LiteLLMModels

Claude Sonnet 4 API Pricing

As of October 10, 2026, Claude Sonnet 4 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens from Databricks, the lowest of 4 providers, with cache reads at $0.30 and cache writes at $3.75 per 1M tokens. It has a 200,000-token context window and returns up to 64,000 tokens per response.

By AnthropicModel ID databricks/databricks-claude-sonnet-4Prices updated Checked
Deprecated: Databricks lists October 9, 2026 as the deprecation date for databricks/databricks-claude-sonnet-4.
Input
$3.00 / 1M tokens
Output
$15.00 / 1M tokens
Cache read
$0.30 / 1M tokens
Context window
200,000 tokens
Max output
64,000 tokens
Providers
4
Added to LiteLLM
May 2025

Claude Sonnet 4 pricing by provider

8 listings across 4 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readCache writeContext
Databricksdatabricks/databricks-claude-sonnet-4$3.00$15.00$0.30$3.75200K
Amazon Bedrocksnapshot 20250514anthropic.claude-sonnet-4-20250514-v1:0$3.00$15.00$0.30$3.751M
GMI Cloudgmi/anthropic/claude-sonnet-4$3.00$15.00––400K
Vercel AI Gatewayvercel_ai_gateway/anthropic/claude-sonnet-4$3.00$15.00$0.30$3.75200K
Amazon BedrockAPAC cross-region, snapshot 20250514apac.anthropic.claude-sonnet-4-20250514-v1:0$3.00$15.00$0.30$3.751M
Amazon BedrockEU cross-region, snapshot 20250514eu.anthropic.claude-sonnet-4-20250514-v1:0$3.00$15.00$0.30$3.751M
Amazon BedrockGlobal cross-region, snapshot 20250514global.anthropic.claude-sonnet-4-20250514-v1:0$3.00$15.00$0.30$3.751M
Amazon BedrockUS cross-region, snapshot 20250514us.anthropic.claude-sonnet-4-20250514-v1:0$3.00$15.00$0.30$3.751M

What Claude Sonnet 4 costs in practice

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

Databricks$13.50
Amazon Bedrock$13.50
GMI Cloud$13.50
Vercel AI Gateway$13.50

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

Databricks$33.00
Amazon Bedrock$33.00
GMI Cloud$33.00
Vercel AI Gateway$33.00

Claude Sonnet 4 features

Use Claude Sonnet 4 with LiteLLM

Call Claude Sonnet 4 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="databricks/databricks-claude-sonnet-4",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: claude-sonnet-4
    litellm_params:
      model: databricks/databricks-claude-sonnet-4
      # 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": "claude-sonnet-4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Claude Sonnet 4 FAQ

How much does Claude Sonnet 4 cost?

Claude Sonnet 4 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens from Databricks, the lowest of 4 providers, with cache reads at $0.30 and cache writes at $3.75 per 1M tokens.

What is the context window of Claude Sonnet 4?

Claude Sonnet 4 has a 200,000-token context window and returns up to 64,000 tokens per response.

Which providers offer Claude Sonnet 4?

Claude Sonnet 4 is available from 4 providers through LiteLLM: Databricks, Amazon Bedrock, GMI Cloud and Vercel AI Gateway. The lowest price is on Databricks.

How do I call Claude Sonnet 4 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="databricks/databricks-claude-sonnet-4", 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 Sonnet 4 support?

Claude Sonnet 4 supports function calling, structured output, image input, PDF input, reasoning, prompt caching and computer use.

When did LiteLLM add Claude Sonnet 4?

Claude Sonnet 4 was added to LiteLLM's model price file in May 2025.

Is Claude Sonnet 4 being deprecated?

Databricks deprecated databricks/databricks-claude-sonnet-4 on October 9, 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: Databricks, Amazon Bedrock, GMI Cloud, Vercel AI Gateway.

Provider pages: Databricks, Amazon Bedrock, GMI Cloud, Vercel AI Gateway.