Directory
All models in a plain list
Every model we serve, newest first, at the price you are billed per million tokens.
334 models
- Ling 3.2 Flash (free)
inclusionAI · 1M context · Free in · Free out
- Gemini 4 HydrogenAlso:batchlatest
Google · 1M context · $1.65 in · $8.25 out
- ERNIE-5.5-Flash-Preview (free)
Baidu · 1M context · Free in · Free out
- ERNIE-Light-DT-1.0
Baidu · 1M context · $1.243 in · $4.334 out
- Gemini 4 CarbonAlso:batchlatest
Google · 1M context · $2.20 in · $11.00 out
- Nex-N2.6
Nex AGI · 262k context · $0.132 in · $0.44 out
- Inkling 2 SmallAlso:free
Thinking Machines · 1M context · $0.33 in · $1.10 out
- Claude Fable 5.2Also:batchlatest
Anthropic · 1M context · $8.80 in · $44.00 out
- Muse Ember
Meta · 1M context · $0.11 in · $0.55 out
- LFM3-1.7BAlso:free
LiquidAI · 262k context · $0.088 in · $0.22 out
- Gemini Omni 1.2 Flash
Google · 131k context · $1.65 in · $9.90 out
- Mi:dm K 3.0 Pro
KT · 261k context · $0.22 in · $0.88 out
- Gemini Omni 1.1 Flash
Google · 131k context · $1.65 in · $9.90 out
- Ripple 65B Preview
Ricursive · 1M context · $0.11 in · $0.33 out
- Hy4
Tencent · 1M context · $0.4587 in · $1.37555 out
- Motif 3
Motif Technologies · 262k context · $0.33 in · $1.32 out
- GLM 5.3 FlashX Legal
Z.ai · 1M context · $0.407 in · $1.375 out
- Particle-1Also:free
Particle AI · 1M context · $0.066 in · $0.55 out
- GPT-6.1 Terra ProAlso:batch
OpenAI · 1M context · $1.10 in · $5.50 out
- GPT-6.1 TerraAlso:batchlatest
OpenAI · 1M context · $1.10 in · $5.50 out
- Kimi K3.1 ProAlso:batch
Moonshot · 1M context · $0.26433 in · $9.24253 out
- Flint (free)
Recursive · 262k context · Free in · Free out
- MiniMax M3.1 Flash
MiniMax · 1M context · $0.165 in · $0.66 out
- Glimpse
Elorian · 262k context · $0.66 in · $3.30 out
- Beam 1.0 501B A23B
Reflection · 1M context · $0.33 in · $1.10 out
- Ternary Bonsai 2 9B
PrismML · 262k context · $0.088 in · $0.143 out
- Moondream 3 Preview
Moondream · 32k context · $0.33 in · $2.75 out
- Moondream 3.1
Moondream · 32k context · $0.33 in · $2.75 out
- Muse Spark Open
Meta · 1M context · $1.375 in · $4.675 out
- Nemotron 3.5 Super VLAlso:free
NVIDIA · 1M context · $0.165 in · $0.55 out
- Pareto 26.10Also:latest
Unbiased · 1M context · $0.88 in · $3.52 out
- Pareto 26.9
Unbiased · 262k context · $2.75 in · $8.25 out
- LFM2.5-24B-A2B
LiquidAI · 128k context · $0.055 in · $0.77 out
- Gemini 4 ArgonAlso:batch
Google · 1M context · $2.20 in · $11.00 out
- Summarize
ScaleDown · 1M context · $0.044 in · Free out
- Extract
ScaleDown · 1M context · $0.044 in · Free out
- Muse Wonder
Meta · 1M context · $4.40 in · $22.00 out
- Step 5 Preview
StepFun · 1M context · $1.10 in · $2.97 out
- Claude Haiku 5.5Also:batchlatest
Anthropic · 1M context · $0.11 in · $0.55 out
- Nano Banana 2.1
Google · 65k context · $1.65 in · $8.25 out
- Mistral Large 4
Mistral · 1M context · $0.77 in · $2.31 out
- Ling 3.1 Flash
inclusionAI · 1M context · $0.0495 in · $0.1485 out
- Pareto 26.10 Preview
Unbiased · 1M context · $0.88 in · $3.52 out
- GPT-6.1 Sol ProAlso:batch
OpenAI · 1M context · $2.20 in · $11.00 out
- GPT-6.1 SolAlso:batchlatest
OpenAI · 1M context · $2.20 in · $11.00 out
- Claude Sonnet 5.5Also:batchlatest
Anthropic · 1M context · $2.20 in · $11.00 out
- Jev Router
TypeSafe · 1M context · No published price
- Perceptron Mk1.5
Perceptron · 36k context · $0.165 in · $1.65 out
- Ember-1
Fireworks · 1M context · $3.30 in · $16.50 out
- GLM 5.3 Prime
Z.ai · 1M context · $3.08 in · $9.68 out
- Qwen3.8 Max Prime
Qwen · 1M context · $4.40 in · $13.20 out
- Aion 3.5 Mini
AionLabs · 262k context · $0.77 in · $1.54 out
- Aion 3.5
AionLabs · 262k context · $3.30 in · $6.60 out
- Solar Mini 4
Upstage · 524k context · $0.055 in · $0.22 out
- Command A+
Cohere · 192k context · $0.33 in · $1.65 out
- GPT-6 Luna ProAlso:batch
OpenAI · 1M context · $0.11 in · $0.55 out
- GPT-6 LunaAlso:batchlatest
OpenAI · 1M context · $0.11 in · $0.55 out
- GPT-6 Sol ProAlso:batch
OpenAI · 1M context · $2.20 in · $11.00 out
- GPT-6 SolAlso:batch
OpenAI · 1M context · $2.20 in · $11.00 out
- Claude Opus 5.5Also:batchlatest
Anthropic · 1M context · $4.40 in · $22.00 out
- Switchyard
NVIDIA · 1M context · No published price
- MiMo-V2.6-Pro-UltraSpeed
Xiaomi · 1M context · $4.785 in · $9.57 out
- MiMo-V2.6-Flash
Xiaomi · 1M context · $0.154 in · $0.308 out
- MiMo-V2.6-Pro
Xiaomi · 1M context · $0.4785 in · $0.957 out
- Grok 4.7Also:batchlatest
xAI · 500k context · $2.20 in · $6.60 out
- Qwen3.8 Omni Flash
Qwen · 1M context · $0.165 in · $0.517 out
- Ternary Bonsai 2 27B
PrismML · 262k context · $0.0825 in · $0.55 out
- GLM 5.3 FlashX
Z.ai · 1M context · $0.407 in · $1.375 out
- Schematron V2 Turbo
Inference.net · 128k context · $0.033 in · $0.165 out
- Schematron V2 Small
Inference.net · 128k context · $0.055 in · $0.253 out
- Fugu Ultra v2
Sakana · 1M context · $5.50 in · $33.00 out
- Fugu Max
Sakana · 1M context · $2.20 in · $6.60 out
- Ling 3.0 Flash VL
inclusionAI · 131k context · $0.066 in · $0.198 out
- DeepSeek V4.1 FlashAlso:DeepSeek V4.1 Flash 1017batchlatestbatch
DeepSeek · 1M context · $0.05577 in · $0.22308 out
- Nex-N2.5-Mini
Nex AGI · 262k context · $0.0275 in · $0.11 out
- Nex-N2.5-Pro
Nex AGI · 262k context · $0.0825 in · $0.275 out
- GPT-6 AstraAlso:latestbatch
OpenAI · 1M context · $11.00 in · $55.00 out
- GPT-6 Astra ProAlso:batch
OpenAI · 1M context · $11.00 in · $55.00 out
- Qwen3.8 Max (0902)Also:batch
Qwen · 1M context · $2.20 in · $6.60 out
- Muse Spark 1.3
Meta · 1M context · $1.375 in · $4.675 out
- Gemini 3.8 FlashAlso:batch
Google · 1M context · $0.825 in · $4.125 out
- Claude Fable 5.1Also:batch
Anthropic · 1M context · $11.00 in · $55.00 out
- Granite 4.2 8B
IBM · 131k context · $0.066 in · $0.165 out
- Hy4 preview
Tencent · 1M context · $0.9174 in · $2.7511 out
- Qwen3.8 Flash
Qwen · 1M context · $0.165 in · $0.517 out
- GLM 5.3 FlashAlso:latestbatch
Z.ai · 1M context · $0.04389 in · $0.08624 out
- DeepSeek V4 Flash Vision Exp
DeepSeek · 1M context · $0.484 in · $1.452 out
- Hy-MT2-1.8B
Tencent · 8k context · $0.0484 in · $0.1947 out
- Hy-MT2-30B-A3B
Tencent · 8k context · $0.0814 in · $0.3245 out
- Hy-MT2-7B
Tencent · 8k context · $0.0814 in · $0.3245 out
- GLM 5.3Also:latestbatch
Z.ai · 1M context · $0.0924 in · $3.96 out
- Qwen3.8 27BAlso:batch
Qwen · 1M context · $0.165 in · $2.0625 out
- Dots3-Note Preview (free)
Dots Studio · 512k context · Free in · Free out
- Gemini 3.7 FlashAlso:batch
Google · 1M context · $0.825 in · $4.125 out
- Seed 2.1 Turbo
ByteDance · 262k context · $0.55 in · $2.75 out
- Qwen3.8 2.4T A95B
Qwen · 1M context · $2.20 in · $6.60 out
- Grok 4.6Also:batch
xAI · 500k context · $2.20 in · $6.60 out
- Nemotron 3.5 LightningAlso:free
NVIDIA · 262k context · $0.077 in · $0.22 out
- Solar Pro 4
Upstage · 524k context · $0.165 in · $0.66 out
- Muse Glimmer 30BAlso:batch
Meta · 131k context · $0.33 in · $1.32 out
- Ling 3.0 Tiny
inclusionAI · 262k context · $0.0165 in · $0.0495 out
- Muse Spark 1.2
Meta · 1M context · $1.375 in · $4.675 out
- Inkling SmallAlso:batch
Thinking Machines · 524k context · $0.495 in · $1.32 out
- Qwen3.7 Flash
Qwen · 1M context · $0.033 in · $0.143 out
- Claude Opus 5Also:batch
Anthropic · 1M context · $5.50 in · $27.50 out
- Ling 3.0 Flash
inclusionAI · 262k context · $0.0231 in · $0.0693 out
- Gemini 3.6 FlashAlso:batch
Google · 1M context · $0.825 in · $4.125 out
- Gemini 3.5 Flash LiteAlso:batch
Google · 1M context · $0.33 in · $2.75 out
- LongCat 2.0
Meituan · 1M context · $0.33 in · $1.32 out
- Inkling
Thinking Machines · 524k context · $1.10 in · $4.455 out
- Kimi K3Also:batchlatest
Moonshot · 1M context · $0.2112 in · $17.60 out
- Muse Spark 1.1
Meta · 1M context · $1.375 in · $4.675 out
- GPT-5.6 Luna ProAlso:batch
OpenAI · 1M context · $0.22 in · $1.32 out
- GPT-5.6 Terra ProAlso:batch
OpenAI · 1M context · $2.20 in · $13.20 out
- GPT-5.6 Sol ProAlso:batch
OpenAI · 1M context · $4.40 in · $22.00 out
- Grok 4.5
xAI · 500k context · $2.20 in · $6.60 out
- Aion-3.0-Mini
AionLabs · 131k context · $0.77 in · $1.54 out
- Aion-3.0
AionLabs · 131k context · $3.30 in · $6.60 out
- Hy3
Tencent · 262k context · $0.1452 in · $0.5808 out
- Claude Sonnet 5
Anthropic · 1M context · $2.20 in · $11.00 out
- Nano Banana 2 Lite
Google · 65k context · $0.275 in · $1.65 out
- Fugu Ultra
Sakana · 1M context · $5.50 in · $33.00 out
- Nano Banana 2
Google · 131k context · $0.55 in · $3.30 out
- Nano Banana Pro
Google · 131k context · $2.20 in · $13.20 out
- North Mini Code (free)
Cohere · 256k context · Free in · Free out
- GLM 5.2
Z.ai · 1M context · $0.0077 in · $7.48 out
- Kimi K2.7 Code
Moonshot · 262k context · $0.66 in · $3.85 out
- Claude Fable 5
Anthropic · 1M context · $11.00 in · $55.00 out
- Nemotron 3.5 Content Safety
NVIDIA · 131k context · $0.22 in · $0.22 out
- Nemotron 3 UltraAlso:free
NVIDIA · 262k context · $0.66 in · $2.64 out
- Qwen3.7 PlusAlso:batch
Qwen · 1M context · $0.352 in · $1.408 out
- MiniMax M3Also:batch
MiniMax · 1M context · $0.33 in · $1.32 out
- Step 3.7 Flash
StepFun · 262k context · $0.22 in · $1.265 out
- Claude Opus 4.8
Anthropic · 1M context · $5.50 in · $27.50 out
- Qwen3.7 Max
Qwen · 1M context · $1.6225 in · $4.8675 out
- Grok Build 0.1
xAI · 256k context · $1.10 in · $2.20 out
- Gemini 3.5 FlashAlso:batch
Google · 1M context · $1.65 in · $9.90 out
- Perceptron Mk1
Perceptron · 32k context · $0.165 in · $1.65 out
- Gemini 3.1 Flash LiteAlso:batch
Google · 1M context · $0.275 in · $1.65 out
- GPT Chat Latest
OpenAI · 400k context · $5.50 in · $33.00 out
- Grok 4.3Also:batch
xAI · 1M context · $1.375 in · $2.75 out
- Mistral Medium 3.5Also:batch
Mistral · 262k context · $1.65 in · $8.25 out
- Nemotron 3 Nano Omni (free)
NVIDIA · 256k context · Free in · Free out
- Qwen3.5 Plus 2026-04-20
Qwen · 1M context · $0.33 in · $1.98 out
- Qwen3.6 Flash
Qwen · 1M context · $0.20625 in · $1.2375 out
- Qwen3.6 35B A3B
Qwen · 262k context · $0.11 in · $0.99 out
- Qwen3.6 27B
Qwen · 262k context · $0.352 in · $3.52 out
- DeepSeek V4 Pro 0423Also:latestDeepSeek V4 Pro 0813
DeepSeek · 1M context · $0.99 in · $1.65 out
- DeepSeek V4 Flash 0423Also:latestDeepSeek V4 Flash 0731batch
DeepSeek · 1M context · $0.099 in · $0.198 out
- Hy3 preview
Tencent · 262k context · $0.198 in · $0.66 out
- MiMo-V2.5-Pro
Xiaomi · 1M context · $0.4785 in · $0.957 out
- MiMo-V2.5
Xiaomi · 1M context · $0.44 in · $2.20 out
- GPT-5.4 Image 2
OpenAI · 272k context · $8.80 in · $16.50 out
- Kimi K2.6
Moonshot · 262k context · $0.715 in · $3.751 out
- Claude Opus 4.7
Anthropic · 1M context · $5.50 in · $27.50 out
- GLM 5.1
Z.ai · 204k context · $1.54 in · $4.84 out
- Gemma 4 26B A4BAlso:free
Google · 262k context · $0.07425 in · $0.2475 out
- Gemma 4 31BAlso:free
Google · 262k context · $0.22 in · $0.44 out
- Qwen3.6 Plus
Qwen · 1M context · $0.3575 in · $2.145 out
- GLM 5V Turbo
Z.ai · 202k context · $1.32 in · $4.40 out
- Grok 4.20 Multi-Agent
xAI · 2M context · $1.375 in · $2.75 out
- Grok 4.20
xAI · 2M context · $1.375 in · $2.75 out
- Lyria 3 Pro Preview
Google · 1M context · Free in · Free out
- Lyria 3 Clip Preview
Google · 1M context · Free in · Free out
- Reka Edge
Reka · 16k context · $0.11 in · $0.11 out
- MiniMax M2.7
MiniMax · 196k context · $0.231 in · $0.924 out
- Mistral Small 4
Mistral · 262k context · $0.165 in · $0.66 out
- GLM 5 Turbo
Z.ai · 202k context · $1.32 in · $4.40 out
- Nemotron 3 Super
NVIDIA · 262k context · $0.0825 in · $0.44 out
- Seed-2.0-Lite
ByteDance · 262k context · $0.275 in · $2.20 out
- Qwen3.5-9B
Qwen · 262k context · $0.0495 in · $0.0737 out
- Gemini 3.1 Flash Lite Preview
Google · 1M context · $0.275 in · $1.65 out
- Seed-2.0-Mini
ByteDance · 262k context · $0.11 in · $0.44 out
- Nano Banana 2 Preview
Google · 65k context · $0.55 in · $3.30 out
- Qwen3.5-35B-A3B
Qwen · 262k context · $0.154 in · $1.10 out
- Qwen3.5-27B
Qwen · 262k context · $0.286 in · $2.86 out
- Qwen3.5-122B-A10B
Qwen · 262k context · $0.286 in · $2.288 out
- Qwen3.5-Flash
Qwen · 1M context · $0.0715 in · $0.286 out
- Gemini 3.1 Pro Preview Custom Tools
Google · 1M context · $2.20 in · $13.20 out
- Aion-2.0
AionLabs · 131k context · $0.88 in · $1.76 out
- Gemini 3.1 Pro PreviewAlso:batch
Google · 1M context · $2.20 in · $13.20 out
- Claude Sonnet 4.6
Anthropic · 1M context · $3.30 in · $16.50 out
- Qwen3.5 Plus 2026-02-15
Qwen · 1M context · $0.286 in · $1.716 out
- Qwen3.5 397B A17B
Qwen · 262k context · $0.66 in · $3.96 out
- MiniMax M2.5
MiniMax · 198k context · $0.297 in · $1.045 out
- GLM 5
Z.ai · 204k context · $1.10 in · $3.52 out
- Claude Opus 4.6
Anthropic · 1M context · $5.50 in · $27.50 out
- Qwen3 Coder Next
Qwen · 262k context · $0.132 in · $0.88 out
- Kimi K2.5
Moonshot · 262k context · $0.55 in · $2.75 out
- Palmyra X5
Writer · 1M context · $0.66 in · $6.60 out
- GPT Audio
OpenAI · 128k context · $2.75 in · $11.00 out
- GPT Audio Mini
OpenAI · 128k context · $0.66 in · $2.64 out
- GLM 4.7 Flash
Z.ai · 200k context · $0.06655 in · $0.44 out
- GPT-5.2-Codex
OpenAI · 400k context · $1.925 in · $15.40 out
- GLM 4.7
Z.ai · 204k context · $0.44 in · $1.925 out
- Gemini 3 Flash PreviewAlso:batch
Google · 1M context · $0.55 in · $3.30 out
- Nemotron 3 Nano 30B A3B
NVIDIA · 262k context · $0.066 in · $0.264 out
- Devstral 2 2512
Mistral · 262k context · $0.44 in · $2.20 out
- Relace Search
Relace · 256k context · $1.10 in · $3.30 out
- GLM 4.6V
Z.ai · 131k context · $0.33 in · $0.99 out
- GPT-5.1-Codex-Max
OpenAI · 400k context · $1.375 in · $11.00 out
- Nova 2 Lite
Amazon · 1M context · $0.33 in · $2.75 out
- Ministral 3 14B 2512
Mistral · 262k context · $0.22 in · $0.22 out
- Ministral 3 8B 2512
Mistral · 262k context · $0.165 in · $0.165 out
- Ministral 3 3B 2512
Mistral · 131k context · $0.11 in · $0.11 out
- DeepSeek V3.2
DeepSeek · 163k context · $0.286 in · $0.418 out
- Claude Opus 4.5
Anthropic · 200k context · $5.50 in · $27.50 out
- Nano Banana Pro Preview
Google · 65k context · $2.20 in · $13.20 out
- GPT-5.1-Codex
OpenAI · 400k context · $1.375 in · $11.00 out
- GPT-5.1-Codex-Mini
OpenAI · 400k context · $0.275 in · $2.20 out
- Kimi K2 Thinking
Moonshot · 262k context · $0.66 in · $2.75 out
- Nova Premier 1.0
Amazon · 1M context · $2.75 in · $13.75 out
- Sonar Pro Search
Perplexity · 200k context · $3.30 in · $16.50 out
- Voxtral Small 24B 2507
Mistral · 32k context · $0.11 in · $0.33 out
- gpt-oss-safeguard-20b
OpenAI · 131k context · $0.0825 in · $0.33 out
- GPT-5 Image Mini
OpenAI · 400k context · $2.75 in · $2.20 out
- Claude Haiku 4.5
Anthropic · 200k context · $1.10 in · $5.50 out
- Qwen3 VL 8B Instruct
Qwen · 262k context · $0.275 in · $0.825 out
- GPT-5 Image
OpenAI · 400k context · $11.00 in · $11.00 out
- Nano Banana
Google · 32k context · $0.33 in · $2.75 out
- Qwen3 VL 30B A3B Instruct
Qwen · 262k context · $0.165 in · $0.66 out
- GLM 4.6
Z.ai · 204k context · $0.55 in · $2.20 out
- Claude Sonnet 4.5
Anthropic · 1M context · $3.30 in · $16.50 out
- DeepSeek V3.2 Exp
DeepSeek · 163k context · $0.297 in · $0.451 out
- Cydonia 24B V4.1
TheDrummer · 131k context · $0.33 in · $0.55 out
- Relace Apply 3
Relace · 256k context · $0.935 in · $1.375 out
- Qwen3 VL 235B A22B Instruct
Qwen · 262k context · $0.231 in · $2.09 out
- DeepSeek V3.1 Terminus
DeepSeek · 163k context · $0.297 in · $1.10 out
- Qwen3 Coder Flash
Qwen · 1M context · $0.2145 in · $1.0725 out
- Qwen3 Next 80B A3B Instruct
Qwen · 262k context · $0.099 in · $1.21 out
- Hermes 4 405B
Nous Research · 131k context · $1.10 in · $3.30 out
- DeepSeek V3.1
DeepSeek · 163k context · $0.275 in · $1.045 out
- Mistral Medium 3.1
Mistral · 131k context · $0.44 in · $2.20 out
- GLM 4.5V
Z.ai · 65k context · $0.66 in · $1.98 out
- gpt-oss-120bAlso:batch
OpenAI · 131k context · $0.165 in · $0.66 out
- gpt-oss-20bAlso:batch
OpenAI · 131k context · $0.033 in · $0.143 out
- Claude Opus 4.1
Anthropic · 200k context · $16.50 in · $82.50 out
- Codestral 2508
Mistral · 256k context · $0.33 in · $0.99 out
- Qwen3 Coder 30B A3B Instruct
Qwen · 262k context · $0.165 in · $0.66 out
- Qwen3 30B A3B Instruct 2507
Qwen · 262k context · $0.11 in · $0.33 out
- GLM 4.5
Z.ai · 131k context · $0.66 in · $2.42 out
- GLM 4.5 Air
Z.ai · 131k context · $0.22 in · $1.21 out
- Qwen3 235B A22B Thinking 2507
Qwen · 128k context · $0.495 in · $3.85 out
- Qwen3 Coder 480B A35B
Qwen · 262k context · $0.33 in · $1.10 out
- UI-TARS 7B
ByteDance · 128k context · $0.11 in · $0.22 out
- Gemini 2.5 Flash Lite
Google · 1M context · $0.11 in · $0.44 out
- Qwen3 235B A22B Instruct 2507
Qwen · 262k context · $0.154 in · $0.88 out
- Kimi K2 0711Also:Kimi K2 0905
Moonshot · 131k context · $0.627 in · $2.53 out
- Uncensored
Venice · 128k context · $0.22 in · $0.99 out
- Morph V3 LargeAlso:batch
Morph · 262k context · $0.99 in · $2.09 out
- Morph V3 FastAlso:batch
Morph · 262k context · $0.88 in · $1.32 out
- Mistral Small 3.2 24B
Mistral · 256k context · $0.11 in · $0.33 out
- Gemini 2.5 Flash
Google · 1M context · $0.33 in · $2.75 out
- Gemini 2.5 Pro
Google · 1M context · $1.375 in · $11.00 out
- o3 Pro
OpenAI · 200k context · $22.00 in · $88.00 out
- Gemini 2.5 Pro Preview 06-05
Google · 1M context · $1.375 in · $11.00 out
- R1 0528
DeepSeek · 163k context · $0.55 in · $2.365 out
- Mistral Medium 3
Mistral · 131k context · $0.44 in · $2.20 out
- Llama Guard 4 12B
Meta · 163k context · $0.198 in · $0.198 out
- Qwen3 30B A3B
Qwen · 40k context · $0.132 in · $0.55 out
- Qwen3 14B
Qwen · 40k context · $0.132 in · $0.264 out
- Qwen3 32B
Qwen · 131k context · $0.088 in · $0.308 out
- GPT-4.1 Nano
OpenAI · 1M context · $0.11 in · $0.44 out
- Llama 4 Maverick
Meta · 524k context · $0.385 in · $1.10 out
- Llama 4 Scout
Meta · 327k context · $0.11 in · $0.33 out
- DeepSeek V3 0324
DeepSeek · 163k context · $0.319 in · $1.254 out
- Mistral Small 3.1 24B
Mistral · 128k context · $0.3861 in · $0.6105 out
- Gemma 3 4B
Google · 131k context · $0.055 in · $0.11 out
- Gemma 3 12B
Google · 131k context · $0.055 in · $0.165 out
- Command A
Cohere · 256k context · $2.75 in · $11.00 out
- Reka Flash 3
Reka · 65k context · $0.11 in · $0.22 out
- Gemma 3 27B
Google · 131k context · $0.088 in · $0.385 out
- Skyfall 36B V2
TheDrummer · 32k context · $0.605 in · $0.88 out
- Sonar Reasoning Pro
Perplexity · 128k context · $2.20 in · $8.80 out
- Sonar Pro
Perplexity · 200k context · $3.30 in · $16.50 out
- Sonar Deep Research
Perplexity · 128k context · $2.20 in · $8.80 out
- Saba
Mistral · 32k context · $0.22 in · $0.66 out
- Aion-RP 1.0 (8B)
AionLabs · 32k context · $0.88 in · $1.76 out
- Qwen2.5 VL 72B Instruct
Qwen · 128k context · $0.88 in · $1.10 out
- Qwen-Plus
Qwen · 1M context · $0.286 in · $0.858 out
- Mistral Small 3
Mistral · 32k context · $0.055 in · $0.088 out
- Sonar
Perplexity · 127k context · $1.10 in · $1.10 out
- Phi 4
Microsoft · 16k context · $0.077 in · $0.154 out
- DeepSeek V3
DeepSeek · 163k context · $0.28314 in · $1.13157 out
- Command R7B (12-2024)
Cohere · 128k context · $0.04125 in · $0.165 out
- Llama 3.3 70B Instruct
Meta · 131k context · $0.781 in · $0.781 out
- Nova Lite 1.0
Amazon · 300k context · $0.066 in · $0.264 out
- Nova Micro 1.0
Amazon · 128k context · $0.0385 in · $0.154 out
- Nova Pro 1.0
Amazon · 300k context · $0.88 in · $3.52 out
- Qwen2.5 Coder 32B Instruct
Qwen · 32k context · $0.726 in · $1.10 out
- UnslopNemo 12B
TheDrummer · 1M context · $0.44 in · $0.44 out
- Magnum v4 72B
Anthracite · 32k context · $2.75 in · $5.50 out
- Llama 3.2 1B Instruct
Meta · 60k context · $0.0297 in · $0.2211 out
- Llama 3.2 3B Instruct
Meta · 131k context · $0.05599 in · $0.3685 out
- Qwen2.5 72B Instruct
Qwen · 32k context · $0.396 in · $0.44 out
- Command R (08-2024)
Cohere · 128k context · $0.165 in · $0.66 out
- Command R+ (08-2024)
Cohere · 128k context · $2.75 in · $11.00 out
- Llama 3.1 Euryale 70B v2.2
Sao10K · 131k context · $0.935 in · $0.935 out
- Llama 3 8B Lunaris
Sao10K · 8k context · $0.044 in · $0.055 out
- Llama 3.1 70B Instruct
Meta · 131k context · $0.792 in · $0.792 out
- Llama 3.1 8B Instruct
Meta · 131k context · $0.022 in · $0.044 out
- Mistral Nemo
Mistral · 131k context · $0.0319 in · $0.033 out
- Gemma 2 27B
Google · 8k context · $0.715 in · $0.715 out
- Mixtral 8x22B Instruct
Mistral · 65k context · $2.20 in · $6.60 out
- Mistral LargeAlso:Mistral Large 3 2512Mistral Large 2407
Mistral · 128k context · $2.20 in · $6.60 out
- GPT-3.5 Turbo (older v0613)
OpenAI · 4k context · $1.10 in · $2.20 out
- GPT-3.5 Turbo 16k
OpenAI · 16k context · $3.30 in · $4.40 out
- Weaver (alpha)
Mancer · 8k context · $0.33 in · $0.55 out
- ReMM SLERP 13B
Undi95 · 6k context · $0.33 in · $0.55 out
- MythoMax 13B
Gryphe · 8k context · $0.088 in · $0.121 out
- GPT-4
OpenAI · 8k context · $33.00 in · $66.00 out
- gpt-4.1
OpenAI · 1M context · $2.20 in · $8.80 out
- gpt-4.1-mini
OpenAI · 1M context · $0.44 in · $1.76 out
- gpt-4oAlso:GPT-4o (2024-11-20)GPT-4o (2024-08-06)GPT-4o (2024-05-13)
OpenAI · 128k context · $2.75 in · $11.00 out
- gpt-4o-miniAlso:GPT-4o-mini (2024-07-18)
OpenAI · 128k context · $0.165 in · $0.66 out
- gpt-5
OpenAI · 400k context · $1.375 in · $11.00 out
- gpt-5-mini
OpenAI · 400k context · $0.275 in · $2.20 out
- gpt-5-nanoAlso:batch
OpenAI · 400k context · $0.055 in · $0.44 out
- gpt-5-pro
OpenAI · 400k context · $16.50 in · $132.00 out
- gpt-5-search-api
OpenAI · No published price
- gpt-5.1
OpenAI · 400k context · $1.375 in · $11.00 out
- gpt-5.2
OpenAI · 400k context · $1.925 in · $15.40 out
- gpt-5.2-pro
OpenAI · 400k context · $23.10 in · $184.80 out
- gpt-5.3-codex
OpenAI · 400k context · $1.925 in · $15.40 out
- gpt-5.4
OpenAI · 1M context · $2.75 in · $16.50 out
- gpt-5.4-miniAlso:latest
OpenAI · 400k context · $0.825 in · $4.95 out
- gpt-5.4-nano
OpenAI · 400k context · $0.22 in · $1.375 out
- gpt-5.4-pro
OpenAI · 1M context · $33.00 in · $198.00 out
- gpt-5.5
OpenAI · 1M context · $5.50 in · $33.00 out
- gpt-5.5-pro
OpenAI · 1M context · $33.00 in · $198.00 out
- gpt-5.6-lunaAlso:batch
OpenAI · 1M context · $0.22 in · $1.32 out
- gpt-5.6-solAlso:batch
OpenAI · 1M context · $4.40 in · $22.00 out
- gpt-5.6-terraAlso:batch
OpenAI · 1M context · $2.20 in · $13.20 out
- o3
OpenAI · 200k context · $2.20 in · $8.80 out
Prices are what you are billed, in US dollars per million tokens.