
Trillion-scale MoE flagship for coding, long-horizon agents, and professional work, with image and video understanding across a 1M-token context.
Trillion-scale MoE flagship for coding, long-horizon agents, and professional work, with image and video understanding across a 1M-token context.
Supports text, image, and video input, thinking mode with enable_thinking and thinking_budget up to 262144 tokens, function calling, structured output including strict JSON Schema, and five built-in tools: tool_web_search, tool_web_extractor, tool_code_interpreter, tool_web_search_image, and tool_image_search. Thinking tokens are billed as output tokens.
Also known as Alibaba Cloud Qwen3.8 Max
qwen3-8-max/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/qwen3-8-max:generateContentqwen3.8-maxLive pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.
Qwen3.8 Max serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id qwen3-8-max. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-8-max",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="qwen3-8-max",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the Qwen3.8 Max API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| temperature | number | 0.7 | 0 to 1.99 | Sampling temperature. 0 is deterministic and 1.99 is maximum randomness. |
| top_p | number | 0.9 | 0 to 1 | Nucleus sampling probability mass. Lower values make outputs more focused. |
| max_tokens | number | - | 1 to 131072 | Maximum output tokens. When omitted, the model's own default applies. |
| stop | string | - | - | Up to 4 strings where the model will stop generating further tokens. |
| enable_thinking | boolean | true | - | Enable reasoning before answering. |
| reasoning_effort | enum | - | none, low, medium, high, max | Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model. |
| thinking_budget | number | - | 1 to 262144 | Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason. |
| preserve_thinking | boolean | true | - | 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... |
| seed | integer | - | 0 to 2147483647 | Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output. |
| top_k | integer | - | 1 to 100 | Sample only from the K most likely tokens. When omitted, the model's own default applies. |
| presence_penalty | number | - | -2 to 2 | Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies. |
| repetition_penalty | number | - | 0.1 to 2 | 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... |
| n | integer | 1 | 1 to 4 | 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... |
| logprobs | boolean | 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. |
Text, image, and video input are supported. Web search, web extractor, code interpreter, text-to-image search, and image-to-image search are optional built-in tools exposed through tool_* parameters. Web search, text-to-image search, and image-to-image search add $0.02 for each invoked call; web extractor and code interpreter run at no extra cost. Web extractor requires web search, and both web extractor and code interpreter require thinking. A single request can invoke a tool more than once, and each invoked call is billed. Thinking tokens are billed as output tokens. The qwen3-8-max id always serves the current Qwen3.8 Max build and moves with Alibaba's snapshot upgrades; since September 5, 2026 it serves the qwen3-8-max-0902 snapshot. Use qwen3-8-max-0902 when output must stay pinned to that exact snapshot.
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, "code_interpreter": 1}
}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.
:variant1
Text, image, and video input are supported. Web search, web extractor, code interpreter, text-to-image search, and image-to-image search are optional built-in tools exposed through tool_* parameters. Web search, text-to-image search, and image-to-image search add $0.02 for each invoked call; web extractor and code interpreter run at no extra cost. Web extractor requires web search, and both web extractor and code interpreter require thinking. A single request can invoke a tool more than once, and each invoked call is billed. Thinking tokens are billed as output tokens. This id always serves the current Qwen3.8 Max build on the China endpoint and moves with Alibaba's snapshot upgrades. Use qwen3-8-max-0902 when output must stay pinned to the September 2, 2026 snapshot.
Variants are alternate versions of Qwen3.8 Max with their own model id. Depending on the variant, they can differ in serving region, pricing, or supported parameters; everything else works the same way.
qwen3-8-max:variant1qwen3.8-max:variant1Announcements, prompt tests, and comparisons that cover this model.
API Access How to Use the Qwen3.8 Max API Call Qwen3.8 Max, Alibaba's trillion-scale Qwen3.8 flagship with a 1M token context, deep thinking, five built-in tools,...
Guides Qwen4 Max vs Qwen3.8 Max vs Kimi K3.1 Pro vs DeepSeek V4 Pro 0813: four coding tests We gave Qwen4 Max, Qwen3.8 Max, Kimi K3.1 Pro and DeepSeek V4 Pro 0813 the same four coding prompts and measured time,...
Guides Kimi K3 vs GLM 5.3 vs Qwen3.8 Max vs DeepSeek V4 Pro: four one-shot coding tests We gave Kimi K3, GLM 5.3, Qwen3.8 Max and DeepSeek V4 Pro 0813 the same four coding prompts at max reasoning, one shot...On EmpirioLabs, Qwen3.8 Max is billed pay as you go: Input $2.00 per 1M prompt tokens; Output $6.00 per 1M generated tokens; Web search $0.02 per call when invoked; Text-to-image search $0.02 per call when invoked; Image-to-image search $0.02 per call when invoked; Web extractor $0.00 per call when invoked; Code interpreter $0.00 per call when invoked. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.
Qwen3.8 Max takes Text, Image, Video as input and returns Text.
Qwen3.8 Max supports a 983.6K-token context window with up to 131,072 output tokens per response.
Yes. Qwen3.8 Max serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to qwen3-8-max.
Send qwen3-8-max as the model in your request. The alternate IDs qwen3.8-max also work.
Alibaba Cloud released Qwen3.8 Max on Aug 3, 2026.
Qwen3.8 Max on EmpirioLabs is served from Singapore.
Qwen3.8 Max is available as 2 model ids: the default qwen3-8-max plus qwen3-8-max:variant1 (China). Variants can differ in serving region, pricing, or supported parameters; the rate cards for each are on this page.
Yes. The EmpirioLabs playground runs Qwen3.8 Max in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.
Check out our pricing or reach out if you want your own model deployed on our stack.