LiteLLMModels

Qwen3 8B API Pricing

As of October 10, 2026, Qwen3 8B costs $0.04 per 1M input tokens and $0.14 per 1M output tokens from LlamaGate, the lowest of 3 providers. It has a 32,768-token context window and returns up to 8,192 tokens per response.

By AlibabaModel ID llamagate/qwen3-8bPrices updated Checked
Input
$0.04 / 1M tokens
Output
$0.14 / 1M tokens
Context window
32,768 tokens
Max output
8,192 tokens
Providers
3
Added to LiteLLM
July 2025

Qwen3 8B 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 LiteLLMInputOutputContext
LlamaGatellamagate/qwen3-8b$0.04$0.1432K
Fireworks AIfireworks_ai/accounts/fireworks/models/qwen3-8b$0.20$0.2040K
Novita AIfp8novita/qwen/qwen3-8b-fp8$0.035$0.138128K

What Qwen3 8B costs in practice

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

LlamaGate$0.15
Fireworks AI$0.50

Qwen3 8B features

Use Qwen3 8B with LiteLLM

Call Qwen3 8B 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="llamagate/qwen3-8b",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: qwen3-8b
    litellm_params:
      model: llamagate/qwen3-8b
      # credentials: see the provider's LiteLLM docs page
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": "qwen3-8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen3 8B FAQ

How much does Qwen3 8B cost?

Qwen3 8B costs $0.04 per 1M input tokens and $0.14 per 1M output tokens from LlamaGate, the lowest of 3 providers.

What is the context window of Qwen3 8B?

Qwen3 8B has a 32,768-token context window and returns up to 8,192 tokens per response.

Which providers offer Qwen3 8B?

Qwen3 8B is available from 3 providers through LiteLLM: LlamaGate, Fireworks AI and Novita AI. The lowest price is on LlamaGate.

How do I call Qwen3 8B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="llamagate/qwen3-8b", 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 8B support?

Qwen3 8B supports function calling, structured output and reasoning.

When did LiteLLM add Qwen3 8B?

Qwen3 8B was added to LiteLLM's model price file in July 2025.

Sources

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

LiteLLM docs: LlamaGate, Fireworks AI.

Provider pages: LlamaGate, Fireworks AI, Novita AI.