LLM Reference

Qwen3.5-9B

Released
2026-03-02
Last refreshed
2026-06-15
Status
Researched 55d ago
Open sourceCommercial use: permittedMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

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
Specifications
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
Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
$0.150
Input / 1M
$0.100

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/$ A

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ A

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
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

VisionMultimodalFunction CallingTool UseStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(5)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Google-Proof Q&A81.7diamondhttps://huggingface.co/Qwen/Qwen3.5-9B
MMLU PRO82.5From official HuggingFace model card benchmark table (accuracy)https://huggingface.co/Qwen/Qwen3.5-9B
Berkeley Function Calling Leaderboard v366.1BFCL-V4, from official model card (accuracy)https://huggingface.co/Qwen/Qwen3.5-9B
LiveCodeBench65.6LiveCodeBench v6 (pass@1)https://huggingface.co/Qwen/Qwen3.5-9B
τ-bench79.1TAU2-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.

Compare Qwen3.5-9B with other models

Show all 55 popular comparisonssorted by 7-day search impressions
Qwen3.5-9B vs DeepSeek V3.129Qwen3.5-9B vs Llama 2 7B24Qwen3.5-9B vs Mistral Small 321Qwen3.5-9B vs Mistral Small 3.1 24B Instruct19Qwen3.5-9B vs Nemotron Mini Hindi 4B Instruct18Qwen3.5-9B vs MiniCPM 2B18Qwen3.5-9B vs ELYZA Japanese Llama 2 13B16Qwen3.5-9B vs Llama 3 Swallow 70B Instruct14Qwen3.5-9B vs Llama Guard 4 12B14Qwen3.5-9B vs Llama Guard 7B13Qwen3.5-9B vs Llama 3.1 NemoGuard 8B Content Safety12Qwen3.5-9B vs Nemotron Mini 4B Instruct11Qwen3.5-9B vs Together AI - Gemma 3n-e4B11Qwen3.5-9B vs Claude 3.5 Haiku11Qwen3.5-9B vs Mistral 7B v0.110Qwen3.5-9B vs Xiaomi MiMo-V2.59Qwen3.5-9B vs Phi 4 Multimodal Instruct9Qwen3.5-9B vs Mistral Medium 3 Instruct9Qwen3.5-9B vs Llama 3.1 NemoGuard 8B Topic Control8Qwen3.5-9B vs Granite Guardian 3.0 8B8Qwen3.5-9B vs GPT-4 Turbo Preview8Qwen3.5-9B vs GPT-5.1 Codex Max7Qwen3.5-9B vs Bielik 11B v2.6 Instruct6Qwen3.5-9B vs GPT-26Qwen3.5-9B vs Codex Mini Latest6Qwen3.5-9B vs Llama 3.1 Nemotron 70B Reward6Qwen3.5-9B vs Stockmark 2 100B Instruct5Qwen3.5-9B vs Teuken 7B Instruct5Qwen3.5-9B vs Llama 3.1 Nemotron Nano VL 8B v15Qwen3.5-9B vs Llama 3 Taiwan 70B Instruct5Qwen3.5-9B vs Llama 3.1 Nemotron Nano 4B v1.14Qwen3.5-9B vs Llama 2 7B Chat4Qwen3.5-9B vs Mistral Large 3 675B Instruct4Qwen3.5-9B vs Llama Guard 2 8B4Qwen3.5-9B vs Claude Instant 1.24Qwen3.5-9B vs Aquila 2 7B3Qwen3.5-9B vs GPT-13Qwen3.5-9B vs Gemma 7B Instruct3Qwen3.5-9B vs GPT-2 Medium3Qwen3.5-9B vs Kimi K2.53Qwen3.5-9B vs Dracarys Llama 3.1 70B Instruct2Qwen3.5-9B vs Seed-OSS 36B Instruct2Qwen3.5-9B vs Mistral Nemotron2Qwen3.5-9B vs Claude Instant 1.12Qwen3.5-9B vs Magistral Small 25062Qwen3.5-9B vs Marin 8B Instruct2Qwen3.5-9B vs Aquila 2 34B2Qwen3.5-9B vs Grok Build 0.12Qwen3.5-9B vs Llama 3.2 1B2Qwen3.5-9B vs Colosseum 355B Instruct1Qwen3.5-9B vs Sarvam-M Multilingual Hybrid1Qwen3.5-9B vs Mistral 7B v0.31Qwen3.5-9B vs Mistral Large 2 (2407)1Qwen3.5-9B vs Code Davinci 0011Qwen3.5-9B vs GPT-5.51

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.