Available now
MiniMax
minimax-m3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
TextReasoningToolsFilesVision512KVideoCache
Input$0.63/ 1M
Output$2.52/ 1M
Context512K
Endpointsopenai
Capabilities
ReasoningToolsVisionVideoCacheStructuredSystem msg
Modalities
Input
textimagevideo
Output
text
Quick stats
Context window512K
Max output128K
Modechat
TokenizerOther
Quantizationfp8
Performance
Loading performance data...
Supported parameters
| Parameter | Always | Default |
|---|---|---|
| frequency_penalty | - | (do not send) |
| include_reasoning | - | |
| max_tokens | - | |
| presence_penalty | - | (do not send) |
| reasoning | - | |
| repetition_penalty | - | (do not send) |
| response_format | - | |
| temperature | 1 | |
| tool_choice | - | |
| tools | - | |
| top_k | - | (do not send) |
| top_p | 0.95 |
§ 01
Pricing
| Input price | $0.63 · 1M tokens |
| Output price | $2.52 · 1M tokens |
| Context window | 512K tokens |
| Compatible endpoints | openai |
| Vendor | MiniMax |
§ 02
Call minimax-m3 from your code
Point any OpenAI-compatible SDK at UnoRouter and request the model by name. Replace YOUR_API_KEY with a real key from your dashboard.
bash
curl https://api.unorouter.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-m3",
"messages": [{"role": "user", "content": "Hello!"}]
}'§ 03
Frequently asked questions
How much does minimax-m3 cost per 1M tokens?
Input is priced at $0.63 per 1M tokens, output at $2.52 per 1M tokens. Billing is per token, no rounding to batch sizes.
How do I access minimax-m3 via API?
Send requests to the UnoRouter /v1/chat/completions endpoint with model=minimax-m3. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.
What is the context window of minimax-m3?
minimax-m3 supports a context window of 512K tokens, shared between your prompt and the model's response.
§ 04