Context
1M
Max output
524K
Input / 1M
$0.30
Output / 1M
$1.20
Modality
Chat
Cutoff
unknown
About this model
MiniMax-M3 is MiniMax's flagship model supporting up to 1M tokens of context (guaranteed minimum 512K), with text, image, and video input.
Best suited for
- Long-context conversations (up to 1M tokens)
- Reasoning and engineering workflows
- Multimodal (text/image/video) tasks
- General-purpose AI applications
Capabilities
Vision
Accepts images alongside text in the same message.
Files
Accepts file attachments — PDFs, transcripts, spreadsheets.
Tools
Native function calling, so agents can invoke your endpoints.
System prompt
Honours a dedicated system role, separate from the user turn.
Supported parameters
max_tokensMax Tokens LimitSpecifies the maximum number of text units (tokens) allowed in a response, limiting its length.
toolsLists tool definitions or capabilities available to the model.
tool_choiceDecides whether to use tools or just the model for generating responses.
response_typeDefines the format or type of the generated response.
creativity_levelControls randomness (temperature). Higher values (0.8) make output more random, lower values (0.2) more focused and deterministic.
log_probabilityLog ProbabilitiesWhether to return log probabilities of the output tokens.
probability_cutoffNucleus sampling parameter. The model considers tokens with top_p probability mass.
Use this model
OpenAI-SDK compatible, with gateway fallback and routing across providers.
Other Minimax models
| Model | Context | Max output | Input | Output | Capabilities |
|---|---|---|---|---|---|
| MiniMax-M3.1-Flash Chat | 1M | 524K | $0.15 | $0.60 | Vision, Files, Tools, System prompt |
| MiniMax-M2.7 Chat | 205K | 128K | $0.30 | $1.20 | Vision, Files, Tools, System prompt |
| MiniMax-M2.7-highspeed Chat | 205K | 128K | $0.60 | $2.40 | Vision, Files, Tools, System prompt |
| minimax-m3 Chat | 1M | 524K | $0.30 | $1.20 | Vision, Files, Tools, System prompt, Reasoning |
| MiniMax-M2 Chat | 205K | 128K | $0.30 | $1.20 | Files, Tools, System prompt |
| minimax-m2.1-highspeed Chat | 205K | 128K | $0.60 | $2.40 | Files, Tools, System prompt |
| minimax-m2.1 Chat | 205K | 128K | $0.30 | $1.20 | Files, Tools, System prompt |
| minimax-m2.5-highspeed Chat | 205K | 128K | $0.60 | $2.40 | Files, Tools, System prompt |
| minimax-m2.5 Chat | 205K | 128K | $0.30 | $1.20 | Files, Tools, System prompt |
Pricing & provider details
Minimax
minimax/MiniMax-M3
- Input · per 1M
- $0.30
- Output · per 1M
- $1.20
- Cached input · per 1M
- —
- Context window
- 1,000,000 tokens
- Max output
- 524,288 tokens
- Knowledge cutoff
- unknown
- Auto-router
- Supported
Start building today
Route MiniMax-M3 — and every other model in the catalogue — through one endpoint, with failover built in.