Qwen3 4B API Pricing

Qwen3 4B 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.

What Qwen3 4B costs in practice

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

Qwen3 4B features

• Function calling
• Reasoning

Use Qwen3 4B with LiteLLM

Call Qwen3 4B 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.

from litellm import completion

response = completion(
    model="nebius/Qwen/Qwen3-4B",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: qwen3-4b
    litellm_params:
      model: nebius/Qwen/Qwen3-4B
      # credentials: see the provider's LiteLLM docs page

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "qwen3-4b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen3 4B FAQ

More Alibaba models

• Qwen3 4B Instruct 2507$0.20 / $0.20 per 1M tokens
• Qwen3.8 Omni Flash$0.15 / $0.47 per 1M tokens
• Qwen2.5 14B Instruct$0.80 / $0.80 per 1M tokens
• Qwen3.6 Max Preview$1.268 / $7.608 per 1M tokens
• Qwen35 122B A10B$0.22 / $2.20 per 1M tokens
• Qwen3.8 Flash$0.15 / $0.47 per 1M tokens
• Qwen3 14B Instruct$0.05 / $0.22 per 1M tokens
• Qwen3 Max Thinking$1.20 / $6 per 1M tokens