Mistral
99.75%Context128K
Max output4K
p50 latency324 ms
Throughput145.0 t/s
Input price$0.3
Output price$0.9
Zero retentionNo training
Model directory
Baseer model profileLanguage model
mistral/codestral
Mistral Codestral
Mistral's cutting-edge language model for coding released end of July 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.
Input / 1M tokens$0.3
Output / 1M tokens$0.9
Maximum context128K
Inference providers1
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Mistral | 128K | 4K | 324 ms | 145.0 t/s | 99.748% | $0.3 | $0.9 |
What can this model do?
Available modalities and capabilities across inference providers.
TextTool useTools
Technical profile
- Model type
- Language model
- Release date
- May 29, 2024
- Knowledge cutoff
- 2024-10
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
mistral/codestralModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.