Mistral Small 4 (batch)
Mistral · Multimodal · Released Mar 2026
Mistral Small 4 is a fast, cost-effective model designed for high-volume and latency-sensitive workloads with a 262K token context window.
- Strengths
- It delivers strong performance on reasoning and code generation while maintaining low latency and operational efficiency.
- Best for
- High-frequency, latency-critical tasks and large-scale production deployments where throughput matters.
- Limitations
- It is positioned below Mistral Medium 3.5 in capability; use Medium 3.5 for workloads requiring stronger reasoning or when latency is not a primary constraint.
Input / 1M
$0.075
Output / 1M
$0.3
Cached input / 1M
$0.0075
Context window
262K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 50.0% out decreased 50.0%
- 90d
- in decreased 50.0% out decreased 50.0%
- 1y
- in decreased 50.0% out decreased 50.0%
- Since launch
- in decreased 50.0% out decreased 50.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 10 Sep 2026 | $0.075 | $0.3 | $0.0075 | Imported from OpenRouter | openrouter.ai |
| 28 Aug 2026 | $0.15 | $0.6 | $0.015 | Imported from OpenRouter | openrouter.ai |