Qwen3-Max
Qwen3-Max is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 262k context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- Qwen3
- Released
- 2025-04-28
- Context
- 262k
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-12
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Unknown
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 3 routes · OpenRouter
About
Alibaba's Qwen3-Max, flagship model with improved multilingual and reasoning capabilities.
Qwen3-Max is an open-source model in the Qwen3 family. The structured metadata tracks a 262k-token context window, multimodal input, function calling, tool use, and structured outputs. This page tracks provider routes through OpenRouter, Vercel AI Gateway, and Novita AI, with the cheapest tracked route listed at $0.78 input and $3.9 output per 1M tokens. Headline tracked benchmarks include SWE-bench Verified 78.8, τ-bench 76.8, and Berkeley Function Calling Leaderboard v3 71.9.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ D1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ C4 relevant benchmarks in the decision map.
Provider price ladder
Compare all 3Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| OpenRouter | $0.780 | $3.90 | - | Serverless |
| Vercel AI Gateway | $1.20 | $6.00 | read $0.240 | Serverless |
| Novita AI | $2.11 | $8.45 | - | Serverless |
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(4)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| SWE-bench Verified | 78.8 | SWE-bench VerifiedObserved 2026-04-24 | — | Source |
| τ-bench | 76.8 | τ-benchObserved 2026-04-24 | — | Source |
| Berkeley Function Calling Leaderboard v3 | 71.9 | Berkeley Function Calling Leaderboard (BFCL v3)Observed 2026-04-12 | — | Source |
| MultiChallenge | 41.2 | MultiChallengeObserved 2026-04-26 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(2)
Compare Qwen3-Max with other models
Comparison and alternatives
Browse all comparisons →Show all 31 popular comparisonssorted by 7-day search impressions
Frequently asked questions
What is the context window of Qwen3-Max?
Qwen3-Max has a context window of 262k tokens.
How much does Qwen3-Max cost?
Qwen3-Max pricing ranges from $0.78/1M to $2.11/1M input tokens depending on the provider.
When was Qwen3-Max released?
Qwen3-Max was released on 2025-04-28.
Which providers offer Qwen3-Max?
Qwen3-Max is available from 3 providers: OpenRouter, Vercel AI Gateway, Novita AI.
What benchmarks has Qwen3-Max been tested on?
Qwen3-Max has been evaluated on 4 benchmarks, including SWE-bench Verified, τ-bench, Berkeley Function Calling Leaderboard v3, MultiChallenge.
Cheapest of 3 routes · OpenRouter