> 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 Flash > Fast Qwen3.7 vision-language model for text, image, video, tool use, and agentic tasks, with implicit caching and a 1M token context. ![Qwen3.7 Flash](https://media.empiriolabs.ai/model-logos/qwen.png) [Alibaba Cloud](/providers/alibaba) · Text Generation `POST /v1/chat/completions` Fast Qwen3.7 vision-language model for text, image, video, tool use, and agentic tasks, with implicit caching and a 1M token context. ## At a glance | Field | Value | | ------------------- | --------------------------------------------------------------------------------------------------------------------------- | | Model id | `qwen3-7-flash` | | Model release date | 2026-07-15 | | Input modalities | Text, Image, Video | | Output modalities | Text | | Context window | 1M | | Weight precision | - | | Max output tokens | 65,536 | | Region | Singapore | | Features | reasoning, vision, video, web_search, code_interpreter, function_calling, prefix_continuation, cache, agentic_coding | | Native inference | No | | New | No | | Structured output | JSON Mode | | Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/qwen3-7-flash:generateContent` | | Alternate model ids | `qwen3.7-flash` | ## Pricing | Charge | Spec | Rate | | --------------------- | -------------------------- | ----------------------------------------------- | | Input | per 1M prompt tokens | \<=32K \$0.03; 32K-256K \$0.10; 256K-1M \$0.20 | | Output | per 1M generated tokens | \<=32K \$0.13; 32K-256K \$0.40; 256K-1M \$0.80 | | Implicit cache read | per 1M cached input tokens | \<=32K \$0.006; 32K-256K \$0.02; 256K-1M \$0.04 | | Web search | per call when invoked | \$0.03 | | Text-to-image search | per call when invoked | \$0.03 | | Image-to-image search | per call when invoked | \$0.03 | | Web extractor | per call when invoked | \$0.00 | | Code interpreter | per call when invoked | \$0.00 | ## 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-flash", "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 | - | Maximum output tokens. When omitted, the model's own default applies. · 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. A request that forces a tool call runs without reasoning unless it sets enable_thinking. | | `reasoning_effort` | enum | no | - | 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 | - | Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason. · Range: 1 – 131072 | | `vl_high_resolution_images` | boolean | no | true | Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses. | | `max_pixels` | number | no | `2621440` | Maximum pixel count per image when high resolution processing is disabled. · Range: 4096 – 16777216 | | `video_fps` | number | no | `2` | Frames per second to sample from video inputs. · Range: 0.1 – 10 | | `treat_images_as_video` | boolean | no | false | Treat a sequence of images as video frames. | | `tool_web_search` | boolean | no | false | Search the web for real-time information. Adds \$0.03 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input. | | `tool_web_extractor` | boolean | no | false | Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input. | | `tool_code_interpreter` | boolean | no | false | Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input. | | `tool_web_search_image` | boolean | no | false | Search the web for images from text descriptions. Adds \$0.03 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input. | | `tool_image_search` | boolean | no | false | Find similar images from an uploaded image. Adds \$0.03 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input. | | `disable_formatting` | boolean | no | false | Return the answer without EmpirioLabs formatting: citations stay as plain \[N] markers and no References block is added. Applies to streamed responses that use a built-in tool. | | `response_format` | enum | no | - | Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt. | ## Notes Token pricing is tiered by prompt size and steps up above 32K and again above 256K input tokens. Cached prompt tokens are billed at the implicit cache rate for the matching tier. Web Search, Text-to-Image Search, and Image-to-Image Search are billed only when invoked. Text-to-Image Search and Image-to-Image Search use the Image Search pricing row. 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-flash:variant1` | | Model release date | 2026-07-15 | | Region | China | | Context window | 1M | | Weight precision | - | | Max output tokens | 65,536 | | Features | reasoning, vision, video, web_search, code_interpreter, function_calling, prefix_continuation, cache, agentic_coding | | Native inference | No | | Structured output | JSON Mode | | Batch API | 35% off list price | | Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/qwen3-7-flash:variant1:generateContent` | **Pricing** | Charge | Spec | Rate | | --------------------- | -------------------------- | ---------------------------------------------------------------------------------- | | Input | per 1M prompt tokens | \<=32K ~~\$0.03~~ \$0.028; 32K-256K ~~\$0.10~~ \$0.083; 256K-1M ~~\$0.20~~ \$0.165 | | Output | per 1M generated tokens | \<=32K ~~\$0.13~~ \$0.11; 32K-256K ~~\$0.40~~ \$0.33; 256K-1M ~~\$0.80~~ \$0.66 | | Implicit cache read | per 1M cached input tokens | \<=32K \$0.006; 32K-256K ~~\$0.02~~ \$0.017; 256K-1M ~~\$0.04~~ \$0.033 | | Web search | per call when invoked | \$0.01 | | Text-to-image search | per call when invoked | \$0.01 | | Image-to-image search | per call when invoked | \$0.01 | | Web extractor | per call when invoked | \$0.00 | | Code interpreter | per call when invoked | \$0.00 | **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 | - | Maximum output tokens. When omitted, the model's own default applies. · 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. A request that forces a tool call runs without reasoning unless it sets enable_thinking. | | `reasoning_effort` | enum | no | - | 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 | - | Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason. · Range: 1 – 131072 | | `vl_high_resolution_images` | boolean | no | true | Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses. | | `max_pixels` | number | no | `2621440` | Maximum pixel count per image when high resolution processing is disabled. · Range: 4096 – 16777216 | | `video_fps` | number | no | `2` | Frames per second to sample from video inputs. · Range: 0.1 – 10 | | `treat_images_as_video` | boolean | no | false | Treat a sequence of images as video frames. | | `tool_web_search` | boolean | no | false | Search the web for real-time information. Adds \$0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input. | | `tool_web_extractor` | boolean | no | false | Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input. | | `tool_code_interpreter` | boolean | no | false | Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input. | | `tool_web_search_image` | boolean | no | false | Search the web for images from text descriptions. Adds \$0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input. | | `tool_image_search` | boolean | no | false | Find similar images from an uploaded image. Adds \$0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input. | | `disable_formatting` | boolean | no | false | Return the answer without EmpirioLabs formatting: citations stay as plain \[N] markers and no References block is added. Applies to streamed responses that use a built-in tool. | | `response_format` | enum | no | - | Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt. | **Notes** China pricing is discounted versus Singapore. Token pricing is tiered by prompt size and steps up above 32K and again above 256K input tokens. Implicit cache input uses the cached-token row. Web Search, Text-to-Image Search, and Image-to-Image Search are billed only when invoked. Text-to-Image Search and Image-to-Image Search use the Image Search pricing row. China paid tool calls are \$0.01 each. 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. --- *Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/qwen3-7-flash`.