Qwen3.7 Flash | EmpirioLabs AI Docs

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	Yes
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 request when enabled	$0.03
Image Search	per call	$0.03

Example request

$ 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	`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 – 131072
`vl_high_resolution_images`	boolean	no	true	Use higher resolution processing for image inputs.
`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	true	Search the web for real-time information. Adds $0.03 to the request cost for each invoked call.
`tool_web_extractor`	boolean	no	true	Extract and read content from URLs. Requires Web Search and Thinking.
`tool_code_interpreter`	boolean	no	true	Run Python code in a sandbox. Requires Thinking.
`tool_web_search_image`	boolean	no	true	Search the web for images from text descriptions. Adds $0.03 to the request cost for each invoked call.
`tool_image_search`	boolean	no	true	Find similar images from an uploaded image. Adds $0.03 to the request cost for each invoked call.
`response_format`	enum	no	-	Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.
`disable_formatting`	boolean	no	false	Return raw provider-style output without EmpirioLabs source formatting where supported.

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
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 $0.028 (was $0.03); 32K-256K $0.083 (was $0.10); 256K-1M $0.165 (was $0.20)
Output	per 1M generated tokens	<=32K $0.11 (was $0.13); 32K-256K $0.33 (was $0.40); 256K-1M $0.66 (was $0.80)
Implicit cache read	per 1M cached input tokens	<=32K $0.006; 32K-256K $0.017 (was $0.02); 256K-1M $0.033 (was $0.04)
Web search	per request when enabled	$0.01
Image Search	per call	$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 – 131072
`vl_high_resolution_images`	boolean	no	true	Use higher resolution processing for image inputs.
`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	true	Search the web for real-time information. Adds $0.01 to the request cost for each invoked call.
`tool_web_extractor`	boolean	no	true	Extract and read content from URLs. Requires Web Search and Thinking.
`tool_code_interpreter`	boolean	no	true	Run Python code in a sandbox. Requires Thinking.
`tool_web_search_image`	boolean	no	true	Search the web for images from text descriptions. Adds $0.01 to the request cost for each invoked call.
`tool_image_search`	boolean	no	true	Find similar images from an uploaded image. Adds $0.01 to the request cost for each invoked call.
`response_format`	enum	no	-	Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.
`disable_formatting`	boolean	no	false	Return raw provider-style output without EmpirioLabs source formatting where supported.

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)

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/qwen3-7-flash.