Skip to content
runcrate
Console

Inference pricing

Pay per token. Or per image, or per second.

121 models behind one OpenAI-compatible API, at the prices you are billed. For example, Kimi K2.6 at $0.788 per 1M input tokens. 5 open models are free with your GitHub account, then half price on shared capacity, list price when it's busy.

Get an API keyRead the docs

In the catalog

121 models

Price list

Every model we serve. Search it, or filter by what it makes.

ModelTypePriceContextTry
Google
Gemma 4 E2B
Google$0.042in$0.084outno cache discountper 1M tokens
Text$0.042in$0.084outno cache discountper 1M tokens128KTry
Mistral AI
Devstral 2 123B
Mistral AI$0.42in$2.10out$0.042cached input$0.42cache writeper 1M tokens
Text$0.42in$2.10out$0.042cached input$0.42cache writeper 1M tokens256KTry
Mistral AI
Ministral 14B 3.0
Mistral AI$0.21in$0.21out$0.021cached input$0.21cache writeper 1M tokens
Text$0.21in$0.21out$0.021cached input$0.21cache writeper 1M tokens128KTry
Mistral AI
Ministral 3 8B
Mistral AI$0.158in$0.158outno cache discountper 1M tokens
Text$0.158in$0.158outno cache discountper 1M tokens128KTry
Mistral AI
Ministral 3B
Mistral AI$0.105in$0.105out$0.0105cached input$0.105cache writeper 1M tokens
Text$0.105in$0.105out$0.0105cached input$0.105cache writeper 1M tokens128KTry
OpenAI
gpt-oss Safeguard 120B
OpenAI$0.158in$0.63outno cache discountper 1M tokens
Text$0.158in$0.63outno cache discountper 1M tokens128KTry
Meta
Muse Spark Open
Meta$1.31in$4.46out$0.158cached input$1.31cache writeper 1M tokens
Text$1.31in$4.46out$0.158cached input$1.31cache writeper 1M tokens1MTry
OpenAI
gpt-oss Safeguard 20B
OpenAI$0.0788in$0.315outno cache discountper 1M tokens
Text$0.0788in$0.315outno cache discountper 1M tokens128KTry
Mistral AI
Mistral Small 4
Mistral AI$0.158in$0.63outno cache discountper 1M tokens
Text$0.158in$0.63outno cache discountper 1M tokens256KTry
NVIDIA
Nemotron Nano 12B v2 VL BF16
NVIDIA$0.21in$0.63outno cache discountper 1M tokens
Text$0.21in$0.63outno cache discountper 1M tokens128KTry
Mistral AI
Mistral Large 3
Mistral AI$0.525in$1.58out$0.0525cached input$0.525cache writeper 1M tokens
Text$0.525in$1.58out$0.0525cached input$0.525cache writeper 1M tokens256KTry
Mistral AI
Magistral Small 2509
Mistral AI$0.525in$1.58out$0.0788cached input$0.525cache writeper 1M tokens
Text$0.525in$1.58out$0.0788cached input$0.525cache writeper 1M tokens128KTry
MiniMax
MiniMax M3.1 Flash
MiniMax$0.0788in$0.315out$0.00788cached input$0.0788cache writeper 1M tokens
Text$0.0788in$0.315out$0.00788cached input$0.0788cache writeper 1M tokens1MTry
Alibaba
Qwen3.5 397B A17B
Alibaba$0.473in$3.15out$0.231cached inputper 1M tokens
Text$0.473in$3.15out$0.231cached inputper 1M tokens262KTry
Resemble AI
Chatterbox Multilingual
Resemble AI$0.00105per 1k characters
Speech$0.00105per 1k charactersnot listedTry
Alibaba
Qwen3.8 27B
Alibaba$0.158in$1.97out$0.0394cached inputper 1M tokens
Text$0.158in$1.97out$0.0394cached inputper 1M tokens262KTry
inclusionAI
Ling 3.0 Flash VL
inclusionAI$0.063in$0.189out$0.0126cached inputper 1M tokens
Vision$0.063in$0.189out$0.0126cached inputper 1M tokens131KTry
Alibaba
Qwen3 Next 80B A3B
Alibaba$0.0945in$1.16outno cache discountper 1M tokens
Text$0.0945in$1.16outno cache discountper 1M tokens262KTry
Alibaba
Qwen3.5 35B A3B
Alibaba$0.147in$1.05out$0.0525cached inputper 1M tokens
Text$0.147in$1.05out$0.0525cached inputper 1M tokens262KTry
Google
Gemma 3 12B
Google$0.0525in$0.158outno cache discountper 1M tokens
Text$0.0525in$0.158outno cache discountper 1M tokens131KTry
Google
Gemma 4 26B A4B
Google$0.0735in$0.357outno cache discountper 1M tokens
Text$0.0735in$0.357outno cache discountper 1M tokens262KTry
Microsoft
Multilingual E5 Large Instruct
Microsoft$0.0105per 1M tokens
Embeddings$0.0105per 1M tokens512Try
DeepSeek
DeepSeek R1 0528
DeepSeek$0.525in$2.26out$0.368cached inputper 1M tokens
Text$0.525in$2.26out$0.368cached inputper 1M tokens164KTry
Alibaba
Qwen3 TTS
Alibaba$0.021per 1k characters
Speech$0.021per 1k charactersnot listedTry