z-ai
Mistral Small 4 vs GLM 5.3 Flash
71.6 overall · $0.237 / 1M
// mistralai
Mistral Small 4
mistralai/mistral-small-2603
reasoningtool callingimage inputprompt caching
Mistral Small 4 costs $0.150 per 1M input tokens and $0.600 per 1M output tokens with a 262K-token context window.
A reasoning, tool-calling model from mistralai, released Mar 16, 2026. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $0.150
- Output / 1M
- $0.600
- Context
- 262K
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $0.150 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $0.600 |
| Blended price 3:1 input:output — #93 cheapest of 343 listed models | $0.262 |
| Cached input read Blank means not priced separately — not free | $0.015 |
| Cache write | — |
| Context window | 262,144 tokens |
| Max output | 209,715 tokens |
| Input modalities | text, image |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Mar 16, 2026 |
Also listed as mistralai/mistral-small-2603:batch ($0.131 blended)— the same model at a different price or rate limit.
What Mistral Small 4 costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $74.28/mo |
| RAG assistant 8K in / 600 out × 100K requests | $102.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $92.40/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $188.25/mo |
| Bulk classification 500 in / 20 out × 5M requests | $367.50/mo |
Compare Mistral Small 4 with
Benchmarked models at a similar price.
deepseek
Mistral Small 4 vs DeepSeek V4 Flash Vision Exp
76.8 overall · $0.330 / 1M
openai
Mistral Small 4 vs GPT-6 Luna
72.0 overall · $0.200 / 1M
deepseek
Mistral Small 4 vs DeepSeek V4.1 Flash
81.1 overall · $0.200 / 1M
deepseek
Mistral Small 4 vs DeepSeek V4 Flash 0731
74.2 overall · $0.190 / 1M
openai
Mistral Small 4 vs GPT-5.6 Luna
73.6 overall · $0.450 / 1M
Mistral Small 4 FAQ
How much does Mistral Small 4 cost?
Mistral Small 4 lists at $0.150 per 1M input tokens and $0.600 per 1M output tokens, with cached input reads at $0.015 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $102.00 at list price.
What is the context window of Mistral Small 4?
Mistral Small 4 accepts up to 262,144 tokens of context and can return up to 209,715 output tokens per response.
Does Mistral Small 4 support tool calling?
Yes — Mistral Small 4 supports tool (function) calling and exposes extended reasoning. It accepts text, image input.
How does Mistral Small 4 score on benchmarks?
LiveBench has not published a run for Mistral Small 4 yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for Mistral Small 4?
On OpenRouter the model ID is "mistralai/mistral-small-2603". It was listed on Mar 16, 2026.
More from mistralai
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.