Qwen3.8 Omni Flash

POST /v1/chat/completions

Omni-modal reasoner that reads text, images, audio, and video and answers in text, with a 1M token context, thinking, and native web search.

At a glance

Field	Value
Model id	`qwen3-8-omni-flash`
Model release date	2026-09-17
Input modalities	Text, Image, Audio, Video
Output modalities	Text
Context window	1.01M
Weight precision	-
Max output tokens	131,072
Region	Singapore
Features	reasoning, vision, audio_in, video, web_search, function_calling, structured_output
Native inference	No
New	Yes
Structured output	JSON Schema
Supported endpoints	`POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/qwen3-8-omni-flash:generateContent`
Alternate model ids	`qwen3.8-omni-flash`

Pricing

Charge	Spec	Rate
Input	per 1M prompt tokens	$0.30
Output	per 1M generated tokens	$0.94
Web search	per call when invoked	$0.02

Example request

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "qwen3-8-omni-flash", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

Parameter	Type	Required	Default	Description
`temperature`	number	no	`0.7`	Sampling temperature. 0 is deterministic and 1.99 is maximum randomness. · Range: 0 – 1.99
`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 – 131072
`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 – 262144
`preserve_thinking`	boolean	no	false	Include the reasoning of earlier assistant turns in the model’s input on /v1/chat/completions. Return each turn’s reasoning unchanged in that assistant message’s reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.
`seed`	integer	no	-	Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output. · Range: 0 – 2147483647
`top_k`	integer	no	-	Sample only from the K most likely tokens. When omitted, the model’s own default applies. · Range: 1 – 100
`presence_penalty`	number	no	-	Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model’s own default applies. · Range: -2 – 2
`repetition_penalty`	number	no	-	Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model’s own default applies. Not available when a built-in tool is on, or on /v1/responses. · Range: 0.1 – 2
`n`	integer	no	`1`	Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed. · Range: 1 – 4
`logprobs`	boolean	no	false	Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.
`top_logprobs`	integer	no	`0`	Return up to this many most likely alternatives for each answer token. Needs logprobs set to true. · Range: 0 – 5
`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 $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.
`parallel_tool_calls`	boolean	no	-	Allow multiple tool calls in a single assistant turn. When omitted, the model’s own default applies.
`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	-	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, image, audio, and video input are supported, and the model replies in text. Thinking is on by default; use enable_thinking to turn it off and thinking_budget to cap it at up to 262144 tokens. Thinking tokens are billed as output tokens. Web search is an optional built-in tool exposed through tool_web_search and adds $0.02 for each invoked call; a single request can invoke it more than once, and each invoked call is billed. For audio input, pass the file as a URL or a base64 data URI. A video’s soundtrack is billed as audio tokens alongside its video 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:

"usage": {
  "prompt_tokens": 123,
  "completion_tokens": 456,
  "cost_usd": 0.0042,
  "tool_usage": {"web_search": 3}
}

Tool counts are already factored into cost_usd and are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/qwen3-8-omni-flash.