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 2.0(OSI)Commercial use allowed
- Training
- finetuned
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 | Source |
|---|---|---|---|
| SWE-bench Verified | 78.8 | SWE-bench Verified | https://www.swebench.com/verified.html |
| τ-bench | 76.8 | τ-bench | https://taubench.com/ |
| Berkeley Function Calling Leaderboard v3 | 71.9 | Berkeley Function Calling Leaderboard (BFCL v3) | https://gorilla.cs.berkeley.edu/leaderboard.html |
| MultiChallenge | 41.2 | MultiChallenge | https://labs.scale.com/leaderboard/multichallenge |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(10)
Comparison and alternatives
Browse all comparisons →Show all 31 popular comparisonssorted by 7-day search impressions
Cheapest of 3 routes · OpenRouter