 t/s
Qwen Chat 14B
$0.000 t/s
Qwen3 1.7B (Non-reasoning)
$0.190 t/s
Qwen3 0.6B (Reasoning)
$0.400 t/s
Qwen3 0.6B (Non-reasoning)
$0.190 t/s

NVIDIA

18 models
Nemotron 3 Ultra 550B A55B (Reasoning)
$1.18197 t/s
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
$0.38154 t/s
Nemotron Cascade 2 30B A3B
$0.000 t/s
Nemotron 3 Nano Omni 30B A3B Reasoning
$0.13288 t/s
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
$0.09123 t/s
Llama Nemotron Super 49B v1.5 (Reasoning)
$0.4052 t/s
Llama 3.3 Nemotron Super 49B v1 (Reasoning)
$0.000 t/s
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
$0.9052 t/s
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)
$0.30297 t/s
NVIDIA Nemotron Nano 9B V2 (Reasoning)
$0.0793 t/s
NVIDIA Nemotron 3 Nano 4B
$0.000 t/s
Llama Nemotron Super 49B v1.5 (Non-reasoning)
$0.4052 t/s
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)
$0.000 t/s
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)
$0.000 t/s
Llama 3.1 Nemotron Instruct 70B
$1.20307 t/s
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
$0.09157 t/s
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
$0.09113 t/s
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
$0.30218 t/s

Amazon

14 models
Nova 2.0 Pro Preview (medium)
$3.44131 t/s
Nova 2.0 Omni (medium)
$0.850 t/s
Nova 2.0 Pro Preview (low)
$3.44143 t/s
Nova 2.0 Lite (medium)
$0.85172 t/s
Nova 2.0 Lite (high)
$0.85166 t/s
Nova 2.0 Lite (low)
$0.85173 t/s
Nova 2.0 Omni (low)
$0.850 t/s
Nova 2.0 Pro Preview (Non-reasoning)
$3.44132 t/s
Nova Premier
$5.0061 t/s
Nova 2.0 Lite (Non-reasoning)
$0.85237 t/s
Nova 2.0 Omni (Non-reasoning)
$0.850 t/s
Nova Pro
$1.400 t/s
Nova Lite
$0.10174 t/s
Nova Micro
$0.06340 t/s

Microsoft

4 models
Phi-4 Mini Instruct
$0.0046 t/s
Phi-4
$0.2238 t/s
Phi-3 Mini Instruct 3.8B
$0.000 t/s
Phi-4 Multimodal Instruct
$0.0017 t/s

Cohere

6 models
Command A+
$0.00179 t/s
North Mini Code
$0.00108 t/s
Command A
$4.3854 t/s
Command-R+ (Apr '24)
$6.000 t/s
Command-R (Mar '24)
$0.750 t/s
Tiny Aya Global
$0.00136 t/s

Moonshot

9 models
Kimi K2.6
$1.7141 t/s
Kimi K2.7 Code
$1.7141 t/s
Kimi K2.5 (Reasoning)
$1.2038 t/s
Kimi K2.6 (Non-reasoning)
$1.7135 t/s
Kimi K2 Thinking
$1.07168 t/s
Kimi K2.5 (Non-reasoning)
$1.2035 t/s
Kimi K2 0905
$1.0737 t/s
Kimi K2
$1.0437 t/s
Kimi Linear 48B A3B Instruct
$0.000 t/s

ai2

10 models
Llama 3.1 Tulu3 405B
$0.000 t/s
Olmo 3.1 32B Think
$0.000 t/s
Olmo 3.1 32B Instruct
$0.000 t/s
Olmo 3 32B Think
$0.000 t/s
OLMo 2 32B
$0.000 t/s
Olmo 3 7B Think
$0.000 t/s
OLMo 2 7B
$0.000 t/s
Molmo 7B-D
$0.000 t/s
Olmo 3 7B Instruct
$0.130 t/s
Molmo2-8B
$0.000 t/s

ai21-labs

7 models
Jamba 1.7 Large
$3.5056 t/s
Jamba 1.5 Large
$3.500 t/s
Jamba 1.6 Large
$3.5054 t/s
Jamba Reasoning 3B
$0.000 t/s
Jamba 1.7 Mini
$0.000 t/s
Jamba 1.5 Mini
$0.250 t/s
Jamba 1.6 Mini
$0.25181 t/s

arcee

1 models
Trinity Large Thinking
$0.40202 t/s

baidu

2 models
ERNIE 5.0 Thinking Preview
$0.000 t/s
ERNIE 4.5 300B A47B
$0.480 t/s

bytedance_seed

2 models
Doubao Seed Code
$0.000 t/s
Seed-OSS-36B-Instruct
$0.3034 t/s

china-mobile

2 models
JT-35B-Flash
$0.000 t/s
JT-MINI
$0.000 t/s

databricks

1 models
DBRX Instruct
$0.000 t/s

deepcogito

1 models
Cogito v2.1 (Reasoning)
$1.2594 t/s

ibm

10 models
Granite 4.1 30B
$0.000 t/s
Granite 4.1 8B
$0.06131 t/s
Granite 4.0 H Small
$0.11397 t/s
Granite 4.1 3B
$0.000 t/s
Granite 4.0 H 1B
$0.000 t/s
Granite 4.0 Micro
$0.000 t/s
Granite 4.0 1B
$0.000 t/s
Granite 3.3 8B (Non-reasoning)
$0.09354 t/s
Granite 4.0 350M
$0.000 t/s
Granite 4.0 H 350M
$0.000 t/s

inception

1 models
Mercury 2
$0.381194 t/s

inclusionai

8 models
Ring-2.6-1T
$0.85124 t/s
Ling-2.6-1T
$0.850 t/s
Ring-1T
$0.000 t/s
Ling 2.6 Flash
$0.15182 t/s
Ling-1T
$0.000 t/s
Ling-flash-2.0
$0.2556 t/s
Ring-flash-2.0
$0.250 t/s
Ling-mini-2.0
$0.000 t/s

korea-telecom

2 models
Mi:dm K 2.5 Pro
$0.000 t/s
Mi:dm K 2.5 Pro Preview
$0.000 t/s

kwaikat

2 models
KAT Coder Pro V2
$0.53103 t/s
KAT-Coder-Pro V1
$0.53101 t/s

lg

7 models
K-EXAONE (Reasoning)
$0.000 t/s
EXAONE 4.5 33B
$0.000 t/s
K-EXAONE (Non-reasoning)
$0.000 t/s
EXAONE 4.0 32B (Reasoning)
$0.000 t/s
EXAONE 4.0 32B (Non-reasoning)
$0.000 t/s
Exaone 4.0 1.2B (Reasoning)
$0.000 t/s
Exaone 4.0 1.2B (Non-reasoning)
$0.000 t/s

liquidai

9 models
LFM2.5-8B-A1B
$0.00342 t/s
LFM2 24B A2B
$0.05126 t/s
LFM 40B
$0.000 t/s
LFM2.5-1.2B-Instruct
$0.000 t/s
LFM2 2.6B
$0.000 t/s
LFM2.5-1.2B-Thinking
$0.000 t/s
LFM2 8B A1B
$0.000 t/s
LFM2 1.2B
$0.000 t/s
LFM2.5-VL-1.6B
$0.00455 t/s

longcat

1 models
LongCat Flash Lite
$0.000 t/s

mbzuai

4 models
K2 Think V2
$0.000 t/s
K2-V2 (high)
$0.000 t/s
K2-V2 (medium)
$0.000 t/s
K2-V2 (low)
$0.000 t/s

minimax

7 models
MiniMax-M3
$0.53104 t/s
MiniMax-M2.7
$0.5348 t/s
MiniMax-M2.5
$0.5374 t/s
MiniMax-M2.1
$0.5372 t/s
MiniMax-M2
$0.5384 t/s
MiniMax M1 80k
$0.960 t/s
MiniMax M1 40k
$0.000 t/s

motif-technologies

1 models
Motif-2-12.7B-Reasoning
$0.000 t/s

multiversecomputing

1 models
HyperNova 60B 2605
$0.07351 t/s

nanbeige

1 models
Nanbeige4.1-3B
$0.000 t/s

nex

1 models
Nex-N2-Pro
$1.00113 t/s

nous-research

7 models
Hermes 4 - Llama-3.1 70B (Reasoning)
$0.2085 t/s
Hermes 4 - Llama-3.1 405B (Reasoning)
$1.5038 t/s
Hermes 4 - Llama-3.1 405B (Non-reasoning)
$1.5039 t/s
Hermes 4 - Llama-3.1 70B (Non-reasoning)
$0.2094 t/s
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
$0.000 t/s
Hermes 3 - Llama-3.1 70B
$0.7034 t/s
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)
$0.000 t/s

openbmb

3 models
MiniCPM5-1B (Reasoning)
$0.000 t/s
MiniCPM5-1B (Non-reasoning)
$0.000 t/s
MiniCPM-V 4.6 1.3B
$0.000 t/s

openchat

1 models
OpenChat 3.5 (1210)
$0.000 t/s

perplexity

5 models
Sonar Reasoning Pro
$0.000 t/s
Sonar Reasoning
$0.000 t/s
Sonar
$0.000 t/s
Sonar Pro
$0.000 t/s
R1 1776
$0.000 t/s

prime-intellect

1 models
INTELLECT-3
$0.000 t/s

reka-ai

2 models
Reka Flash (Sep '24)
$0.3586 t/s
Reka Flash 3
$0.3594 t/s

sarvam

3 models
Sarvam 105B (high)
$0.07149 t/s
Sarvam 30B (high)
$0.05236 t/s
Sarvam M (Reasoning)
$0.000 t/s

servicenow

2 models
Apriel-v1.5-15B-Thinker
$0.000 t/s
Apriel-v1.6-15B-Thinker
$0.000 t/s

snowflake

1 models
Arctic Instruct
$0.000 t/s

stepfun

4 models
Step 3.7 Flash
$0.44393 t/s
Step 3.5 Flash 2603
$0.15177 t/s
Step 3.5 Flash
$0.15178 t/s
Step3 VL 10B
$0.000 t/s

swiss-ai-initiative

2 models
Apertus 70B Instruct
$1.340 t/s
Apertus 8B Instruct
$0.130 t/s

tencent

2 models
Hy3-preview (Reasoning)
$0.20207 t/s
Hy3-preview (Non-reasoning)
$0.20189 t/s

tii-uae

1 models
Falcon-H1R-7B
$0.000 t/s

trillionlabs

2 models
Tri-21B-think Preview
$0.000 t/s
Tri-21B-Think
$0.000 t/s

upstage

7 models
Solar Open 100B (Reasoning)
$0.000 t/s
Solar Pro 3
$0.000 t/s
Solar Pro 2 (Preview) (Reasoning)
$0.000 t/s
Solar Pro 2 (Preview) (Non-reasoning)
$0.000 t/s
Solar Pro 2 (Reasoning)
$0.000 t/s
Solar Pro 2 (Non-reasoning)
$0.000 t/s
Solar Mini
$0.1576 t/s

xiaomi

9 models
MiMo-V2.5-Pro
$0.5446 t/s
MiMo-V2-Pro
$1.500 t/s
MiMo-V2.5
$0.1787 t/s
MiMo-V2-Omni-0327
$0.800 t/s
MiMo-V2-Omni
$0.000 t/s
MiMo-V2-Flash (Feb 2026)
$0.150 t/s
MiMo-V2-Flash (Reasoning)
$0.150 t/s
MiMo-V2.5-Pro (Non-reasoning)
$0.9352 t/s
MiMo-V2-Flash (Non-reasoning)
$0.150 t/s

zai

19 models
GLM-5.2 (max)
$2.15189 t/s
GLM-5.1 (Reasoning)
$2.1572 t/s
GLM-5 (Reasoning)
$1.5546 t/s
GLM-5-Turbo
$0.000 t/s
GLM-5.1 (Non-reasoning)
$2.1454 t/s
GLM 5V Turbo (Reasoning)
$0.000 t/s
GLM-4.7 (Reasoning)
$1.00103 t/s
GLM-5 (Non-reasoning)
$1.5554 t/s
GLM-4.6 (Reasoning)
$0.9641 t/s
GLM-4.7 (Non-reasoning)
$1.00104 t/s
GLM-4.6 (Non-reasoning)
$0.9840 t/s
GLM-4.7-Flash (Reasoning)
$0.1599 t/s
GLM-4.5 (Reasoning)
$1.000 t/s
GLM-4.6V (Reasoning)
$0.4546 t/s
GLM-4.5-Air
$0.3764 t/s
GLM-4.7-Flash (Non-reasoning)
$0.15130 t/s
GLM-4.6V (Non-reasoning)
$0.4545 t/s
GLM-4.5V (Reasoning)
$0.9047 t/s
GLM-4.5V (Non-reasoning)
$0.9046 t/s

Tools

Rankings

Guides

Comparisons