Qwen3 Embedding 8B API Pricing

As of October 10, 2026, Qwen3 Embedding 8B costs $0.01 per 1M input tokens from Nebius AI Studio, the lowest of 5 providers. It has a 40,960-token context window and returns up to 40,960 tokens per response.

By AlibabaModel ID nebius/Qwen/Qwen3-Embedding-8BPrices updated October 10, 2026Checked October 10, 2026

Input: $0.01 / 1M tokens
Output: $0 / 1M tokens
Context window: 40,960 tokens
Max output: 40,960 tokens
Providers: 5
Added to LiteLLM: December 2025

Qwen3 Embedding 8B pricing by provider

5 listings across 5 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

Provider	Model name in LiteLLM	Input	Output	Context
Nebius AI Studio	`nebius/Qwen/Qwen3-Embedding-8B`	$0.01	$0	40K
Fireworks AI	`fireworks_ai/accounts/fireworks/models/qwen3-embedding-8b`	$0.10	$0	40K
LlamaGate	`llamagate/qwen3-embedding-8b`	$0.02	$0	40K
Novita AI	`novita/qwen/qwen3-embedding-8b`	$0.07	$0	32K
Scaleway	`scaleway/qwen/qwen3-embedding-8b`	$0.10	$0	–

What Qwen3 Embedding 8B costs in practice

Embedding 10,000 documents of 500 tokens each

Nebius AI Studio	$0.05
LlamaGate	$0.10
Novita AI	$0.35
Fireworks AI	$0.50

Use Qwen3 Embedding 8B with LiteLLM

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

Python SDK

from litellm import embedding

response = embedding(
    model="nebius/Qwen/Qwen3-Embedding-8B",
    input=["hello world"],
)

Proxy config.yaml

model_list:
  - model_name: qwen3-embedding-8b
    litellm_params:
      model: nebius/Qwen/Qwen3-Embedding-8B
      # credentials: see the provider's LiteLLM docs page

Call the proxy

curl http://0.0.0.0:4000/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "qwen3-embedding-8b",
    "input": "hello world"
  }'

Qwen3 Embedding 8B FAQ

How much does Qwen3 Embedding 8B cost?

Qwen3 Embedding 8B costs $0.01 per 1M input tokens from Nebius AI Studio, the lowest of 5 providers.

What is the context window of Qwen3 Embedding 8B?

Qwen3 Embedding 8B has a 40,960-token context window and returns up to 40,960 tokens per response.

Which providers offer Qwen3 Embedding 8B?

Qwen3 Embedding 8B is available from 5 providers through LiteLLM: Nebius AI Studio, Fireworks AI, LlamaGate, Novita AI and Scaleway. The lowest price is on Nebius AI Studio.

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

Use the LiteLLM Python SDK with model="nebius/Qwen/Qwen3-Embedding-8B", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/embeddings from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add Qwen3 Embedding 8B?

Qwen3 Embedding 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: Nebius AI Studio, Fireworks AI, LlamaGate, Scaleway.

Provider pages: Nebius AI Studio, Fireworks AI, LlamaGate, Novita AI, Scaleway.