LiteLLMModels

Qwen3.8 27B API Pricing

As of October 10, 2026, Qwen3.8 27B costs $0.40 per 1M input tokens and $3.00 per 1M output tokens from Weights & Biases, the lowest of 5 providers, with cache reads at $0.15 per 1M tokens. It has a 262,000-token context window and returns up to 32,768 tokens per response.

By AlibabaModel ID wandb/Qwen/Qwen3.8-27BPrices updated Checked
Input
$0.40 / 1M tokens
Output
$3.00 / 1M tokens
Cache read
$0.15 / 1M tokens
Context window
262,000 tokens
Max output
32,768 tokens
Providers
5
Added to LiteLLM
August 27, 2026

Qwen3.8 27B 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.

ProviderModel name in LiteLLMInputOutputCache readContext
Weights & Biaseswandb/Qwen/Qwen3.8-27B$0.40$3.00$0.15262K
Cerebrascerebras/qwen-3.8-27b$0.99$1.49–64K
DeepInfradeepinfra/Qwen/Qwen3.8-27B$0.40$3.00$0.04256K
Groqgroq/qwen/qwen3.8-27b$0.80$4.00–128K
Nebius AI Studionebius/Qwen/Qwen3.8-27B$0.45$3.00–256K

What Qwen3.8 27B costs in practice

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

Weights & Biases$2.30
DeepInfra$2.30
Nebius AI Studio$2.40
Groq$3.60

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

Weights & Biases$4.60
DeepInfra$4.60
Nebius AI Studio$5.10
Groq$8.80

Qwen3.8 27B features

Use Qwen3.8 27B with LiteLLM

Call Qwen3.8 27B 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="wandb/Qwen/Qwen3.8-27B",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: qwen3.8-27b
    litellm_params:
      model: wandb/Qwen/Qwen3.8-27B
      # 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": "qwen3.8-27b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen3.8 27B FAQ

How much does Qwen3.8 27B cost?

Qwen3.8 27B costs $0.40 per 1M input tokens and $3.00 per 1M output tokens from Weights & Biases, the lowest of 5 providers, with cache reads at $0.15 per 1M tokens.

What is the context window of Qwen3.8 27B?

Qwen3.8 27B has a 262,000-token context window and returns up to 32,768 tokens per response.

Which providers offer Qwen3.8 27B?

Qwen3.8 27B is available from 5 providers through LiteLLM: Weights & Biases, Cerebras, DeepInfra, Groq and Nebius AI Studio. The lowest price is on Weights & Biases.

How do I call Qwen3.8 27B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="wandb/Qwen/Qwen3.8-27B", 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 Qwen3.8 27B support?

Qwen3.8 27B supports function calling, parallel tool calls, structured output, image input, reasoning and prompt caching.

When did LiteLLM add Qwen3.8 27B?

Qwen3.8 27B was added to LiteLLM's model price file on August 27, 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: Weights & Biases, Cerebras, DeepInfra, Groq, Nebius AI Studio.

Provider pages: Weights & Biases, Cerebras, DeepInfra, Groq, Nebius AI Studio.