> 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. # Qwen3.7 Max > Qwen3.7 Max is a flagship text model for coding, productivity, long-running agents, deep thinking, tools, and 1M-token context. ![Qwen3.7 Max](https://media.empiriolabs.ai/model-logos/qwen.png) [Alibaba Cloud](/providers/alibaba) · Text Generation `POST /v1/chat/completions` Qwen3.7 Max is a flagship text model for coding, productivity, long-running agents, deep thinking, tools, and 1M-token context. ## At a glance | Field | Value | | ------------------- | ------------------------------------------------------------------------------------------------------------------------- | | Model id | `qwen3-7-max` | | Model release date | 2026-05-21 | | Input modalities | Text | | Output modalities | Text | | Context window | 1M | | Weight precision | - | | Max output tokens | 65,536 | | Region | Singapore | | Features | reasoning, web\_search, code\_interpreter, function\_calling, agentic\_coding | | Native inference | No | | New | No | | Structured output | JSON Schema | | Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/qwen3-7-max:generateContent` | | Alternate model ids | `qwen3.7-max` | ## Pricing | Charge | Spec | Rate | | ---------------- | ----------------------- | ------ | | Input | per 1M prompt tokens | \$2.50 | | Output | per 1M generated tokens | \$7.50 | | Web search | per call when invoked | \$0.02 | | Web extractor | per call when invoked | \$0.02 | | Code interpreter | per call when invoked | \$0.02 | ## Example request ```bash curl https://api.empiriolabs.ai/v1/chat/completions \ -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \ -H 'Content-Type: application/json' \ -d '{"model": "qwen3-7-max", "messages": [{"role":"user","content":"Hello"}]}' ``` ## Parameters | Parameter | Type | Required | Default | Description | | ----------------------- | ------- | -------- | ---------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `temperature` | number | no | `0.7` | Sampling temperature. 0 is deterministic and 2 is maximum randomness. · Range: 0 – 2 | | `top_p` | number | no | `0.9` | Nucleus sampling probability mass. Lower values make outputs more focused. · Range: 0 – 1 | | `max_tokens` | number | no | `4096` | Maximum output tokens. · Range: 1 – 65536 | | `stop` | string | no | - | Up to 4 strings where the model will stop generating further tokens. | | `enable_thinking` | boolean | no | true | Enable reasoning before answering. | | `reasoning_effort` | enum | no | `"medium"` | Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model. · Allowed: `none`, `low`, `medium`, `high`, `max` | | `thinking_budget` | number | no | `32768` | Maximum tokens reserved for reasoning when thinking is enabled. · Range: 1 – 64000 | | `tool_web_search` | boolean | no | false | Search the web for real-time information. Adds \$0.02 to the request cost for each invoked call. | | `tool_web_extractor` | boolean | no | false | Extract and read content from URLs. Requires Web Search and Thinking. Adds \$0.02 to the request cost for each invoked call. | | `tool_code_interpreter` | boolean | no | false | Run Python code in a sandbox. Requires Thinking. Adds \$0.02 to the request cost for each invoked call. | | `disable_formatting` | boolean | no | false | Return raw provider-style output without EmpirioLabs source formatting where supported. | | `response_format` | enum | no | - | Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape. | ## Notes Text input only. Web search, web extractor, and code interpreter are optional built-in tools exposed through tool\_\* parameters. Each built-in tool call adds \$0.02 when invoked. Thinking tokens are billed as output tokens. **Per-tool billing (`usage.tool_usage`)** When this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency. ## Variants ### `:variant1` | Field | Value | | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------- | | Model id | `qwen3-7-max:variant1` | | Model release date | 2026-05-21 | | Region | China | | Context window | 1M | | Weight precision | - | | Max output tokens | 65,536 | | Features | reasoning, web\_search, code\_interpreter, function\_calling, agentic\_coding | | Native inference | No | | Structured output | JSON Schema | | Batch API | 35% off list price | | Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/qwen3-7-max:variant1:generateContent` | **Pricing** | Charge | Spec | Rate | | ---------------- | ----------------------- | -------------------- | | Input | per 1M prompt tokens | \$1.65 (was \$2.50) | | Output | per 1M generated tokens | \$4.951 (was \$7.50) | | Web search | per call when invoked | \$0.01 | | Web extractor | per call when invoked | \$0.01 | | Code interpreter | per call when invoked | \$0.01 | **Parameters** | Parameter | Type | Required | Default | Description | | ----------------------- | ------- | -------- | ---------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `temperature` | number | no | `0.7` | Sampling temperature. 0 is deterministic and 2 is maximum randomness. · Range: 0 – 2 | | `top_p` | number | no | `0.9` | Nucleus sampling probability mass. Lower values make outputs more focused. · Range: 0 – 1 | | `max_tokens` | number | no | `4096` | Maximum output tokens. · Range: 1 – 65536 | | `stop` | string | no | - | Up to 4 strings where the model will stop generating further tokens. | | `enable_thinking` | boolean | no | true | Enable reasoning before answering. | | `reasoning_effort` | enum | no | `"medium"` | Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model. · Allowed: `none`, `low`, `medium`, `high`, `max` | | `thinking_budget` | number | no | `32768` | Maximum tokens reserved for reasoning when thinking is enabled. · Range: 1 – 64000 | | `tool_web_search` | boolean | no | false | Search the web for real-time information. Adds \$0.01 to the request cost for each invoked call. | | `tool_web_extractor` | boolean | no | false | Extract and read content from URLs. Requires Web Search and Thinking. Adds \$0.01 to the request cost for each invoked call. | | `tool_code_interpreter` | boolean | no | false | Run Python code in a sandbox. Requires Thinking. Adds \$0.01 to the request cost for each invoked call. | | `disable_formatting` | boolean | no | false | Return raw provider-style output without EmpirioLabs source formatting where supported. | | `response_format` | enum | no | - | Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape. | **Notes** Text input only. Web search, web extractor, and code interpreter are optional built-in tools exposed through tool\_\* parameters. Each built-in tool call adds \$0.01 when invoked. Thinking tokens are billed as output tokens. **Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency. --- *Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/qwen3-7-max`.