Mistral: Mistral Small 4 (batch)
The Mistral Small 4 is an AI model that handles both text and image inputs, with a maximum context length of 262144 tokens. It supports tools and reasoning capabilities, but does not provide structured output. For those looking for a model with robust tool support and reasoning abilities, the Mistral Small 4 may be worth considering due to its price point and benchmark standing. With an input cost of $0.075 per million tokens and an output cost of $0.3 per million tokens, it falls in the middle tier of models in terms of pricing. Its blended benchmark score of 4.2 across one independent benchmark also suggests that it performs well, but further evaluation is needed to confirm its overall capabilities.
Benchmark results
Independent, published benchmarks. Blended score 4.2 across 1 benchmark, last refreshed 2026-09-10. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 9.6 |
- Model ID
- mistralai/mistral-small-2603:batch
- Vendor
- mistralai
- Released
- March 2026
- Tokenizer
- Mistral
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 209,715 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.07/M input and $0.30/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.05 |
| A month of a busy support chatbot | 5M in / 2M out | $0.97 |
Price & spec history
Tracked daily by PicksByModel since 2026-08-29.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-09-10 | $0.07 | $0.30 | 262,144 |
| 2026-08-29 | $0.15 | $0.60 | 262,144 |
Category rankings
Where Mistral: Mistral Small 4 (batch) places across the 7 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #15 | Self-Hosted / LocalCost · of 25 ranked | 117 |
| #15 | Real-Time ChatLatency · of 25 ranked | 118 |
| #19 | Cheap Bulk InferenceCost · of 25 ranked | 137 |
| #23 | Social Media PostsWriting · of 25 ranked | 119 |
| #23 | Voice Assistant BackendVoice · of 25 ranked | 123 |
| #24 | Bulk Data LabelingData · of 25 ranked | 129 |
| #25 | Dataset AnnotationResearch · of 25 ranked | 133 |
Similar models
Mistral: Mistral Medium 3.5
Mistral: Mistral Medium 3.5 (batch)
Mistral: Mistral Small 4
Mistral: Mistral Large 3 2512
Mistral: Mistral Large 3 2512 (batch)
Mistral: Ministral 3 8B 2512 (batch)
Quick answers
- How much does Mistral: Mistral Small 4 (batch) cost?
- $0.07 per million input tokens and $0.30 per million output tokens.
- What is Mistral: Mistral Small 4 (batch)'s context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Mistral: Mistral Small 4 (batch) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Mistral: Mistral Small 4 (batch) process images?
- Yes, it accepts image input.