Qwen3.5 9B
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.
Qwen3.5-9BReleased 10 Mar 2026 (Mar 2026)Pricing
List prices at DeepInfra, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.10 | $0.15 |
What it costs a month
At DeepInfra list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$41.25
- RAG over documents2,000 requests a day, 8K in / 0.6K out$53.40
- Coding agent1,000 requests a day, 40K in / 2K out$129
- Overnight batch20,000 requests a day, 4K in / 0.4K out$276
Where to run it
4 hosts serve Qwen3.5 9B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
EmpirioLabs AICloud qwen3-5-9b | $0.09 / $0.13 −11% vs headline | qwen3-5-9b | |
DeepInfraInference Qwen3.5-9B | $0.10 / $0.15 | Qwen3.5-9B | |
Together AIInference Qwen3.5-9B | $0.17 / $0.25 +69% vs headline | Qwen3.5-9B | |
OpenInferCloud Qwen3.5-9B | $5.00 / $0.15 +3267% vs headline | Qwen3.5-9B |
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
- Open weights
- License: Apache-2.0Runs in about 23.2 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 AI11% lessqwen3-5-9b$0.09 / $0.13
Smaller Alibaba Qwen models
No cheaper Alibaba Qwen model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 11% less
- 11% less
- 16% less
- 2% less
Call it
Using DeepInfra's API.
from litellm import completion
response = completion(
model="deepinfra/Qwen3.5-9B",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Qwen3.5 9B cost?
On DeepInfra, Qwen3.5 9B costs $0.10 per million input tokens and $0.15 per million output tokens. The cheapest host is EmpirioLabs AI, at $0.09 per million input tokens and $0.13 per million output tokens.
Which APIs offer Qwen3.5 9B?
Qwen3.5 9B runs on 4 APIs: EmpirioLabs AI, DeepInfra, Together AI and OpenInfer.
What is Qwen3.5 9B's context window?
262K tokens, with up to 262K tokens in one reply.
Is Qwen3.5 9B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Qwen3.5 9B?
Models that cost less and keep most of what it can do: MiniMax M3.1 Flash on Refuseless (11% less). Qwen3.5 9B itself costs 11% less on EmpirioLabs AI. Savings are on a mix of 3 input tokens to 1 output token.
When was Qwen3.5 9B released?
Alibaba Qwen released it on 10 Mar 2026.
What is Qwen3.5 9B's API model id?
Use Qwen3.5-9B with DeepInfra. Other hosts use their own ids: qwen3-5-9b on EmpirioLabs AI.
Sources
Raw catalog entry for Qwen3.5-9B on DeepInfra
{
"max_output_tokens": 262144,
"max_input_tokens": 262144,
"input_cost_per_token": 1e-7,
"output_cost_per_token": 1.5e-7,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_response_schema": true,
"supports_vision": true,
"source": "https://deepinfra.com/pricing"
}