qwen4-max) is the flagship model in Alibaba’s Qwen4 series. Its 2.4-trillion-parameter backbone supports native text, image, and video input for complex reasoning, coding agents, long-document analysis, and professional workflows. The model is live on APIYI at the same list price as the international provider site, backed by 325 pre-release test calls and 15 release checks in the Default group.
Model name:
qwen4-max. Available in the Default, SVIP, CodexResponses, and ClaudeCode groups, with Chat Completions, Responses, and Messages endpoints open. Thinking is enabled by default; set reasoning_effort="none" for everyday chat to reduce reasoning token usage.Why this model
Provider pricing plus top-up bonuses
Input $1.50, output $4.50, cached input $0.075 per 1M tokens. Top-up bonuses of 10%–20% provide an effective rate of roughly 83–91% of list price.
Near-1M context verified
A request with 951,498 input tokens recalled markers from both the middle and end in 92.3 seconds. The reported input ceiling is 991,808 tokens.
Native multimodal input
Text, image, and video input were all tested. Image OCR and two-image identification passed across all three provider endpoints; Chat video understanding described the test footage correctly.
Complete agent tool loop
Single, parallel, forced, named, and streaming tool calls passed, along with full two-round tool-result replay.
Endpoints and groups
All three endpoints are open. These are client-specific group recommendations, not restrictions on other groups. Minimal Responses and Messages requests also passed with a Default-group token; the groups available to each token are governed by its console configuration.
Pricing
Per 1M tokens, before top-up bonuses:
Prices match the international Qwen4-Max provider site and may change. Check Model pricing for the current rate. Top-up bonuses provide an effective rate of roughly 83–91% of list price; see Top-up promotions.
Specifications and measurements
These measurements come from the pre-release test window on 2026-11-17 (UTC+8) and are not a long-term SLA.
Thinking and output budget
reasoning_effort accepts none, off, minimal, low, medium, high, xhigh, and max. Invalid values return a 400 listing the accepted set.
none/off: disable thinking for everyday chat, extraction, and high-frequency calls.minimal/low/medium: retain some reasoning; token usage may not increase monotonically on simple tasks.high/xhigh/max: produced more reasoning in testing and are better suited to complex tasks.reasoning_effortandthinking_budgetare mutually exclusive; sending both returns 400.
Code examples
Python (OpenAI SDK compatible)
Image input
video_url, or a frame sequence in {"type": "video", "video": [...]}; frame sequences require 4–80 frames.
cURL
Tool calling
Chat Completions passed pre-release tests for single and parallel tools,parallel_tool_calls=false, tool_choice="required", named tools, disabled tools, streaming tool deltas, and full two-round tool-result replay.
n > 1 together with reasoning_effort="none"; n > 1 returns 400 while thinking is enabled.
Structured output
response_format={"type": "json_schema"} passed tests for nested objects, arrays, enums, and additionalProperties: false. Streaming responses also produced valid JSON.
Context caching
- A short prefix of about 170 tokens did not hit; longer fixed prefixes produced cache reads.
- Explicit Chat
cache_controlhit 1,657 tokens on every subsequent pre-release call, and the second release check in the APIYI Default group also hit 1,657 tokens. Implicit cache hits were less consistent. - Cached input is listed at $0.075 per 1M tokens.
Parameter compatibility
The provider accepted
max_tokens=131072 and 200000 and returned short answers. This only shows that the values were not rejected; it does not verify generation at those lengths.
FAQ
Why did I get HTTP 200 with an empty answer?
Why did I get HTTP 200 with an empty answer?
Default reasoning can consume a small
max_tokens budget, leaving no visible content and a length finish reason. Disable thinking or increase the output budget, and inspect reasoning_content and finish_reason.Can I use Responses or Claude Code directly?
Can I use Responses or Claude Code directly?
Yes. Use the CodexResponses group for Responses clients and ClaudeCode for Claude Code; minimal requests on all three endpoints also passed with a Default-group token. Provider testing ignored
tool_choice="required" on Responses, so prefer a named tool or Chat for forced structured calls. Messages does not support OpenAI-style response_format and requires max_tokens; use tool calling for structured output. Validate complex Claude Code agent workflows against your client version before broad rollout.How can I reduce routine usage costs?
How can I reduce routine usage costs?
Set
reasoning_effort="none" for everyday chat and structured extraction, reuse fixed prefixes for long documents, verify cache billing in the console, and use eligible top-up bonus tiers.Can I advertise a 200K maximum output?
Can I advertise a 200K maximum output?
No. Accepting
max_tokens=200000 does not prove that 200K output was generated. This page does not assign a maximum output length based on that result.Related
- Model pricing — current prices, groups, and endpoints
- Top-up promotions — bonus tiers and effective rates
- Qwen3.8-Max overview — previous generation
- API manual — authentication, requests, and error handling
Measurements come from 325 pre-release calls on 2026-11-17 (UTC+8), plus 15 same-day release checks in the APIYI Default group covering Chat Completions, Responses, Messages, streaming, tools, JSON Schema, image, video, caching, and 32K context. Provider reference:
https://qwen.ai/blog?id=qwen4-max. Model and channel behavior may change; live responses and console billing details are the source of truth.