> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server. # MiniMax M3 > MiniMax M3 is a multimodal reasoning model for coding, agents, and long-context analysis with text, image, and video input. ![MiniMax M3](https://media.empiriolabs.ai/model-logos/minimax.png) [MiniMax](/providers/minimax) · Text Generation `POST /v1/chat/completions` MiniMax M3 is a multimodal reasoning model for coding, agents, and long-context analysis with text, image, and video input. ## At a glance | Field | Value | | ------------------- | ------------------------------------------------------------------------------------------------------------------------ | | Model id | `minimax-m3` | | Model release date | 2026-06-01 | | Input modalities | Text, Image, Video | | Output modalities | Text | | Context window | 1M | | Weight precision | - | | Max output tokens | 524,288 | | Region | Singapore | | Features | reasoning, vision, video, web_search, function_calling, cache, long_context | | Native inference | No | | New | No | | Structured output | JSON Mode | | Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/minimax-m3:generateContent` | | Alternate model ids | `minimax-m3-standard`, `minimax/m3`, `minimax/m3-standard` | ## Pricing | Charge | Spec | Rate | | ------------------- | -------------------------- | ------------------------------------------------------- | | Input | per 1M prompt tokens | \<=512K \$0.225 (was \$0.30); >512K \$0.45 (was \$0.60) | | Output | per 1M generated tokens | \<=512K \$0.90 (was \$1.20); >512K \$1.80 (was \$2.40) | | Implicit cache read | per 1M cached input tokens | \<=512K \$0.045 (was \$0.06); >512K \$0.09 (was \$0.12) | | Web Search (Linkup) | per call when invoked | \$0.013 | ## Example request ```bash curl https://api.empiriolabs.ai/v1/chat/completions \ -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \ -H 'Content-Type: application/json' \ -d '{"model": "minimax-m3", "messages": [{"role":"user","content":"Hello"}]}' ``` ## Parameters | Parameter | Type | Required | Default | Description | | ----------------------- | ------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `temperature` | number | no | `1` | Controls randomness. Lower values are more deterministic; higher values are more exploratory. · Range: 0 – 2 | | `top_p` | number | no | `0.95` | Controls nucleus sampling by limiting generation to the most likely token mass. · Range: 0 – 1 | | `max_completion_tokens` | integer | no | `4096` | Maximum generated tokens, including reasoning tokens when thinking is enabled. · Range: 1 – 524288 | | `stop` | array | no | - | Optional stop sequence or list of stop sequences. | | `enable_thinking` | boolean | no | true | Enable adaptive model thinking before answering. Set false to request a direct answer without a reasoning phase. | | `tools` | array | no | - | OpenAI-compatible tool definitions for function calling. | | `tool_choice` | object | no | - | Optional OpenAI-compatible tool_choice value. | | `response_format` | enum | no | - | Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt. | | `web_search_linkup` | boolean | no | false | Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds \$0.013 per call when invoked on top of the model's normal token cost. Disabled by default. | | `disable_formatting` | boolean | no | false | When enabled, the gateway will not append the "Sources" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration. | ## Notes Text, image, and video input with text output. Thinking defaults to adaptive and can be disabled. Pricing is based on input tokens including cache hits: \<=512K uses the discounted standard tier, while >512K uses the high-context tier. Supports up to 1M input tokens. Linkup web search is available through web_search_linkup and adds \$0.013 per successful search. ## Variants ### `:priority` | Field | Value | | ------------------- | --------------------------------------------------------------------------------------------------------------------------------- | | Model id | `minimax-m3:priority` | | Model release date | 2026-06-01 | | Region | Singapore | | Context window | 1M | | Weight precision | - | | Max output tokens | 524,288 | | Features | reasoning, vision, video, web_search, function_calling, cache, long_context | | Native inference | No | | Structured output | JSON Mode | | Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/minimax-m3:priority:generateContent` | **Pricing** | Charge | Spec | Rate | | ------------------- | -------------------------- | --------------------------------------------------------- | | Input | per 1M prompt tokens | \<=512K \$0.3375 (was \$0.45); >512K \$0.675 (was \$0.90) | | Output | per 1M generated tokens | \<=512K \$1.35 (was \$1.80); >512K \$2.70 (was \$3.60) | | Implicit cache read | per 1M cached input tokens | \<=512K \$0.0675 (was \$0.09); >512K \$0.135 (was \$0.18) | | Web Search (Linkup) | per call when invoked | \$0.013 | **Parameters** | Parameter | Type | Required | Default | Description | | ----------------------- | ------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `temperature` | number | no | `1` | Controls randomness. Lower values are more deterministic; higher values are more exploratory. · Range: 0 – 2 | | `top_p` | number | no | `0.95` | Controls nucleus sampling by limiting generation to the most likely token mass. · Range: 0 – 1 | | `max_completion_tokens` | integer | no | `4096` | Maximum generated tokens, including reasoning tokens when thinking is enabled. · Range: 1 – 524288 | | `stop` | array | no | - | Optional stop sequence or list of stop sequences. | | `enable_thinking` | boolean | no | true | Enable adaptive model thinking before answering. Set false to request a direct answer without a reasoning phase. | | `tools` | array | no | - | OpenAI-compatible tool definitions for function calling. | | `tool_choice` | object | no | - | Optional OpenAI-compatible tool_choice value. | | `response_format` | enum | no | - | Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt. | | `web_search_linkup` | boolean | no | false | Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds \$0.013 per call when invoked on top of the model's normal token cost. Disabled by default. | | `disable_formatting` | boolean | no | false | When enabled, the gateway will not append the "Sources" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration. | **Notes** This is the priority service tier: requests receive priority admission for faster response times and improved reliability, priced above the standard MiniMax M3 route. Text, image, and video input with text output. Thinking defaults to adaptive and can be disabled. Pricing is tiered by input tokens including cache hits, with \<=512K cheaper than >512K. Supports up to 1M input tokens. Linkup web search is available through web_search_linkup and adds \$0.013 per successful search. --- *Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/minimax-m3`.