MiniMax M3
nano-gpt/minimax/minimax-m3 · family minimax · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.52
Blended $/1M (3:1)
$0.3
Input $/1M
$1.2
Output $/1M
$1.50
1M in + 1M out
$0.06 −80%
Cache read $/1M
#2914 of 7,708
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 512,000 tokens
- Max output
- 80,000 tokens
- Capabilities
- tools text image
Same model, other providers
“MiniMax M3” is offered by 6 providers — cheapest-effective first. EmpirioLabs AI is the cheapest at $0.39 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| EmpirioLabs AI | $0.225 | $0.9 | $0.39 | 1M |
| CoreWeave | $0.23 | $0.96 | $0.41 | 262k |
| Lilac | $0.28 | $1.1 | $0.49 | 1M |
| NanoGPT (this) | $0.3 | $1.2 | $0.52 | 512k |
| Vercel AI Gateway | $0.3 | $1.2 | $0.52 | 512k |
| Merge Gateway | $0.3 | $1.2 | $0.52 | 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/minimax-m3","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):