LiteLLMModels

Arctic API Pricing

Arctic is available through LiteLLM. It has a 4,096-token context window and returns up to 8,192 tokens per response.

Model ID snowflake/snowflake-arcticPrices updated Checked
Context window
4,096 tokens
Max output
8,192 tokens
Providers
1
Added to LiteLLM
March 2025

Arctic pricing by provider

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

ProviderModel name in LiteLLMContext
Snowflake Cortexsnowflake/snowflake-arctic4K

Use Arctic with LiteLLM

Call Arctic 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="snowflake/snowflake-arctic",
    messages=[{"role": "user", "content": "Hello!"}],
)
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": "arctic",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Arctic FAQ

What is the context window of Arctic?

Arctic has a 4,096-token context window and returns up to 8,192 tokens per response.

When did LiteLLM add Arctic?

Arctic was added to LiteLLM's model price file in March 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: Snowflake Cortex.

Provider pages: Snowflake Cortex.