Claude 4 Sonnet API Pricing
As of October 10, 2026, Claude 4 Sonnet costs $3.00 per 1M input tokens and $15.00 per 1M output tokens from Snowflake Cortex, the lowest of 5 providers, with cache reads at $0.30 per 1M tokens. It has a 200,000-token context window and returns up to 16,384 tokens per response.
- Input
- $3.00 / 1M tokens
- Output
- $15.00 / 1M tokens
- Cache read
- $0.30 / 1M tokens
- Context window
- 200,000 tokens
- Max output
- 16,384 tokens
- Providers
- 5
- Added to LiteLLM
- June 2025
Claude 4 Sonnet 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 | Cache read | Cache write | Context |
|---|---|---|---|---|---|---|
| Snowflake Cortex | snowflake/claude-4-sonnet | $3.00 | $15.00 | $0.30 | – | 200K |
| DeepInfra | deepinfra/anthropic/claude-4-sonnet | $3.30 | $16.50 | – | – | 200K |
| Heroku | heroku/claude-4-sonnet | – | – | – | – | 200K |
| Replicate | replicate/anthropic/claude-4-sonnet | $3.00 | $15.00 | – | – | – |
| Vercel AI Gateway | vercel_ai_gateway/anthropic/claude-4-sonnet | $3.00 | $15.00 | $0.30 | $3.75 | 200K |
What Claude 4 Sonnet costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Snowflake Cortex | $13.50 |
| Replicate | $13.50 |
| Vercel AI Gateway | $13.50 |
| DeepInfra | $14.85 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Snowflake Cortex | $33.00 |
| Replicate | $33.00 |
| Vercel AI Gateway | $33.00 |
| DeepInfra | $36.30 |
Claude 4 Sonnet features
- Function calling
- Parallel tool calls
- Structured output
- Image input
- Prompt caching
Use Claude 4 Sonnet with LiteLLM
Call Claude 4 Sonnet 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.
from litellm import completion
response = completion(
model="snowflake/claude-4-sonnet",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: claude-4-sonnet
litellm_params:
model: snowflake/claude-4-sonnet
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "claude-4-sonnet",
"messages": [{"role": "user", "content": "Hello!"}]
}'Claude 4 Sonnet FAQ
How much does Claude 4 Sonnet cost?
Claude 4 Sonnet costs $3.00 per 1M input tokens and $15.00 per 1M output tokens from Snowflake Cortex, the lowest of 5 providers, with cache reads at $0.30 per 1M tokens.
What is the context window of Claude 4 Sonnet?
Claude 4 Sonnet has a 200,000-token context window and returns up to 16,384 tokens per response.
Which providers offer Claude 4 Sonnet?
Claude 4 Sonnet is available from 5 providers through LiteLLM: Snowflake Cortex, DeepInfra, Heroku, Replicate and Vercel AI Gateway. The lowest price is on Snowflake Cortex.
How do I call Claude 4 Sonnet with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="snowflake/claude-4-sonnet", 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 Claude 4 Sonnet support?
Claude 4 Sonnet supports function calling, parallel tool calls, structured output, image input and prompt caching.
When did LiteLLM add Claude 4 Sonnet?
Claude 4 Sonnet was added to LiteLLM's model price file in June 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, DeepInfra, Heroku, Replicate, Vercel AI Gateway.
Provider pages: Snowflake Cortex, DeepInfra, Heroku, Replicate, Vercel AI Gateway.