jishie

Devstral 2

opper/mistral/devstral-2512 · family devstral · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.

$0.80
Blended $/1M (3:1)
$0.4
Input $/1M
$2
Output $/1M
$2.40
1M in + 1M out
Cache read $/1M
#3236 of 6,829
Cheapest rank
Provider
Opper (opper)
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 10 providers — cheapest-effective first. This one (Opper) is the cheapest.

ProviderInputOutputBlendedContext
Opper (this)$0.4$2$0.80262k
Merge Gateway$0.4$2$0.80256k
Mistral$0.4$2$0.80262k
Vercel AI Gateway$0.4$2$0.80256k
Eden AI$0.4$2$0.80262k
DevPass (LLM Gateway)$0.4$2$0.80262k
Pioneer$0.4$2$0.80256k
Cortecs$0.446$2.23$0.89262k
GreenPT$0.57$2.74$1.11200k
AnyAPI262k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Opper and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"mistral/devstral-2512","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Opper models · model index · JSON