Claude Sonnet 5 API Pricing

As of October 10, 2026, Claude Sonnet 5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens on Anthropic, with cache reads at $0.20 and cache writes at $2.50 per 1M tokens. Across 9 providers on LiteLLM, the input price ranges from $2.00 to $3.00. It has a 1,000,000-token context window and returns up to 128,000 tokens per response.

By AnthropicModel ID claude-sonnet-5Prices updated October 10, 2026Checked October 10, 2026

Input: $2.00 / 1M tokens
Output: $10.00 / 1M tokens
Cache read: $0.20 / 1M tokens
Context window: 1,000,000 tokens
Max output: 128,000 tokens
Providers: 9
Added to LiteLLM: June 30, 2026

Claude Sonnet 5 pricing by provider

19 listings across 9 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	Batch in	Batch out	Context
Anthropic	`claude-sonnet-5`	$2.00	$10.00	$0.20	$2.50	$1.00	$5.00	1M
AIHubMix	`aihubmix/claude-sonnet-5`	$2.00	$10.00	$0.20	$2.50	–	–	1M
Amazon Bedrock	`anthropic.claude-sonnet-5`	$2.00	$10.00	$0.20	$2.50	–	–	1M
Azure AI Foundry	`azure_ai/claude-sonnet-5`	$2.00	$10.00	$0.20	$2.50	–	–	1M
Databricks	`databricks/databricks-claude-sonnet-5`	$3.00	$15.00	$0.30	$3.75	–	–	1M
DeepInfra	`deepinfra/anthropic/claude-sonnet-5`	$2.00	$10.00	–	–	–	–	1M
GitHub Copilot	`github_copilot/claude-sonnet-5`	–	–	–	–	–	–	200K
Google Vertex AI	`vertex_ai/claude-sonnet-5`	$2.00	$10.00	$0.20	$2.50	$1.00	$5.00	1M
Google Vertex AI	`vertex_ai/claude-sonnet-5@default`	$2.00	$10.00	$0.20	$2.50	$1.00	$5.00	1M
Perplexity	`perplexity/anthropic/claude-sonnet-5`	$2.00	$10.00	$0.20	–	–	–	–
Amazon BedrockAPAC cross-region	`apac.anthropic.claude-sonnet-5`	$2.20	$11.00	$0.22	$2.75	–	–	1M
Amazon BedrockAustralia cross-region	`au.anthropic.claude-sonnet-5`	$2.20	$11.00	$0.22	$2.75	–	–	1M
Amazon Bedrockus-gov-east-1	`bedrock/us-gov-east-1/anthropic.claude-sonnet-5`	$2.40	$12.00	$0.24	$3.00	–	–	1M
Amazon Bedrockus-gov-west-1	`bedrock/us-gov-west-1/anthropic.claude-sonnet-5`	$2.40	$12.00	$0.24	$3.00	–	–	1M
Amazon BedrockEU cross-region	`eu.anthropic.claude-sonnet-5`	$2.20	$11.00	$0.22	$2.75	–	–	1M
Amazon BedrockGlobal cross-region	`global.anthropic.claude-sonnet-5`	$2.00	$10.00	$0.20	$2.50	–	–	1M
Amazon BedrockJapan cross-region	`jp.anthropic.claude-sonnet-5`	$2.20	$11.00	$0.22	$2.75	–	–	1M
Amazon BedrockUS GovCloud cross-region	`us-gov.anthropic.claude-sonnet-5`	$2.40	$12.00	$0.24	$3.00	–	–	1M
Amazon BedrockUS cross-region	`us.anthropic.claude-sonnet-5`	$2.20	$11.00	$0.22	$2.75	–	–	1M

Other Claude Sonnet 5 prices on Anthropic

Cache write, 1 hour	$4.00 per 1M tokens
Web search	$10.00 per 1K searches

What Claude Sonnet 5 costs in practice

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

Anthropic	$9.00
AIHubMix	$9.00
Amazon Bedrock	$9.00
Azure AI Foundry	$9.00
Anthropic batch	$4.50

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

Anthropic	$22.00
AIHubMix	$22.00
Amazon Bedrock	$22.00
Azure AI Foundry	$22.00

Claude Sonnet 5 features

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

Use Claude Sonnet 5 with LiteLLM

Call Claude Sonnet 5 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="claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: claude-sonnet-5
    litellm_params:
      model: claude-sonnet-5
      api_key: os.environ/ANTHROPIC_API_KEY

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-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Claude Sonnet 5 FAQ

How much does Claude Sonnet 5 cost?

Claude Sonnet 5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens on Anthropic, with cache reads at $0.20 and cache writes at $2.50 per 1M tokens. Batch requests cost $1.00 per 1M input tokens and $5.00 per 1M output tokens. Across 9 providers on LiteLLM, the input price ranges from $2.00 to $3.00.

What is the context window of Claude Sonnet 5?

Claude Sonnet 5 has a 1,000,000-token context window and returns up to 128,000 tokens per response.

Which providers offer Claude Sonnet 5?

Claude Sonnet 5 is available from 9 providers through LiteLLM: Anthropic, AIHubMix, Amazon Bedrock, Azure AI Foundry, Databricks, DeepInfra, GitHub Copilot, Google Vertex AI and Perplexity. The lowest price is on Anthropic.

How do I call Claude Sonnet 5 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="claude-sonnet-5", 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 5 support?

Claude Sonnet 5 supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching, web search and computer use.

When did LiteLLM add Claude Sonnet 5?

Claude Sonnet 5 was added to LiteLLM's model price file on June 30, 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: Anthropic, AIHubMix, Amazon Bedrock, Azure AI Foundry, Databricks, DeepInfra.

Provider pages: Anthropic, AIHubMix, Amazon Bedrock, Azure AI Foundry, Databricks, DeepInfra, GitHub Copilot, Google Vertex AI, Perplexity.