Claude 3 Opus API Pricing

As of October 10, 2026, Claude 3 Opus costs $15.00 per 1M input tokens and $75.00 per 1M output tokens from Google Vertex AI, the lowest of 4 providers. It has a 200,000-token context window and returns up to 4,096 tokens per response.

By AnthropicModel ID vertex_ai/claude-3-opusPrices updated October 10, 2026Checked October 10, 2026

Deprecated: Google Vertex AI lists August 1, 2025 as the deprecation date for vertex_ai/claude-3-opus.

Input: $15.00 / 1M tokens
Output: $75.00 / 1M tokens
Context window: 200,000 tokens
Max output: 4,096 tokens
Providers: 4
Added to LiteLLM: March 2024

Claude 3 Opus pricing by provider

7 listings across 4 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
Google Vertex AI	`vertex_ai/claude-3-opus`	$15.00	$75.00	–	–	200K
Amazon Bedrocksnapshot 20240229	`anthropic.claude-3-opus-20240229-v1:0`	$15.00	$75.00	$1.50	$18.75	200K
Google Vertex AI	`vertex_ai/claude-3-opus@20240229`	$15.00	$75.00	–	–	200K
GradientAI	`gradient_ai/anthropic-claude-3-opus`	$15.00	$75.00	–	–	200K
Vercel AI Gateway	`vercel_ai_gateway/anthropic/claude-3-opus`	$15.00	$75.00	$1.50	$18.75	200K
Amazon BedrockEU cross-region, snapshot 20240229	`eu.anthropic.claude-3-opus-20240229-v1:0`	$15.00	$75.00	$1.50	$18.75	200K
Amazon BedrockUS cross-region, snapshot 20240229	`us.anthropic.claude-3-opus-20240229-v1:0`	$15.00	$75.00	$1.50	$18.75	200K

What Claude 3 Opus costs in practice

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

Google Vertex AI	$67.50
Amazon Bedrock	$67.50
GradientAI	$67.50
Vercel AI Gateway	$67.50

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

Google Vertex AI	$165.00
Amazon Bedrock	$165.00
GradientAI	$165.00
Vercel AI Gateway	$165.00

Claude 3 Opus features

Function calling
Structured output
Image input

Use Claude 3 Opus with LiteLLM

Call Claude 3 Opus 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="vertex_ai/claude-3-opus",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: claude-3-opus
    litellm_params:
      model: vertex_ai/claude-3-opus
      vertex_project: os.environ/VERTEX_PROJECT
      vertex_location: os.environ/VERTEX_LOCATION

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

Claude 3 Opus FAQ

How much does Claude 3 Opus cost?

Claude 3 Opus costs $15.00 per 1M input tokens and $75.00 per 1M output tokens from Google Vertex AI, the lowest of 4 providers.

What is the context window of Claude 3 Opus?

Claude 3 Opus has a 200,000-token context window and returns up to 4,096 tokens per response.

Which providers offer Claude 3 Opus?

Claude 3 Opus is available from 4 providers through LiteLLM: Google Vertex AI, Amazon Bedrock, GradientAI and Vercel AI Gateway.

How do I call Claude 3 Opus with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="vertex_ai/claude-3-opus", 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 Opus support?

Claude 3 Opus supports function calling, structured output and image input.

When did LiteLLM add Claude 3 Opus?

Claude 3 Opus was added to LiteLLM's model price file in March 2024.

Is Claude 3 Opus being deprecated?

Google Vertex AI deprecated vertex_ai/claude-3-opus on August 1, 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: Google Vertex AI, Amazon Bedrock, GradientAI, Vercel AI Gateway.

Provider pages: Google Vertex AI, Amazon Bedrock, GradientAI, Vercel AI Gateway.