Qwen3.5 35B-A3B
Summary
Qwen3.5 35B-A3B is an open-weight language model from Alibaba (Qwen), released on 23 Feb 2026. It accepts text, images and video and generates text, with a 262K-token context window and up to 66K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.14 per million input tokens and $1 per million output tokens (DeepInfra), across 6 providers we track.
Qwen vision-language model for visual reasoning, documents, and agent tasks
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | 23 Feb 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 36B [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 66K tokens [models.dev] |
| Knowledge cutoff | Apr 2025 [models.dev] |
| Input | Text, images and video [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | Qwen/Qwen3.5-35B-A3B [Hugging Face] |
Qwen3.5 35B-A3B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepInfra Qwen/Qwen3.5-35B-A3B | $0.14 | $1 | $0.05 | 262K | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen3.5-35b-a3b | $0.14 | $1 | $0.05 | 262K | OpenRouter, 18 Nov 2026 |
| SiliconFlow Qwen/Qwen3.5-35B-A3B | $0.24 | $1.80 | $0.15 | 262K | models.dev, 18 Nov 2026 |
| Alibaba Cloud Model Studio qwen3.5-35b-a3b | $0.25 | $2 | – | 262K | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers Qwen/Qwen3.5-35B-A3B | $0.25 | $2 | – | 262K | models.dev, 18 Nov 2026 |
| Novita AI qwen/qwen3.5-35b-a3b | $0.25 | $2 | – | 262K | models.dev, 18 Nov 2026 |
Running Qwen3.5 35B-A3B locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 22 GB | 23 GB | 23 GB |
| Q8_0 (8-bit) | 38 GB | 39 GB | 40 GB |
| FP16 / BF16 (16-bit) | 72 GB | 73 GB | 73 GB |
At 4-bit with an 8K conversation, Qwen3.5 35B-A3B needs about 23 GB, so it fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.
Frequently asked questions
What is the context window of Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B has a context window of 262,144 tokens (262K) and can generate up to 65,536 tokens in a single response, according to models.dev.
How much does the Qwen3.5 35B-A3B API cost?
Through Alibaba Cloud Model Studio, Qwen3.5 35B-A3B costs $0.25 per million input tokens and $2 per million output tokens. The lowest listed price is $0.14 input / $1 output through DeepInfra. Prices last verified 18 Nov 2026.
Is Qwen3.5 35B-A3B open source?
Qwen3.5 35B-A3B is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3.5-35B-A3B under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen3.5 35B-A3B released?
Alibaba (Qwen) released Qwen3.5 35B-A3B on 23 Feb 2026, according to models.dev.
Which providers offer Qwen3.5 35B-A3B?
We track Qwen3.5 35B-A3B on 6 providers: DeepInfra, OpenRouter, SiliconFlow, Alibaba Cloud Model Studio, Hugging Face Inference Providers, Novita AI.
How much VRAM does Qwen3.5 35B-A3B need?
About 23 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 39 GB at 8-bit. The 4-bit model fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Mistral Small 4 | Mistral AI | 16 Mar 2026 | 262K | $0.15 | $0.60 | Open |
| Hy3 preview | Tencent (Hunyuan) | 20 Apr 2026 | 262K | $0.18 | $0.60 | Open |
| Step 3.7 Flash | StepFun | 29 May 2026 | 256K | $0.20 | $1.15 | Open |
| Jamba Mini | AI21 Labs | 8 Jan 2026 | 256K | $0.20 | $0.40 | Open |
| NVIDIA Nemotron 3 Super 120B A12B | NVIDIA | 11 Mar 2026 | 262K | $0.07 | $0.40 | Open |
| Gemma 4 31B IT | Google DeepMind | 2 Apr 2026 | 262K | $0.14 | $0.40 | Open |
Change history
- Knowledge cutoff changed from Jan 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Jan 2025
- Knowledge cutoff changed from Jan 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Jan 2025
- Knowledge cutoff changed from Jan 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Jan 2025
- Knowledge cutoff changed from Jan 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Jan 2025
- Knowledge cutoff changed from Jan 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Jan 2025
- Knowledge cutoff changed from Jan 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Jan 2025
- SiliconFlow price changed: input $0.24 → $0.24, output $1.80 → $1.80 per 1M tokens
- Knowledge cutoff changed from Jan 2025 to Apr 2025
- OpenRouter price changed: input $0.15 → $0.14, output $1 → $1 per 1M tokens
- Knowledge cutoff changed from Apr 2025 to Jan 2025
- Knowledge cutoff changed from Jan 2025 to Apr 2025
- Input modalities changed from text, image, video, audio to text, image, video
- OpenRouter price changed: input $0.08 → $0.15, output $0.75 → $1 per 1M tokens
- OpenRouter price changed: input $0.15 → $0.08, output $1 → $0.75 per 1M tokens
- OpenRouter price changed: input $0.08 → $0.15, output $0.75 → $1 per 1M tokens
- OpenRouter price changed: input $0.15 → $0.08, output $1 → $0.75 per 1M tokens
Sources
- https://openrouter.ai/qwen/qwen3.5-35b-a3b
- https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3.5-35b-a3b.toml
- https://huggingface.co/Qwen/Qwen3.5-35B-A3B
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3.5-35B-A3B.toml
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/Qwen/Qwen3.5-35B-A3B.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3.5-35B-A3B.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3.5-35b-a3b.toml