Pricing and availability as of
Code specialist model for low-latency code generation and FIM.
codestral-2508Compare price, limits and live performance side by side. LLM Gateway routes each request to the best provider that can handle your prompt size and parameters.
1 provider
| Provider | Actions | ||||||
|---|---|---|---|---|---|---|---|
| 256k | $0.30 | $0.90 |
Prices are per provider at standard rates; open a row for regions, tiers and cache pricing. Throughput, latency and uptime come from LLM Gateway traffic over the last 24 hours and are hidden under 1,000 requests.
Codestral API pricing starts at $0.30 per 1M input tokens and $0.90 per 1M output tokens through LLM Gateway.
| Provider | Input / 1M tokens | Output / 1M tokens | Cached input / 1M tokens | Context window |
|---|---|---|---|---|
| Mistral AI | $0.30 | $0.90 | — | 256,000 tokens |
| Monthly usage | Cost on Mistral AI |
|---|---|
| 1M input + 250K output tokens | $0.525 |
| 10M input + 2.5M output tokens | $5.25 |
| 100M input + 25M output tokens | $52.50 |
Code specialist model for low-latency code generation and FIM. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Codestral on LLM Gateway starts at $0.30 per million input tokens and $0.90 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Codestral supports a context window of up to 256,000 tokens on its largest provider deployment.
Codestral is served by Mistral AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Codestral supports soft JSON output, but not tool calling or strict JSON output schema.
Codestral was released on July 30, 2025.