Mistral Small API pricing
Mistral Small costs $0.10 per million input tokens and $0.30 per million output tokens on the Mistral API, and $0.010 per million cached input tokens. Context window: 32k tokens. Updated .
| Price per 1M tokens | US dollars |
|---|---|
| Input | $0.10 |
| Cached input | $0.010 |
| Output | $0.30 |
What it costs in practice
- One chat or extraction call (2,000 tokens in, 500 out): $0.0003
- 1,000 such calls: $0.350
- 1 million tokens at a typical 80% input / 20% output mix: $0.140
Abilities: tool use, reasoning, 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
| Model | Input | Output | Context | Typical call ×1,000 |
|---|---|---|---|---|
| Qwen Turbo Alibaba (Qwen) | $0.050 | $0.20 | 129k | $0.20 |
| GPT-5 nano OpenAI | $0.050 | $0.40 | 272k | $0.30 |
| Gemini 2.5 Flash Lite Google | $0.10 | $0.40 | 1.0M | $0.40 |
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | $0.45 |
| GPT-6 luna OpenAI | $0.10 | $0.50 | 922k | $0.45 |
| Qwen3.8 Flash Alibaba (Qwen) | $0.15 | $0.47 | 992k | $0.54 |
Other Mistral models
| Model | Input | Output | Context | Typical call ×1,000 |
|---|---|---|---|---|
| Zai GLM 5.3 Flash Mistral | $0.15 | $0.50 | 1.0M | $0.55 |
| Mistral Vibe Cli Fast Mistral | $0.15 | $0.60 | 262k | $0.60 |
| Mistral Tiny Mistral | $0.25 | $0.25 | 32k | $0.63 |
| Open Mistral Nemo Mistral | $0.30 | $0.30 | 128k | $0.75 |
| Mistral Large 3 Mistral | $0.50 | $1.50 | 262k | $1.75 |
| Mistral Large 4 Mistral | $0.70 | $2.10 | 1.0M | $2.45 |
Questions
How much does Mistral Small cost?
Mistral Small costs $0.10 per million input tokens and $0.30 per million output tokens on the Mistral API; cached input is $0.010 per million. A typical call with 2,000 tokens in and 500 out costs about $0.0003.
What is the context window of Mistral Small?
Mistral Small accepts up to 32,000 input tokens and returns up to 8,191 output tokens.
Is there a cheaper alternative to Mistral Small?
For a typical call, Qwen Turbo (Alibaba (Qwen), $0.0002 per call), GPT-5 nano (OpenAI, $0.0003 per call) cost less and also support tool use, reasoning, JSON schema output. Quality differs, so test on your own prompts.
Source: the open LiteLLM model price map (MIT), checked daily (data file).