MiniMax-M3
minimax/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
#2999 of 7,710
Cheapest rank
- Provider
- MiniMax (minimax.io) (
minimax) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 512,000 tokens
- Capabilities
- tools reasoning text image video
Same model, other providers
“MiniMax-M3” is offered by 42 providers — cheapest-effective first. MiniMax Token Plan (minimax.io) is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| MiniMax Token Plan (minimax.io) | free | free | $0.00 | 1M |
| MiniMax Token Plan (minimax.cn) | free | free | $0.00 | 1M |
| Volcengine Ark Coding Plan | free | free | $0.00 | 1M |
| SCNet Token Plan | free | free | $0.00 | 1M |
| Nvidia | free | free | $0.00 | 1M |
| Kenari | free | free | $0.00 | 1M |
| Vancine | $0.24 | $0.96 | $0.42 | 1M |
| Deep Infra | $0.28 | $1.1 | $0.49 | 524k |
| AIHubMix | $0.288 | $1.15 | $0.50 | 1M |
| IteraCompute | $0.29 | $1.2 | $0.52 | 1M |
| MiniMax (minimax.io) (this) | $0.3 | $1.2 | $0.52 | 1M |
| SiliconFlow | $0.3 | $1.2 | $0.52 | 1M |
| Kilo Gateway | $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 MiniMax (minimax.io) 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):