Qwen-Max
Alibaba DashScope chatQwen-Max is an Alibaba DashScope chat model.It supports a 30,720-token context windowwith up to 8,192 output tokens.Input is priced at $1.60/M tokens and output at $6.40/M tokens. Capabilities include function calling, reasoning. Route Qwen-Max via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
Estimate Qwen-Max spend
Pick a workload, fine-tune the sliders, and see the monthly bill.
Estimate uses $1.60/M input · $6.40/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.
Pricing
Per-token rates, expressed in USD per 1M tokens. Verified Oct 22, 2026.
| Input | $1.60/M | |
| Output | $6.40/M | |
| Blended (3:1 in:out) | $2.80/M Cross-model comparable price |
Context & limits
- Context window
- 30,720 tokens
- Max input
- 30,720 tokens
- Max output
- 8,192 tokens
- Modalities
- text
Capabilities
- Function calling ✓ supported
- Parallel tool calls — not advertised
- Vision input — not advertised
- Audio input — not advertised
- Audio output — not advertised
- PDF input — not advertised
- Streaming ✓ supported
- Structured output — not advertised
- Prompt caching — not advertised
- Reasoning ✓ supported
Strengths & caveats — when to pick Qwen-Max
Data-driven from Qwen-Max's percentile within chat peers.
Where it's strong
- +multi-step reasoning and analysis tasks
- +agentic workflows that depend on reliable tool calls
Watch out for
- !limited context — 30,720-token window is in the bottom quartile; not ideal for long documents or large RAG
- !strict structured output — no JSON-schema enforcement, expect retry loops
Benchmark scores
Reported public benchmark numbers. Each row links to the source. Faded bar shows 6-peer average for context.
Call Qwen-Max via Agent Command Center
One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.
agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.# Qwen-Max via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC
client = AgentCC(
api_key=os.environ["AGENTCC_API_KEY"], # from app.futureagi.com → Settings → API Keys
base_url="https://gateway.futureagi.com/v1",
)
resp = client.chat.completions.create(
model="dashscope/qwen-max",
messages=[{"role": "user", "content": "Hello, Qwen-Max!"}],
)
print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")
# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
model="dashscope/qwen-max",
messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost: ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache: ", raw.headers.get("x-agentcc-cache"))AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗Advanced: fallback + cache config (YAML) ▸
strategy: cost-optimized
targets:
- model: qwen-max
provider: dashscope
weight: 80
fallbacks:
- model: qwen-plus-2025-07-14
provider: dashscope
- model: qwen-plus-2025-04-28
provider: dashscope
guardrails: [pii, prompt-injection, secrets]
cache: { exact: true, semantic: true } Explore similar models
Grouped by Chatbot Arena tier (Qwen-Max sits at 1318 ELO). Side-by-side links appear where a comparison page exists; otherwise, open the model profile.
- Qwen-Plus (2025-07-14)Alibaba DashScope · $0.400/M in · $1.20/M out · 129,024 ctxView model →
- Qwen-Turbo (2025-04-28)Alibaba DashScope · $0.0500/M in · $0.200/M out · 1,000,000 ctxView model →
- Qwen3.8 FlashAlibaba DashScope · $0.150/M in · $0.470/M out · 991,808 ctxView model →
- Qwen3.8 MaxAlibaba DashScope · $2.00/M in · $6.00/M out · 991,808 ctxView model →
Arena ELO within −25, ≤70% of price
- Claude 3.5 Sonnet latestAnthropic · $3.00/M in · $15.00/M out · 200,000 ctxView model →
- Claude 3.5 Sonnet (2024-10-22)Anthropic · $3.00/M in · $15.00/M out · 200,000 ctxView model →
- Gemini 2.0 FlashGoogle AI · $0.1000/M in · $0.400/M out · 1,048,576 ctxView model →
- DeepSeek V3Azure AI Foundry · $1.14/M in · $4.56/M out · 128,000 ctxView model →
≥30 ELO higher
- Gemini 4 ArgonGoogle AI · $2.00/M in · $10.00/M out · 1,048,576 ctxView model →
- Claude Opus 5.5Azure AI Foundry · $4.00/M in · $20.00/M out · 1,000,000 ctxView model →
- Claude Fable 5Azure AI Foundry · $10.00/M in · $50.00/M out · 1,000,000 ctxView model →
- Claude Fable 5.1Azure AI Foundry · $10.00/M in · $50.00/M out · 1,000,000 ctxView model →
25–100 ELO lower, ≤50% of price
FAQ
How much does Qwen-Max cost?
Input is priced at $1.60 per 1M tokens and output at $6.40 per 1M tokens (Alibaba DashScope, last verified Oct 22, 2026).
What is the context window of Qwen-Max?
Qwen-Max supports a 30,720-token context window with up to 8,192 output tokens.
Does Qwen-Max support function calling?
Yes — Qwen-Max supports function (tool) calling.
Is Qwen-Max good for production?
Qwen-Max is well-suited for multi-step reasoning and analysis tasks and agentic workflows that depend on reliable tool calls. Consider alternatives if you need limited context — 30,720-token window is in the bottom quartile; not ideal for long documents or large RAG.
How can I route to Qwen-Max with fallback?
Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.
Useful links for Qwen-Max
Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.
Third-party evals — verify the marketing.
Cross-check our number against the rest of the ecosystem.