MiniMax
MiniMax M3
M3 can reason over up to one million tokens in one request, enough to compare lengthy specifications or trace dependencies across a large codebase.
minimax/minimax-m3- Input
- Chat messages
- Output
- Text
- Endpoint
POST /v1/chat/completions
Best for
- Trace a behavior across several parts of a codebase
- Compare requirements across lengthy specifications
Technical details
Read the model documentation- API model ID
minimax/minimax-m3- Provider
- MiniMax
- Modality
- Text
- Input
- Chat messages
- Output
- Text
- Endpoint
POST /v1/chat/completions
Request parameters
messagesobject[] · RequiredThe conversation, in OpenAI's format.
OpenAI chat messages (system, user, assistant, tool)
max_completion_tokensinteger · Optional · Default: the model'sThinking tokens count toward it: too small a cap ends with finish_reason: length and an empty answer.
1 up to the model's output limit
streamboolean · Optional · Default: falseServer-sent events, as in OpenAI's API.
- true
- false
temperaturenumber · Optional · Default: 1MiniMax documents it as having no effect on M3 (fixed at 1).
(0, 1]
toolsobject[] · OptionalFunction calling, in OpenAI's format.
OpenAI function tools
Additional parameters
max_tokensinteger · OptionalThe older name for the same cap; MiniMax marks it deprecated.
as above
reasoning_splitboolean · Optional · Default: the vendor'strue returns the reasoning in reasoning_content; false leaves it inside the answer between think tags.
- true
- false
service_tierstring · Optional · Default: standardMiniMax's priority tier, on M3 only, billed at 1.5× the standard rates.
priority
stream_optionsobject · OptionalAdds a final chunk with token usage.
{"include_usage": true}
thinkingobject · Optional · Default: onThe model reasons before answering by default; disabled turns it off.
{"type": "adaptive"} · {"type": "disabled"}
tool_choicestring · Optional · Default: autoWhether the model may, must, or must not call a tool, as MiniMax documents for M3.
- none
- auto
- required
top_pnumber · Optional · Default: 0.95MiniMax documents it as having no effect on M3 (fixed at 0.95).
(0, 1]
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per 1M input tokens | |
| Base rate | $0.36 |
| prompts over 512,000 tokens | $0.72 |
| priority (service_tier: priority) | $0.54 |
| Per 1M output tokens | |
| Base rate | $1.44 |
| prompts over 512,000 tokens | $2.88 |
| priority (service_tier: priority) | $2.16 |
| Per 1M cached input tokens | |
| Base rate | $0.072 |
| prompts over 512,000 tokens | $0.144 |
| priority (service_tier: priority) | $0.108 |
| Per 1M cache-write tokens | |
| Base ratefree | $0.00 |
| priority (service_tier: priority)free | $0.00 |
Billing notes
- A prompt over 512,000 tokens bills the whole request at the long-context rates.
Catalogue rates on 21 Nov 2026. Prices exclude VAT.
View in pricing catalogue