Codestral 25.08

CODING

Mistral · mistral/codestral

Coming soon

Mistral's code model for chat and fill-in-the-middle completion.

Not callable yet: Padma has not connected Mistral on this server. The price is real; requests answer 503 model_unavailable, and are not charged, until it is.

Input / 1M tokens

৳36.90

Output / 1M tokens

৳110.71

Cached input / 1M

৳3.69

Context length

128K

Max output

64K

Provider list price: $0.30 in · $0.90 out per 1M tokens (Mistral), × ৳123.01 per dollar. No markup.

Suitable for

Coding
Fast

Example request

cURL

curl https://padmarouter.com/v1/chat/completions \
  -H "Authorization: Bearer $PADMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/codestral",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Docs for this model

Performance

Throughput170 tok/s

Time to first token0.3s

StreamingSupported

Tool callingSupported

Typical figures for this model, which the auto/* routers score on — not a guarantee for any one request.

Routing

Primary routeMistral direct

Fallback hostsNone — one host

Prompt retentionPadma keeps none unless you turn on payload logging; the provider's own API terms apply