Qwen3.8 Max

qwen/qwen3.8-max
NewFeatured
VisionToolsJSONReasoning
by Qwen · 2026-08-03

Qwen3.8-Max is Alibaba's newest flagship model in the Qwen line and its highest-capability tier to date. Alibaba positions it directly against GPT-5.5, Claude Opus 4.7, and Gemini 3.1 Pro in its own migration guide, recommending it whenever a task needs the strongest available reasoning — complex multi-step analysis, deep logical derivation, and demanding agentic work. It is natively multimodal, listed by Alibaba under both text generation and image/video understanding: it accepts text, images, and video and returns text, with a 1M-token context window. The official capability matrix confirms full support for thinking mode, function calling, built-in tools, and structured outputs, making it a complete drop-in for agent frameworks and tool-calling pipelines. Qwen3.8-Max is served through three wire formats — OpenAI-compatible, Anthropic-compatible, and native DashScope — across Beijing, Singapore, Tokyo, Frankfurt, and Virginia. Thinking is toggled with the enable_thinking parameter (or reasoning.effort on the Responses API). It is the premium tier of the family: reach for it when correctness on hard problems outweighs cost, and drop to Qwen3.7-Plus or Qwen3.7-Flash for everyday volume.

ctx1M tokens
Inputtext + image + video
Outputtext
p50 TTFT5.03 s
INPUT$2.00/ 1M tokens
OUTPUT$6.00/ 1M tokens
p50 TTFT5.03 s7d
p95 TTFT10.00 s7d
TRAFFIC52.8Mtokens / 7d

Qwen3.8 Max is a multimodal large language model from the Qwen family, available through OrcaRouter with the model id 'qwen/qwen3.8-max'. The provider is qwen. It has a context window of 1,000,000…

What is Qwen3.8 Max?

Who is Qwen3.8 Max designed for?

What input modalities does Qwen3.8 Max support?

What does the 1,000,000-token context window mean?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
  • Anthropic SDKhttps://api.orcarouter.ai
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="qwen/qwen3.8-max",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • enable_thinking
  • include_reasoning
  • max_tokens
  • presence_penalty
  • reasoning
  • reasoning_effort
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_p

Pricing

Input / 1M tokens$2.00
Output / 1M tokens$6.00
Cache read / 1M$0.250
Cache write / 1M$2.50
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $32.00 · With prompt caching $25.88

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.003040

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
5.03 s
Output speed
53.7 tok/s
p95 TTFT
10.00 s
Error rate
0.17%

Public benchmarks

Source: Design Arena

Community buzz

What developers are saying this week

Hacker News4 mentions · 7dup 4 vs the previous week

How it compares

Qwen3.8 Maxqwen/qwen3-max-previewQwen3.5 397B A17Bqwen/qwen3.5-plus
Input $/M$2.00$0.86$0.17$0.12
Output $/M$6.00$3.44$1.03$0.69
Context1.0M262K33K1.0M
Quality9/108/108/108/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What does Qwen3.8 Max cost?
$2.00 per 1M input tokens and $6.00 per 1M output tokens, billed at the qwen provider rate with zero markup on OrcaRouter.
What is the context window of Qwen3.8 Max?
1,000,000 tokens. Input can include text, image, and video content up to that token limit.
What are the strengths of Qwen3.8 Max?
The main strengths are the 1,000,000-token context and support for text, image, and video input. No benchmark scores are listed, so verify quality on your own tasks.
How does Qwen3.8 Max compare to other models?
It has a larger context window and multimodal input versus many smaller or text-only models, but it also has a higher token price. Without benchmark scores, compare by testing on OrcaRouter.
How does OrcaRouter handle data sent to Qwen3.8 Max?
The catalog entry does not describe data handling. Review OrcaRouter's privacy policy and the qwen provider's terms before sending sensitive data.
How do I call Qwen3.8 Max via an OpenAI-compatible API?
Set the base URL to https://api.orcarouter.ai/v1 and the model id to 'qwen/qwen3.8-max', then send a chat completions request with your OrcaRouter API key.
Can Qwen3.8 Max process video?
Yes, video is listed as an input modality, along with text and image. The exact schema for video is not specified in the catalog entry, so test with OrcaRouter.
Is input caching available for Qwen3.8 Max?
Caching is not listed for this model. Assume input tokens are billed at $2.00 per 1M tokens. Check API usage metadata for cached tokens if the provider supports it.

Embed this badge

Qwen: Qwen3.8 Max$2.00/M in5029ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/qwen/qwen3.8-max" target="_blank"> <img src="https://www.orcarouter.ai/embed/qwen/qwen3.8-max.svg" alt="Qwen: Qwen3.8 Max on OrcaRouter" /> </a>
Markdown [![Qwen: Qwen3.8 Max](https://www.orcarouter.ai/embed/qwen/qwen3.8-max.svg)](https://www.orcarouter.ai/models/qwen/qwen3.8-max)

Model card as data

GET /api/public/models/qwen/qwen3.8-maxOpen
Machine-readable:/llms.txt/llms-full.txt