🇫🇷 Global model

Pixtral 12B

Text Image Function calling File input

Pricing & specs

Input / 1M tokens $0.15

Output / 1M tokens $0.15

Cache / 1M tokens —

Context window 128K tokens

Max output 128K tokens

Updated 2024-09-01

Docs Official docs ↗

Price source View source ↗

Providers

USD / 1M tokens · input / output

Mistral Official $0.15 / $0.15 Pioneer lowest $0.15 / $0.15

Similar models · Top 5

Spark Ultra 🇨🇳 128K In $0.12 · Out $0.12 · Cache — Qwen Doc Turbo 🇨🇳 131K In $0.09 · Out $0.14 · Cache — Qwen2.5-Coder 7B Instruct 🇨🇳 131K In $0.14 · Out $0.29 · Cache — Qwen2.5 7B Instruct 🇨🇳 131K In $0.07 · Out $0.14 · Cache — Qwen-VL Plus 🇨🇳 131K In $0.12 · Out $0.29 · Cache —

Want to go deeper on AI and cloud cost management?

Explore more on AI infrastructure, model API cost and resource optimization at mofcloud.

Go to mofcloud Back to price explorer