Claude 3.5 Sonnet API Pricing

As of October 10, 2026, Claude 3.5 Sonnet costs $3.00 per 1M input tokens and $15.00 per 1M output tokens from Snowflake Cortex, the lowest of 7 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.

By AnthropicModel ID snowflake/claude-3-5-sonnetPrices updated October 10, 2026Checked October 10, 2026

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: 7
Added to LiteLLM: June 2024

Claude 3.5 Sonnet pricing by provider

13 listings across 7 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-3-5-sonnet`	$3.00	$15.00	$0.30	–	200K
Amazon Bedrocksnapshot 20240620	`anthropic.claude-3-5-sonnet-20240620-v1:0`	$3.00	$15.00	$0.30	$3.75	1M
Amazon Bedrocksnapshot 20240620	`bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0`	$3.00	$15.00	$0.30	$3.75	200K
Google Vertex AI	`vertex_ai/claude-3-5-sonnet`	$3.00	$15.00	–	–	200K
Google Vertex AI	`vertex_ai/claude-3-5-sonnet@20240620`	$3.00	$15.00	–	–	200K
GradientAI	`gradient_ai/anthropic-claude-3.5-sonnet`	$3.00	$15.00	–	–	200K
Herokulatest alias	`heroku/claude-3-5-sonnet-latest`	–	–	–	–	200K
Replicate	`replicate/anthropic/claude-3.5-sonnet`	$3.75	$18.75	–	–	–
Vercel AI Gateway	`vercel_ai_gateway/anthropic/claude-3-5-sonnet`	$3.00	$15.00	$0.30	$3.75	200K
Vercel AI Gatewaysnapshot 20241022	`vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022`	$3.00	$15.00	$0.30	$3.75	200K
Vercel AI Gateway	`vercel_ai_gateway/anthropic/claude-3.5-sonnet`	$3.00	$15.00	$0.30	$3.75	200K
Amazon BedrockEU cross-region, snapshot 20240620	`eu.anthropic.claude-3-5-sonnet-20240620-v1:0`	$3.00	$15.00	$0.30	$3.75	200K
Amazon BedrockUS cross-region, snapshot 20240620	`us.anthropic.claude-3-5-sonnet-20240620-v1:0`	$3.00	$15.00	$0.30	$3.75	200K

What Claude 3.5 Sonnet costs in practice

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

Snowflake Cortex	$13.50
Amazon Bedrock	$13.50
Google Vertex AI	$13.50
GradientAI	$13.50

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

Snowflake Cortex	$33.00
Amazon Bedrock	$33.00
Google Vertex AI	$33.00
GradientAI	$33.00

Claude 3.5 Sonnet features

Function calling
Parallel tool calls
Structured output
Image input
PDF input
Prompt caching
Computer use

Use Claude 3.5 Sonnet with LiteLLM

Call Claude 3.5 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.

Python SDK

from litellm import completion

response = completion(
    model="snowflake/claude-3-5-sonnet",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: claude-3-5-sonnet
    litellm_params:
      model: snowflake/claude-3-5-sonnet
      # 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-3-5-sonnet",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Claude 3.5 Sonnet FAQ

How much does Claude 3.5 Sonnet cost?

Claude 3.5 Sonnet costs $3.00 per 1M input tokens and $15.00 per 1M output tokens from Snowflake Cortex, the lowest of 7 providers, with cache reads at $0.30 per 1M tokens.

What is the context window of Claude 3.5 Sonnet?

Claude 3.5 Sonnet has a 200,000-token context window and returns up to 16,384 tokens per response.

Which providers offer Claude 3.5 Sonnet?

Claude 3.5 Sonnet is available from 7 providers through LiteLLM: Snowflake Cortex, Amazon Bedrock, Google Vertex AI, GradientAI, Heroku, Replicate and Vercel AI Gateway. The lowest price is on Snowflake Cortex.

How do I call Claude 3.5 Sonnet with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="snowflake/claude-3-5-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 3.5 Sonnet support?

Claude 3.5 Sonnet supports function calling, parallel tool calls, structured output, image input, PDF input, prompt caching and computer use.

When did LiteLLM add Claude 3.5 Sonnet?

Claude 3.5 Sonnet was added to LiteLLM's model price file in June 2024.

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, Amazon Bedrock, Google Vertex AI, GradientAI, Heroku, Replicate.

Provider pages: Snowflake Cortex, Amazon Bedrock, Google Vertex AI, GradientAI, Heroku, Replicate, Vercel AI Gateway.