Mistral API pricing

Mistral Tiny API pricing

Mistral Tiny costs $0.25 per million input tokens and $0.25 per million output tokens on the Mistral API, and $0.025 per million cached input tokens. Context window: 32k tokens. Updated .

Price per 1M tokensUS dollars
Input$0.25
Cached input$0.025
Output$0.25

What it costs in practice

  • One chat or extraction call (2,000 tokens in, 500 out): $0.0006
  • 1,000 such calls: $0.625
  • 1 million tokens at a typical 80% input / 20% output mix: $0.250

Abilities: JSON schema output. Batch, long-context, priority and regional prices differ; check the full table and the provider’s own pricing page before you commit.

Cheapest alternatives from other providers

ModelInputOutputContextTypical call ×1,000
Qwen Turbo
Alibaba (Qwen)
$0.050$0.20129k$0.20
GLM 4 32b 0414 128k
Zhipu (GLM)
$0.10$0.10128k$0.25
GPT-5 nano
OpenAI
$0.050$0.40272k$0.30
Gemini 2.5 Flash Lite
Google
$0.10$0.401.0M$0.40
DeepSeek Coder
DeepSeek
$0.14$0.28128k$0.42
Claude Haiku 5.5
Anthropic
$0.10$0.501M$0.45

Other Mistral models

ModelInputOutputContextTypical call ×1,000
Mistral Small
Mistral
$0.10$0.3032k$0.35
Zai GLM 5.3 Flash
Mistral
$0.15$0.501.0M$0.55
Mistral Vibe Cli Fast
Mistral
$0.15$0.60262k$0.60
Open Mistral Nemo
Mistral
$0.30$0.30128k$0.75
Mistral Large 3
Mistral
$0.50$1.50262k$1.75
Mistral Large 4
Mistral
$0.70$2.101.0M$2.45

Questions

How much does Mistral Tiny cost?

Mistral Tiny costs $0.25 per million input tokens and $0.25 per million output tokens on the Mistral API; cached input is $0.025 per million. A typical call with 2,000 tokens in and 500 out costs about $0.0006.

What is the context window of Mistral Tiny?

Mistral Tiny accepts up to 32,000 input tokens and returns up to 8,191 output tokens.

Is there a cheaper alternative to Mistral Tiny?

For a typical call, Qwen Turbo (Alibaba (Qwen), $0.0002 per call), GLM 4 32b 0414 128k (Zhipu (GLM), $0.0003 per call), GPT-5 nano (OpenAI, $0.0003 per call) cost less and also support JSON schema output. Quality differs, so test on your own prompts.

Source: the open LiteLLM model price map (MIT), checked daily (data file).