Qwen3.5 35B A3B
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency.
Qwen3.5-35B-A3BReleased 25 Feb 2026 (Feb 2026)Pricing
List prices at DeepInfra, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.14 | $1.00 | |
| Cached input 64% off input | $0.05 | 64% off input |
What it costs a month
At DeepInfra list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$109
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$81.60
- Coding agent1,000 requests a day, 40K in / 2K out, cached$152
- Overnight batch20,000 requests a day, 4K in / 0.4K out$576
Where to run it
5 hosts serve Qwen3.5 35B A3B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
EmpirioLabs AICloud qwen3-5-35b-a3b | $0.057 / $0.459 −56% vs headline | qwen3-5-35b-a3b | |
DeepInfraInference Qwen3.5-35B-A3B | $0.14 / $1.00 | Qwen3.5-35B-A3B | |
W&B InferenceInference Qwen3.5-35B-A3B | $0.25 / $1.25 +41% vs headline | Qwen3.5-35B-A3B | |
GMI CloudInference Qwen3.5-35B-A3B | $0.25 / $2.00 +94% vs headline | Qwen3.5-35B-A3B | |
Novita AIInference qwen3.5-35b-a3b | $0.25 / $2.00 +94% vs headline | qwen3.5-35b-a3b |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: Apache-2.0Runs in about 86.3 GB of GPU memoryRuntimes: Ollama, SGLang, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
- EmpirioLabs AI56% lessqwen3-5-35b-a3b$0.057 / $0.459
Smaller Alibaba Qwen models
No cheaper Alibaba Qwen model keeps its key capabilities.
Other frontier labs
- 44% less
- 44% less
- 26% less
Open-weight picks
- 1% less
- 27% less
- 29% less
- 50% less
Model line
Newer and older versions, at each lab's own price.
- Apr 2026Qwen3.6 35B A3BLatest$0.10 / $0.89
- Feb 2026Qwen3.5 35B A3BThis page$0.14 / $1.00
Call it
Using DeepInfra's API.
from litellm import completion
response = completion(
model="deepinfra/Qwen3.5-35B-A3B",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Qwen3.5 35B A3B cost?
On DeepInfra, Qwen3.5 35B A3B costs $0.14 per million input tokens and $1.00 per million output tokens. Cached input costs $0.05 per million tokens. The cheapest host is EmpirioLabs AI, at $0.057 per million input tokens and $0.459 per million output tokens.
Which APIs offer Qwen3.5 35B A3B?
Qwen3.5 35B A3B runs on 5 APIs: EmpirioLabs AI, DeepInfra, W&B Inference, GMI Cloud and Novita AI.
What is Qwen3.5 35B A3B's context window?
262K tokens, with up to 262K tokens in one reply.
Is Qwen3.5 35B A3B being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Qwen3.5 35B A3B?
Yes. Qwen3.6 35B A3B is the newest model in this line, released on 27 Apr 2026.
What are cheaper alternatives to Qwen3.5 35B A3B?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (44% less), GPT-6 Luna on OpenAI (44% less) and Muse Glimmer 30B on EmpirioLabs AI (1% less). Qwen3.5 35B A3B itself costs 56% less on EmpirioLabs AI. Savings are on a mix of 3 input tokens to 1 output token.
When was Qwen3.5 35B A3B released?
Alibaba Qwen released it on 25 Feb 2026.
What is Qwen3.5 35B A3B's API model id?
Use Qwen3.5-35B-A3B with DeepInfra. Other hosts use their own ids: qwen3-5-35b-a3b on EmpirioLabs AI, qwen3.5-35b-a3b on Novita AI.
Sources
- DeepInfra pricing
- GMI Cloud pricing
- W&B Inference pricing
- EmpirioLabs AI pricing
- Novita AI pricing
- LiteLLM model map
Raw catalog entry for Qwen3.5-35B-A3B on DeepInfra
{
"max_output_tokens": 262144,
"max_input_tokens": 262144,
"input_cost_per_token": 1.4e-7,
"output_cost_per_token": 0.000001,
"cache_read_input_token_cost": 5e-8,
"supports_prompt_caching": true,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_vision": true,
"source": "https://deepinfra.com/pricing"
}