Codestral is Mistral’s language model for coding, specialized in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction, and test generation. It is built for developer productivity and supports a wide range of programming languages and code-related tasks.
$0.15market price $0.30
$0.015market price $0.03
$0.45market price $0.90
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Not enough throughput data
Not enough TTFT data
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
Codestral is Mistral’s language model for coding, specialized in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction, and test generation. It is built for developer productivity and supports a wide range of programming languages and code-related tasks.
On NagaAI, Codestral 2501 costs $0.15 per 1M input tokens and $0.45 per 1M output tokens. You pay only for what you use, with no subscription.
Yes. Codestral 2501 can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Mistral Large 4MistralAIMistral Medium 3.5MistralAI$0.75 / $3.75 per 1MMistral Small 2603MistralAIDevstral 2 2512MistralAI$0.20 / $1 per 1MMinistral 3 14B 2512MistralAI$0.10 / $0.10 per 1MMinistral 3 3B 2512MistralAI$0.05 / $0.05 per 1M