Codestral 2508
cortecs/codestral-2508 · family mistral · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.55
Blended $/1M (3:1)
$0.368
Input $/1M
$1.1
Output $/1M
$1.47
1M in + 1M out
$0.037 −90%
Cache read $/1M
#3094 of 7,708
Cheapest rank
- Provider
- Cortecs (
cortecs) - Kind
- text (outputs text)
- Context
- 256,000 tokens
- Max output
- 256,000 tokens
- Capabilities
- tools text
Same model, other providers
“Codestral 2508” is offered by 3 providers — cheapest-effective first. NanoGPT is the cheapest at $0.45 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.3 | $0.9 | $0.45 | 256k |
| OpenRouter | $0.3 | $0.9 | $0.45 | 256k |
| Cortecs (this) | $0.368 | $1.1 | $0.55 | 256k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Cortecs and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"codestral-2508","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):