LiteLLMModels

Qwen3.5 35B A3B API Pricing

As of October 10, 2026, Qwen3.5 35B A3B costs $0.14 per 1M input tokens and $1.00 per 1M output tokens from DeepInfra, the lowest of 3 providers, with cache reads at $0.05 per 1M tokens. It has a 262,144-token context window and returns up to 65,536 tokens per response.

By AlibabaModel ID deepinfra/Qwen/Qwen3.5-35B-A3BPrices updated Checked
Input
$0.14 / 1M tokens
Output
$1.00 / 1M tokens
Cache read
$0.05 / 1M tokens
Context window
262,144 tokens
Max output
65,536 tokens
Providers
3
Added to LiteLLM
March 2026

Qwen3.5 35B A3B pricing by provider

3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readContext
DeepInfradeepinfra/Qwen/Qwen3.5-35B-A3B$0.14$1.00$0.05256K
Novita AInovita/qwen/qwen3.5-35b-a3b$0.25$2.00–256K
Weights & Biaseswandb/Qwen/Qwen3.5-35B-A3B$0.25$1.25–262K

What Qwen3.5 35B A3B costs in practice

1,000 requests with 2,000 input and 500 output tokens each

DeepInfra$0.78
Novita AI$1.50
Weights & Biases$1.125

100 long-document requests with 100,000 input and 2,000 output tokens each

DeepInfra$1.60
Novita AI$2.90
Weights & Biases$2.75

Qwen3.5 35B A3B features

Use Qwen3.5 35B A3B with LiteLLM

Call Qwen3.5 35B A3B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="deepinfra/Qwen/Qwen3.5-35B-A3B",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: qwen3.5-35b-a3b
    litellm_params:
      model: deepinfra/Qwen/Qwen3.5-35B-A3B
      api_key: os.environ/DEEPINFRA_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "qwen3.5-35b-a3b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen3.5 35B A3B FAQ

How much does Qwen3.5 35B A3B cost?

Qwen3.5 35B A3B costs $0.14 per 1M input tokens and $1.00 per 1M output tokens from DeepInfra, the lowest of 3 providers, with cache reads at $0.05 per 1M tokens.

What is the context window of Qwen3.5 35B A3B?

Qwen3.5 35B A3B has a 262,144-token context window and returns up to 65,536 tokens per response.

Which providers offer Qwen3.5 35B A3B?

Qwen3.5 35B A3B is available from 3 providers through LiteLLM: DeepInfra, Novita AI and Weights & Biases. The lowest price is on DeepInfra.

How do I call Qwen3.5 35B A3B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="deepinfra/Qwen/Qwen3.5-35B-A3B", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Qwen3.5 35B A3B support?

Qwen3.5 35B A3B supports function calling, structured output, image input, reasoning and prompt caching.

When did LiteLLM add Qwen3.5 35B A3B?

Qwen3.5 35B A3B was added to LiteLLM's model price file in March 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: DeepInfra, Weights & Biases.

Provider pages: DeepInfra, Novita AI, Weights & Biases.