Back to Models

Qwen3 Max

qwenqwen/qwen3-max

API guide

Chat completion

Use Qwen3-Max through TheRouter's OpenAI-compatible Chat Completions endpoint for difficult text, coding, and agent prompts.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-max",
    "messages": [{"role": "user", "content": "Summarize this vendor contract and list risky clauses."}],
    "temperature": 0.2,
    "top_p": 0.8,
    "max_tokens": 4096
  }'

Function calling

Alibaba marks qwen3-max as function-calling capable. Through TheRouter, use standard OpenAI tool schemas and execute returned tool calls in your application.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-max",
    "messages": [{"role": "user", "content": "Check whether the customer account has an overdue invoice."}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "lookup_account",
        "description": "Look up customer billing status by account id.",
        "parameters": {
          "type": "object",
          "properties": {"account_id": {"type": "string"}},
          "required": ["account_id"]
        }
      }
    }]
  }'

Structured JSON

Use response_format for extraction and classification tasks that must return machine-readable JSON.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-max",
    "messages": [{"role": "user", "content": "Return JSON with risk_level and reasons for this contract clause."}],
    "response_format": {"type": "json_object"}
  }'

Streaming

Stream long answers and agent traces so users see progress before the full 256K-context response completes.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-max",
    "stream": true,
    "messages": [{"role": "user", "content": "Write a phased reliability review for this incident timeline."}]
  }'
Fact ledger β€” every claim on this page traces here
sourceURLretrieved
Stable aliaswww.alibabacloud.com β†—2026-07-30verified
Available snapshotswww.alibabacloud.com β†—2026-07-30verified
Architecturewww.alibabacloud.com β†—2026-07-30verified
Pretraining datawww.alibabacloud.com β†—2026-07-30verified
Context windowwww.alibabacloud.com β†—2026-07-30verified
Max outputgithub.com β†—2026-07-30verified
Thinking modewww.alibabacloud.com β†—2026-07-30verified
API capabilitieswww.alibabacloud.com β†—2026-07-30verified
TheRouter price bandswww.alibabacloud.com β†—2026-07-30verified
Licenseβ€”β€”verified
SWE-bench Verifiedalibabacloud.com β†—2026-07-30verified
Tau2-Benchalibabacloud.com β†—2026-07-30verified
LMArena Text Arenaalibabacloud.com β†—2026-07-30to verify
AIME 25 / HMMTalibabacloud.com β†—2026-07-30to verify
qwen3-max stable alias advances to the January 2026 snapshotalibabacloud.com β†—2026-07-30verified
Qwen3-Max launches as Alibaba's trillion-parameter Qwen flagshipalibabacloud.com β†—2026-07-30verified
Is qwen/qwen3-max the same as Qwen3-Max-Instruct?www.alibabacloud.com β†—2026-07-30to verify
Does qwen/qwen3-max support thinking mode on TheRouter?www.alibabacloud.com β†—2026-07-30to verify
How much context does qwen/qwen3-max support?www.alibabacloud.com β†—2026-07-30to verify
Should I choose qwen3-max or qwen3.7-max?www.alibabacloud.com β†—2026-07-30to verify
Help & contact