MiniMax M2.5 highspeed
zenmux/minimax/minimax-m2.5-lightning · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$1.65
Blended $/1M (3:1)
$0.6
Input $/1M
$4.8
Output $/1M
$5.40
1M in + 1M out
$0.06 −90%
Cache read $/1M
#4842 of 7,708
Cheapest rank
- Provider
- ZenMux (
zenmux) - Kind
- text (outputs text)
- Context
- 204,800 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“MiniMax M2.5 highspeed” is offered by 3 providers — cheapest-effective first. NovitaAI is the cheapest at $1.05 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NovitaAI | $0.6 | $2.4 | $1.05 | 205k |
| Merge Gateway | $0.6 | $2.4 | $1.05 | 205k |
| ZenMux (this) | $0.6 | $4.8 | $1.65 | 205k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at ZenMux 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-lightning","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):