Mistral
Mistral Small 4
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.
At a glance
- Input / 1M
- $0.15
- Output / 1M
- $0.60
- Context
- 262K
- Max output
- 210K
- Intelligence
- 11.3
- Released
- Mar 2026
Pricing
Mistral Small 4 API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.15 |
|---|---|
| Output tokensPer 1M tokens | $0.60 |
| Cached input (read)Per 1M tokens | $0.02 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.60
per 1,000 requests
Coding task
30K in, 4K out
$6.90
per 1,000 requests
Long document summary
150K in, 2K out
$23.70
per 1,000 requests
Benchmarks
Mistral Small 4 benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
11.3
Coding index
26.6
Agentic index
0.8
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 262K tokens
- Max output
- 210K tokens
- Input types
- Image, Text
- Output types
- Text
- Reasoning effort
- High, None
- Release date
- March 16, 2026
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Mistral Small 4 vs other models
See how Mistral Small 4 stacks up head to head on price, benchmarks, and features.
VS
Mistral Small 4 vs Gemini 2.5 Flash Lite
Mistral vs Google
See comparisonVS
Mistral Small 4 vs gpt-oss-120b
Mistral vs OpenAI
See comparisonVSMistral Small 4 vs GPT-5 Nano
Mistral vs OpenAI
See comparisonVS
Mistral Small 4 vs Qwen3 235B A22B Instruct 2507
Mistral vs Qwen
See comparisonVSMistral Small 4 vs Nemotron 3 Super
Mistral vs NVIDIA
See comparisonVSMistral Small 4 vs Qwen3 Coder 480B A35B
Mistral vs Qwen
See comparisonAlternatives
Mistral Small 4 alternatives
Similar models worth considering, and where each one has the edge.
OpenAI
GPT-5 Nano
NVIDIA
Nemotron 3 Super
Qwen
Qwen3 235B A22B Instruct 2507
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Mistral Small 4 cost?
Mistral Small 4 costs $0.15 per 1M input tokens and $0.60 per 1M output tokens through the API. A typical chat message costs about $0.60 per 1,000 messages.
What is the context window of Mistral Small 4?
Mistral Small 4 accepts up to 262K tokens of input and can write up to 210K tokens in a single response.
What is the best alternative to Mistral Small 4?
GPT-5 Nano from OpenAI is a strong alternative. It offers: 1.5x cheaper output, higher intelligence score, larger 400k context.
Can I use Mistral Small 4 alongside other models?
Yes. Shortcut Chat sends one prompt to Mistral Small 4 and any other models you pick at the same time, so you can compare answers side by side.
Try Mistral Small 4 next to every other model.
Use Mistral Small 4 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.