MiniMax M2.5 High Speed

vercel/minimax/minimax-m2.5-highspeed · family minimax · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$1.05Blended $/1M (3:1)

$0.6Input $/1M

$2.4Output $/1M

$3.001M in + 1M out

$0.03 −95%Cache read $/1M

#3239 of 5,000Cheapest rank

Provider: Vercel AI Gateway (vercel)
Context: 204,800 tokens
Max output: 131,000 tokens
Capabilities: toolsreasoningtext

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"minimax/minimax-m2.5-highspeed","messages":[{"role":"user","content":"hello"}]}'

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