MiniMax-M3
requesty/minimax-m3 · family minimax · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.
$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
#2460 of 6,373
Cheapest rank
- Provider
- Requesty (
requesty) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text image video
Same model, other providers
“MiniMax-M3” is offered by 32 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 1M |
| Kenari | free | free | $0.00 | 512k |
| MiniMax Token Plan (minimaxi.com) | free | free | $0.00 | 1M |
| MiniMax Token Plan (minimax.io) | free | free | $0.00 | 1M |
| SCNet Token Plan | free | free | $0.00 | 512k |
| Deep Infra | $0.28 | $1.1 | $0.49 | 524k |
| Requesty (this) | $0.3 | $1.2 | $0.52 | 1M |
| Jalapeno Cloud | $0.3 | $1.2 | $0.52 | 524k |
| Hugging Face | $0.3 | $1.2 | $0.52 | 524k |
| OpenRouter | $0.3 | $1.2 | $0.52 | 1M |
| OpenCode Go | $0.3 | $1.2 | $0.52 | 1M |
| Nebius Token Factory | $0.3 | $1.2 | $0.52 | 1M |
| Together AI | $0.3 | $1.2 | $0.52 | 524k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Requesty and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"minimax-m3","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):