MiniMax M1
nano-gpt/MiniMax-M1 · family minimax · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.
$0.44
Blended $/1M (3:1)
$0.1394
Input $/1M
$1.33
Output $/1M
$1.47
1M in + 1M out
$0.0697 −50%
Cache read $/1M
#2602 of 7,708
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- text
Same model, other providers
“MiniMax M1” is offered by 5 providers — cheapest-effective first. This one (NanoGPT) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT (this) | $0.1394 | $1.33 | $0.44 | 1M |
| OpenRouter | $0.4 | $2.2 | $0.85 | 1M |
| NovitaAI | $0.55 | $2.2 | $0.96 | 1M |
| Jiekou.AI | $0.55 | $2.2 | $0.96 | 1M |
| Qiniu | — | — | — | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"MiniMax-M1","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):