MiniMax M3.1 Flash
refuseless/minimax-m3.1-flash · family minimax · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.04
Blended $/1M (3:1)
$0.02
Input $/1M
$0.08
Output $/1M
$0.10
1M in + 1M out
$0.002 −90%
Cache read $/1M
#626 of 9,232
Cheapest rank
- Provider
- Refuseless (
refuseless) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 512,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“MiniMax M3.1 Flash” is offered by 6 providers — cheapest-effective first. This one (Refuseless) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Refuseless (this) | $0.02 | $0.08 | $0.04 | 1M |
| EmpirioLabs AI | $0.1125 | $0.45 | $0.20 | 1M |
| OpenCode Go | $0.15 | $0.6 | $0.26 | 1M |
| Merge Gateway | $0.15 | $0.6 | $0.26 | 1M |
| NanoGPT | $0.15 | $0.6 | $0.26 | 1M |
| Venice AI | $0.1875 | $0.75 | $0.33 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Refuseless and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"minimax-m3.1-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):