All AI Models

603 models across 57 providers. Click any model for detailed pricing, benchmarks, and speed data.

OpenAI

81 models

GPT-5.6 Sol (max)

GPT-5.6 Terra (xhigh)

GPT-5.6 Terra (medium)

$4.5098 t/s

GPT-5.3 Codex (xhigh)

GPT-5.6 Sol (Non-reasoning)

$11.2567 t/s

GPT-5.6 Terra (low)

$4.5094 t/s

GPT-5.2 Codex (xhigh)

GPT-5.6 Luna (medium)

GPT-5.5 (Non-reasoning)

GPT-5.6 Terra (Non-reasoning)

$4.5099 t/s

GPT-5.5 Instant (May 2026)

GPT-5.1 Codex mini (high)

$0.69

$3.50112 t/s

GPT-5.4 nano (medium)

$0.46176 t/s

GPT-5.4 mini (medium)

$1.69160 t/s

GPT-5.5 Instant (June 2026)

$11.25117 t/s

GPT-5.4 (Non-reasoning)

$5.6390 t/s

GPT-5.6 Luna (Non-reasoning)

$0.45145 t/s

GPT-5.2 (Non-reasoning)

GPT-5.1 (Non-reasoning)

GPT-5.4 nano (Non-Reasoning)

GPT-5.4 mini (Non-Reasoning)

GPT-4o (March 2025, chatgpt-4o-latest)

Anthropic

39 models

Claude Opus 5 (Adaptive Reasoning, Max Effort)

$10.0053 t/s

Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)

$10.0054 t/s

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

$20.0067 t/s

Claude Opus 5 (Adaptive Reasoning, High Effort)

$10.0052 t/s

Claude Opus 5 (Adaptive Reasoning, Medium Effort)

$10.0053 t/s

Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

$10.0056 t/s

Claude Sonnet 5 (Adaptive Reasoning, Max Effort)

$4.0076 t/s

Claude Opus 4.7 (Adaptive Reasoning, Max Effort)

$10.0048 t/s

Claude Opus 5 (Adaptive Reasoning, Low Effort)

$10.0049 t/s

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)

$6.0055 t/s

Claude Opus 4.6 (Adaptive Reasoning, Max Effort)

$10.0040 t/s

Claude Opus 4.7 (Non-reasoning, High Effort)

$10.0044 t/s

Claude Sonnet 5 (Non-reasoning, High Effort)

$4.0058 t/s

Claude Opus 4.5 (Reasoning)

$10.0046 t/s

Claude Opus 4.6 (Non-reasoning, High Effort)

$10.0036 t/s

Claude 4.5 Sonnet (Reasoning)

$6.0041 t/s

Claude Sonnet 4.6 (Non-reasoning, High Effort)

$6.0043 t/s

Claude Opus 4.5 (Non-reasoning)

$10.0045 t/s

Claude Sonnet 4.6 (Non-reasoning, Low Effort)

$6.0044 t/s

Claude 4.1 Opus (Reasoning)

$30.00

Claude 4 Opus (Reasoning)

$30.00

Claude 4.5 Sonnet (Non-reasoning)

$6.0039 t/s

Claude 4.5 Haiku (Reasoning)

$2.0089 t/s

Claude 4 Sonnet (Reasoning)

$6.00

Claude 4.1 Opus (Non-reasoning)

$30.00

Claude 3.7 Sonnet (Reasoning)

Claude 4 Opus (Non-reasoning)

$30.00

Claude 4 Sonnet (Non-reasoning)

$6.00

Claude 4.5 Haiku (Non-reasoning)

$2.0090 t/s

Claude 3.7 Sonnet (Non-reasoning)

Claude 3.5 Sonnet (Oct '24)

$6.00

Claude 3.5 Sonnet (June '24)

Google

61 models

Gemini 3.7 Flash (high)

$1.50323 t/s

Gemini 3.7 Flash (medium)

$1.50317 t/s

Gemini 3.5 Flash (high)

$3.38171 t/s

Gemini 3.6 Flash (high)

$1.50222 t/s

Gemini 3.7 Flash (low)

$1.50303 t/s

Gemini 3.1 Pro Preview

$4.50108 t/s

Gemini 3.5 Flash (medium)

$3.38180 t/s

Gemini 3 Pro Preview (high)

$4.50

Gemini 3 Flash Preview (Reasoning)

$1.13189 t/s

Gemini 3.5 Flash-Lite

$0.85332 t/s

Gemini 3.5 Flash (minimal)

$3.38154 t/s

Gemini 3 Pro Preview (low)

$4.50

Gemma 4 31B (Reasoning)

$0.0036 t/s

Gemini 3 Flash Preview (Non-reasoning)

$1.13195 t/s

Gemma 4 26B A4B (Reasoning)

$0.18

Gemini 2.5 Pro

$3.44133 t/s

Gemini 3.1 Flash-Lite

$0.56346 t/s

Gemini 2.5 Flash Preview (Sep '25) (Reasoning)

Gemini 2.5 Pro Preview (Mar' 25)

Gemini 2.5 Pro Preview (May' 25)

$3.44

Gemma 4 31B (Non-reasoning)

$0.2182 t/s

Gemma 4 12B (Reasoning)

$0.15112 t/s

Gemma 4 26B A4B (Non-reasoning)

$0.2075 t/s

Gemini 2.5 Flash (Reasoning)

$0.85225 t/s

Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)

Gemini 2.5 Flash Preview (Reasoning)

Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

$0.17

Gemini 2.5 Flash (Non-reasoning)

$0.85225 t/s

DiffusionGemma 26B A4B

Gemini 2.0 Flash Thinking Experimental (Jan '25)

Gemma 4 12B (Non-reasoning)

$0.15114 t/s

Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

$0.17

Gemini 2.0 Flash (Feb '25)

Gemma 4 E4B (Reasoning)

$0.0454 t/s

Gemini 2.0 Pro Experimental (Feb '25)

Gemini 2.5 Flash Preview (Non-reasoning)

Gemini 2.5 Flash-Lite (Reasoning)

$0.17312 t/s

Gemini 2.0 Flash (experimental)

$0.00

Gemini 1.5 Pro (Sep '24)

Gemma 4 E2B (Reasoning)

Gemma 4 E4B (Non-reasoning)

$0.0456 t/s

Gemini 2.0 Flash-Lite (Feb '25)

Gemini 2.0 Flash-Lite (Preview)

Gemini 1.5 Flash (Sep '24)

Gemma 3 27B Instruct

$0.00

Gemini 2.5 Flash-Lite (Non-reasoning)

$0.17232 t/s

Gemini 2.0 Flash Thinking Experimental (Dec '24)

Gemma 4 E2B (Non-reasoning)

Gemini 1.5 Pro (May '24)

Gemma 3 12B Instruct

$0.00

Gemini 1.5 Flash-8B

Gemini 1.5 Flash (May '24)

Gemini 1.0 Ultra

Gemma 3n E4B Instruct Preview (May '25)

Gemma 3n E4B Instruct

$0.0755 t/s

Gemma 3n E2B Instruct

$0.00

Gemma 3 1B Instruct

$0.00

DeepSeek

34 models

DeepSeek V4 Pro 0813 (Reasoning, Max Effort)

$1.9874 t/s

DeepSeek V4 Flash 0731 (Reasoning, Max Effort)

$0.66133 t/s

DeepSeek V4 Pro (Reasoning, Max Effort)

$0.5474 t/s

DeepSeek V4 Pro (Reasoning, High Effort)

$0.5476 t/s

DeepSeek V4 Flash (Reasoning, Max Effort)

$0.17

DeepSeek V4 Flash (Reasoning, High Effort)

$0.17

DeepSeek V3.2 (Reasoning)

$0.32

DeepSeek V4 Pro (Non-reasoning)

$0.5473 t/s

DeepSeek V3.1 Terminus (Reasoning)

$1.92

DeepSeek V4 Flash (Non-reasoning)

$0.12

DeepSeek V3.2 Exp (Reasoning)

$0.32

DeepSeek V3.2 (Non-reasoning)

$0.32

DeepSeek V3.2 Speciale

DeepSeek V3.2 Exp (Non-reasoning)

$0.32

DeepSeek V3.1 Terminus (Non-reasoning)

$0.45

DeepSeek V3.1 (Non-reasoning)

$0.84

DeepSeek V3.1 (Non-reasoning)

$0.84

DeepSeek V3.1 (Reasoning)

$0.86

DeepSeek R1 0528 (May '25)

$1.76

DeepSeek R1 (Jan '25)

$2.50

DeepSeek V3 0324

$0.48

DeepSeek V3 (Dec '24)

$0.49

DeepSeek R1 Distill Qwen 32B

DeepSeek R1 0528 Qwen3 8B

DeepSeek R1 Distill Llama 70B

$0.8025 t/s

DeepSeek R1 Distill Qwen 14B

DeepSeek-V2.5 (Dec '24)

DeepSeek-V2.5

DeepSeek R1 Distill Llama 8B

DeepSeek-Coder-V2

DeepSeek-V2-Chat

DeepSeek R1 Distill Qwen 1.5B

DeepSeek Coder V2 Lite Instruct

DeepSeek LLM 67B Chat (V1)

Mistral

32 models

Alibaba / Qwen

88 models

Qwen3.6 27B (Reasoning)

$1.3558 t/s

Qwen3.5 27B (Reasoning)

$0.8277 t/s

Qwen3.5 397B A17B (Reasoning)

$1.3588 t/s

Qwen3.5 122B A10B (Reasoning)

$1.10130 t/s

Qwen3.5 397B A17B (Non-reasoning)

$1.3583 t/s

Qwen3 Max Thinking

Qwen3.6 35B A3B (Reasoning)

$0.85119 t/s

Qwen3.5 Omni Plus

$1.5049 t/s

Qwen3.6 27B (Non-reasoning)

$1.3555 t/s

Qwen3.5 27B (Non-reasoning)

$0.8282 t/s

Qwen3.5 35B A3B (Reasoning)

$0.69151 t/s

Qwen3.5 122B A10B (Non-reasoning)

$1.10143 t/s

Qwen3 Max Thinking (Preview)

$2.4056 t/s

Qwen3.6 35B A3B (Non-reasoning)

$0.85137 t/s

Qwen3 Max

$2.4058 t/s

Qwen3.5 35B A3B (Non-reasoning)

$0.69169 t/s

Qwen3.5 9B (Reasoning)

$0.1581 t/s

Qwen3 Coder Next

$0.56139 t/s

Qwen3 VL 235B A22B (Reasoning)

$1.3057 t/s

Qwen3.5 9B (Non-reasoning)

$0.1987 t/s

Qwen3.5 4B (Reasoning)

$0.0623 t/s

Qwen3 235B A22B 2507 (Reasoning)

Qwen3 235B A22B 2507 Instruct

$0.4056 t/s

Qwen3 Coder 480B A35B Instruct

$3.0066 t/s

Qwen3 VL 32B (Reasoning)

$0.2890 t/s

Qwen3 Next 80B A3B (Reasoning)

$0.41198 t/s

Qwen3.5 4B (Non-reasoning)

$0.0628 t/s

Qwen3 30B A3B 2507 (Reasoning)

$0.75145 t/s

Qwen3 VL 235B A22B Instruct

$0.7047 t/s

Qwen3 Next 80B A3B Instruct

$0.41183 t/s

Qwen3 Coder 30B A3B Instruct

$0.9091 t/s

Qwen3 235B A22B (Reasoning)

$2.6361 t/s

Qwen3 VL 30B A3B (Reasoning)

$0.75111 t/s

QwQ 32B

$0.74

Qwen3 4B 2507 (Reasoning)

Qwen3 32B (Reasoning)

$0.28101 t/s

Qwen3 VL 32B Instruct

$0.2864 t/s

Qwen3 235B A22B (Non-reasoning)

$1.2359 t/s

Qwen3 VL 8B (Reasoning)

$0.66114 t/s

Qwen3 14B (Reasoning)

$1.3159 t/s

Qwen2.5 Max

Qwen3 VL 30B A3B Instruct

$0.35109 t/s

Qwen3 VL 30B A3B Instruct

$0.35109 t/s

Qwen3 Omni 30B A3B (Reasoning)

$0.4399 t/s

Qwen2.5 Instruct 72B

$0.47

Qwen3 30B A3B (Reasoning)

$0.75103 t/s

QwQ 32B-Preview

Qwen3 30B A3B 2507 Instruct

$0.35142 t/s

Qwen3 32B (Non-reasoning)

Qwen3 VL 4B (Reasoning)

Qwen3.5 2B (Reasoning)

Qwen2.5 Instruct 32B

Qwen2.5 Coder Instruct 32B

Qwen3 4B 2507 Instruct

Qwen3 14B (Non-reasoning)

$0.6160 t/s

Qwen3 30B A3B (Non-reasoning)

$0.35107 t/s

Qwen3 4B (Non-reasoning)

Qwen2.5 Turbo

$0.09108 t/s

Qwen2 Instruct 72B

Qwen3.5 2B (Non-reasoning)

Qwen3.5 0.8B (Reasoning)

Qwen3 Omni 30B A3B Instruct

$0.4393 t/s

Qwen3 8B (Non-reasoning)

$0.3139 t/s

Qwen2.5 Coder Instruct 7B

Qwen1.5 Chat 110B

Qwen3 VL 4B Instruct

Qwen Chat 72B

Qwen3.5 0.8B (Non-reasoning)

Qwen3 1.7B (Reasoning)

Qwen Chat 14B

Qwen3 1.7B (Non-reasoning)

Qwen3 0.6B (Non-reasoning)

Qwen3 0.6B (Reasoning)

NVIDIA

19 models

Nemotron 3 Ultra 550B A55B (Reasoning)

$1.14146 t/s

Nemotron 3 Super 120B A12B (Reasoning)

$0.35144 t/s

Nemotron 3.5 Lightning

$0.11302 t/s

Nemotron Cascade 2 30B A3B

Nemotron 3 Nano Omni 30B A3B Reasoning

$0.13326 t/s

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)

$0.09261 t/s

Llama Nemotron Super 49B v1.5 (Reasoning)

$0.40106 t/s

Llama 3.3 Nemotron Super 49B v1 (Reasoning)

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

$0.9048 t/s

NVIDIA Nemotron Nano 12B v2 VL (Reasoning)

$0.30120 t/s

NVIDIA Nemotron Nano 9B V2 (Reasoning)

$0.07186 t/s

NVIDIA Nemotron 3 Nano 4B

Llama Nemotron Super 49B v1.5 (Non-reasoning)

$0.4090 t/s

Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)

Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)

Llama 3.1 Nemotron Instruct 70B

$1.20108 t/s

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

$0.09225 t/s

NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

$0.09168 t/s

NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

$0.30163 t/s

Amazon

15 models

Nova 2.0 Pro Preview (medium)

$3.44115 t/s

Nova 2.0 Omni (medium)

$0.85

Nova 2.0 Lite (high)

$0.85156 t/s

Nova 2.0 Pro Preview (low)

$3.44115 t/s

Nova 2.0 Lite (medium)

$0.85170 t/s

Nova 2.0 Lite (medium)

Nova 2.0 Pro Preview (Non-reasoning)

$3.44104 t/s

Nova Premier

$5.0033 t/s

Nova 2.0 Lite (Non-reasoning)

$0.85146 t/s

Nova 2.0 Omni (Non-reasoning)

Microsoft

4 models

Phi-3 Mini Instruct 3.8B

Phi-4 Multimodal Instruct

$0.0017 t/s

Cohere

6 models

Moonshot

11 models

Kimi K2.5 (Reasoning)

$1.2043 t/s

Kimi K2.6 (Non-reasoning)

$1.7140 t/s

Kimi K2 Thinking

$1.07121 t/s

Kimi K2.5 (Non-reasoning)

Kimi Linear 48B A3B Instruct

agnes-ai

1 models

Agnes 2.5 Pro Alpha

$0.56130 t/s

ai2

10 models

Llama 3.1 Tulu3 405B

Olmo 3.1 32B Think

$0.00

Olmo 3.1 32B Instruct

ai21-labs

7 models

ai9star

2 models

arcee-ai

1 models

Trinity Large Thinking

$0.39197 t/s

baidu

2 models

ERNIE 5.0 Thinking Preview

ERNIE 4.5 300B A47B

$0.48

bytedance_seed

2 models

Doubao Seed Code

Seed-OSS-36B-Instruct

$0.3029 t/s

celeris

1 models

Celeris-1

$0.331484 t/s

china-mobile

3 models

JT-4.1 Flash 236B A21B

JT-35B-Flash

JT-MINI

databricks

1 models

DBRX Instruct

ibm

9 models

Granite 3.3 8B (Non-reasoning)

$0.0914 t/s

Granite 4.0 350M

Granite 4.0 H 350M

inception

1 models

Mercury 2

$0.38835 t/s

inclusionai

10 models

korea-telecom

1 models

Mi:dm K 2.5 Pro

kwaikat

4 models

lg

8 models

K-EXAONE 2.0 0803

K-EXAONE (Reasoning)

EXAONE 4.5 33B

K-EXAONE (Non-reasoning)

EXAONE 4.0 32B (Reasoning)

EXAONE 4.0 32B (Non-reasoning)

Exaone 4.0 1.2B (Reasoning)

Exaone 4.0 1.2B (Non-reasoning)

liquidai

10 models

longcat

2 models

LongCat 2.0

$1.3044 t/s

LongCat Flash Lite

mbzuai

3 models

K2 Think V2

K2-V2 (medium)

K2-V2 (low)

minimax

7 models

motif-technologies

2 models

Motif 3

Motif-2-12.7B-Reasoning

multiversecomputing

1 models

HyperNova 60B 2605

nanbeige

1 models

Nanbeige4.1-3B

naver

1 models

HyperCLOVA X SEED Think (32B)

nex

1 models

Nex-N2-Pro

$1.00138 t/s

nous-research

7 models

Hermes 4 - Llama-3.1 70B (Reasoning)

$0.2078 t/s

Hermes 4 - Llama-3.1 405B (Reasoning)

$1.5031 t/s

Hermes 4 - Llama-3.1 405B (Non-reasoning)

$1.5022 t/s

Hermes 4 - Llama-3.1 70B (Non-reasoning)

$0.2056 t/s

DeepHermes 3 - Mistral 24B Preview (Non-reasoning)

Hermes 3 - Llama-3.1 70B

$0.7034 t/s

DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)

openbmb

3 models

MiniCPM5-1B (Reasoning)

MiniCPM5-1B (Non-reasoning)

MiniCPM-V 4.6 1.3B

openchat

1 models

OpenChat 3.5 (1210)

perplexity

5 models

prime-intellect

1 models

INTELLECT-3

reka-ai

2 models

sarvam

3 models

servicenow

2 models

Apriel-v1.5-15B-Thinker

$0.00

Apriel-v1.6-15B-Thinker

$0.00

sk-telecom

1 models

A.X-K2

snowflake

1 models

Arctic Instruct

stepfun

4 models

swiss-ai-initiative

2 models

tencent

3 models

Hy3

$0.2467 t/s

Hy3-preview (Reasoning)

$0.10

Hy3-preview (Non-reasoning)

$0.10

thinking-machines

2 models

tii-uae

1 models

Falcon-H1R-7B

trillionlabs

2 models

Tri-21B-think Preview

Tri-21B-Think

upstage

9 models

Solar Pro 4

$0.5347 t/s

Solar Open2 250B

Solar Open 100B (Reasoning)

Solar Pro 3

$0.26152 t/s

Solar Pro 2 (Preview) (Reasoning)

Solar Pro 2 (Preview) (Non-reasoning)

Solar Pro 2 (Reasoning)

Solar Pro 2 (Non-reasoning)

Solar Mini

$0.15

xiaomi

9 models

MiMo-V2-Flash (Feb 2026)

MiMo-V2-Flash (Reasoning)

$0.15

MiMo-V2.5-Pro (Non-reasoning)

$0.5456 t/s

MiMo-V2-Flash (Non-reasoning)

All AI Models

OpenAI

Anthropic

Google

DeepSeek

Meta

Mistral

xAI

Alibaba / Qwen

NVIDIA

Amazon

Microsoft

Cohere

Moonshot

agnes-ai

ai2

ai21-labs

ai9star

arcee-ai

baidu

bytedance_seed

celeris

china-mobile

databricks

ibm

inception

inclusionai

korea-telecom

kwaikat

lg

liquidai

longcat

mbzuai

minimax

motif-technologies

multiversecomputing

nanbeige

naver

nex

nous-research

openbmb

openchat

perplexity

prime-intellect

reka-ai

sarvam

servicenow

sk-telecom

snowflake

stepfun

swiss-ai-initiative

tencent

thinking-machines

tii-uae

trillionlabs

upstage

xiaomi

zai

Tools

Rankings

Guides

Comparisons