LiteLLMModels

Qwen3 Reranker 8B API Pricing

As of October 10, 2026, Qwen3 Reranker 8B costs $0.05 per 1M tokens from Novita AI, the lowest of 2 providers. It has a 32,768-token context window and returns up to 4,096 tokens per response.

By AlibabaModel ID novita/qwen/qwen3-reranker-8bPrices updated Checked
Input
$0.05 / 1M tokens
Output
$0.05 / 1M tokens
Context window
32,768 tokens
Max output
4,096 tokens
Providers
2
Added to LiteLLM
December 2025

Qwen3 Reranker 8B pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputContext
Novita AInovita/qwen/qwen3-reranker-8b$0.05$0.0532K
Fireworks AIfireworks_ai/accounts/fireworks/models/qwen3-reranker-8b$0.20$040K

Use Qwen3 Reranker 8B with LiteLLM

Call Qwen3 Reranker 8B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/rerank. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="novita/qwen/qwen3-reranker-8b",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: qwen3-reranker-8b
    litellm_params:
      model: novita/qwen/qwen3-reranker-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-reranker-8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen3 Reranker 8B FAQ

How much does Qwen3 Reranker 8B cost?

Qwen3 Reranker 8B costs $0.05 per 1M tokens from Novita AI, the lowest of 2 providers.

What is the context window of Qwen3 Reranker 8B?

Qwen3 Reranker 8B has a 32,768-token context window and returns up to 4,096 tokens per response.

Which providers offer Qwen3 Reranker 8B?

Qwen3 Reranker 8B is available from 2 providers through LiteLLM: Novita AI and Fireworks AI. The lowest price is on Novita AI.

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

Use the LiteLLM Python SDK with model="novita/qwen/qwen3-reranker-8b", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/rerank from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add Qwen3 Reranker 8B?

Qwen3 Reranker 8B was added to LiteLLM's model price file in December 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. Provider pricing pages:

LiteLLM docs: Fireworks AI.

Provider pages: Novita AI, Fireworks AI.