Qwen3.5-9B
Qwen3.5-9B 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
- Qwen3.5
- Released
- 2026-03-02
- Context
- 262k
- Parameters
- 9B
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Unknown
- Code
- Unknown
- Training
- Pretrained
Cheapest of 3 routes · Alibaba Cloud PAI-EAS
About
Qwen3.5-9B is Alibaba's Qwen3.5 model with multimodal text and image input. It offers a 256K-token context window with weights openly available for self-hosting.
Qwen3.5-9B is an open-source model in the Qwen3.5 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 Together AI, OpenRouter, and Alibaba Cloud PAI-EAS, with the cheapest tracked route listed at $0.1 input and $0.15 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 81.7, MMLU PRO 82.5, and Berkeley Function Calling Leaderboard v3 66.1.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ A1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ A2 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 | Route |
|---|---|---|---|
| Alibaba Cloud PAI-EAS | $0.100 | $0.150 | Serverless |
| OpenRouter | $0.100 | $0.150 | Serverless |
| Together AI | $0.100 | $0.150 | Serverless |
Available via routers & gateways(1)
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(5)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 81.7 | diamond | https://huggingface.co/Qwen/Qwen3.5-9B |
| MMLU PRO | 82.5 | From official HuggingFace model card benchmark table (accuracy) | https://huggingface.co/Qwen/Qwen3.5-9B |
| Berkeley Function Calling Leaderboard v3 | 66.1 | BFCL-V4, from official model card (accuracy) | https://huggingface.co/Qwen/Qwen3.5-9B |
| LiveCodeBench | 65.6 | LiveCodeBench v6 (pass@1) | https://huggingface.co/Qwen/Qwen3.5-9B |
| τ-bench | 79.1 | TAU2-Bench, from official model card (accuracy) | https://huggingface.co/Qwen/Qwen3.5-9B |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(3)
Compare Qwen3.5-9B with other models
Comparison and alternatives
Browse all comparisons →Show all 55 popular comparisonssorted by 7-day search impressions
Frequently asked questions
What is the context window of Qwen3.5-9B?
Qwen3.5-9B has a context window of 262k tokens.
How much does Qwen3.5-9B cost?
Qwen3.5-9B pricing ranges from $0.1/1M to $0.10/1M input tokens depending on the provider.
When was Qwen3.5-9B released?
Qwen3.5-9B was released on 2026-03-02.
Which providers offer Qwen3.5-9B?
Qwen3.5-9B is available from 3 providers: Together AI, OpenRouter, Alibaba Cloud PAI-EAS.
What benchmarks has Qwen3.5-9B been tested on?
Qwen3.5-9B has been evaluated on 5 benchmarks, including Google-Proof Q&A, MMLU PRO, Berkeley Function Calling Leaderboard v3, LiveCodeBench, τ-bench.
Cheapest of 3 routes · Alibaba Cloud PAI-EAS