MiniMax M2.5
venice/minimax-m25 · family minimax · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.44
Blended $/1M (3:1)
$0.27
Input $/1M
$0.95
Output $/1M
$1.22
1M in + 1M out
$0.03 −89%
Cache read $/1M
#2604 of 7,710
Cheapest rank
- Provider
- Venice AI (
venice) - Kind
- text (outputs text)
- Context
- 198,000 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“MiniMax M2.5” is offered by 9 providers — cheapest-effective first. Deep Infra is the cheapest at $0.40 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Deep Infra | $0.15 | $1.15 | $0.40 | 197k |
| Venice AI (this) | $0.27 | $0.95 | $0.44 | 198k |
| D.Run (China) | $0.29 | $1.16 | $0.51 | 205k |
| NanoGPT | $0.3 | $1.2 | $0.52 | 205k |
| NovitaAI | $0.3 | $1.2 | $0.52 | 205k |
| ZenMux | $0.3 | $1.2 | $0.52 | 205k |
| Vercel AI Gateway | $0.3 | $1.2 | $0.52 | 205k |
| Merge Gateway | $0.3 | $1.2 | $0.52 | 205k |
| Meganova | $0.3 | $1.2 | $0.52 | 205k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Venice AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"minimax-m25","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):