Mistral
Codestral
Codestral is a demonstration listing for coding workflows.
You send text. It returns text. It keeps 256k of context and can write up to 8k tokens back.
- coding
- Context
- 256k
- Max output
- 8k
- Input
- text
- Output
- text
- Latency
- balanced
- Status
- available
Same request. This model.
Keep the client you already use. The model id is the only line that changes.
const response = await client.chat({
model: "codestral",
messages: [{ role: "user", content: "Summarize this brief." }],
});