Devstral 2
opencheap/devstral-2-123b · family devstral · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.01
Blended $/1M (3:1)
$0.006
Input $/1M
$0.03
Output $/1M
$0.04
1M in + 1M out
—
Cache read $/1M
#587 of 9,563
Cheapest rank
- Provider
- OpenCheap (
opencheap) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools text
Same model, other providers
“Devstral 2” is offered by 9 providers — cheapest-effective first. This one (OpenCheap) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OpenCheap (this) | $0.006 | $0.03 | $0.01 | 262k |
| Mistral | $0.4 | $2 | $0.80 | 262k |
| OpenRouter | $0.4 | $2 | $0.80 | 262k |
| Merge Gateway | $0.4 | $2 | $0.80 | 256k |
| Eden AI | $0.4 | $2 | $0.80 | 262k |
| DevPass (LLM Gateway) | $0.4 | $2 | $0.80 | 262k |
| Kilo Gateway | $0.4 | $2 | $0.80 | 262k |
| Cortecs | $0.478 | $2.39 | $0.96 | 256k |
| GreenPT | $0.57 | $2.74 | $1.11 | 200k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at OpenCheap and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"devstral-2-123b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):