Claude Opus 4 API Pricing
As of October 10, 2026, Claude Opus 4 costs $15.00 per 1M input tokens and $75.00 per 1M output tokens from GMI Cloud, the lowest of 4 providers. It has a 409,600-token context window and returns up to 32,000 tokens per response.
- Input
- $15.00 / 1M tokens
- Output
- $75.00 / 1M tokens
- Context window
- 409,600 tokens
- Max output
- 32,000 tokens
- Providers
- 4
- Added to LiteLLM
- May 2025
Claude Opus 4 pricing by provider
6 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 |
|---|---|---|---|---|---|---|
| GMI Cloud | gmi/anthropic/claude-opus-4 | $15.00 | $75.00 | – | – | 400K |
| Amazon Bedrocksnapshot 20250514 | anthropic.claude-opus-4-20250514-v1:0 | $15.00 | $75.00 | $1.50 | $18.75 | 200K |
| Databricks | databricks/databricks-claude-opus-4 | $15.00 | $75.00 | $1.50 | $18.75 | 200K |
| Vercel AI Gateway | vercel_ai_gateway/anthropic/claude-opus-4 | $15.00 | $75.00 | $1.50 | $18.75 | 200K |
| Amazon BedrockEU cross-region, snapshot 20250514 | eu.anthropic.claude-opus-4-20250514-v1:0 | $15.00 | $75.00 | $1.50 | $18.75 | 200K |
| Amazon BedrockUS cross-region, snapshot 20250514 | us.anthropic.claude-opus-4-20250514-v1:0 | $15.00 | $75.00 | $1.50 | $18.75 | 200K |
What Claude Opus 4 costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| GMI Cloud | $67.50 |
| Amazon Bedrock | $67.50 |
| Vercel AI Gateway | $67.50 |
| Databricks | $67.50 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| GMI Cloud | $165.00 |
| Amazon Bedrock | $165.00 |
| Vercel AI Gateway | $165.00 |
| Databricks | $165.00 |
Claude Opus 4 features
- Function calling
- Structured output
- Image input
- PDF input
- Reasoning
- Prompt caching
- Computer use
Use Claude Opus 4 with LiteLLM
Call Claude Opus 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.
from litellm import completion
response = completion(
model="gmi/anthropic/claude-opus-4",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: claude-opus-4
litellm_params:
model: gmi/anthropic/claude-opus-4
# 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-opus-4",
"messages": [{"role": "user", "content": "Hello!"}]
}'Claude Opus 4 FAQ
How much does Claude Opus 4 cost?
Claude Opus 4 costs $15.00 per 1M input tokens and $75.00 per 1M output tokens from GMI Cloud, the lowest of 4 providers.
What is the context window of Claude Opus 4?
Claude Opus 4 has a 409,600-token context window and returns up to 32,000 tokens per response.
Which providers offer Claude Opus 4?
Claude Opus 4 is available from 4 providers through LiteLLM: GMI Cloud, Amazon Bedrock, Databricks and Vercel AI Gateway. The lowest price is on GMI Cloud.
How do I call Claude Opus 4 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gmi/anthropic/claude-opus-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 Opus 4 support?
Claude Opus 4 supports function calling, structured output, image input, PDF input, reasoning, prompt caching and computer use.
When did LiteLLM add Claude Opus 4?
Claude Opus 4 was added to LiteLLM's model price file in May 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. Provider pricing pages:
LiteLLM docs: GMI Cloud, Amazon Bedrock, Databricks, Vercel AI Gateway.
Provider pages: GMI Cloud, Amazon Bedrock, Databricks, Vercel AI Gateway.