Claude 3 Haiku API Pricing
As of October 10, 2026, Claude 3 Haiku costs $0.25 per 1M input tokens and $1.25 per 1M output tokens from Google Vertex AI, the lowest of 2 providers. It has a 200,000-token context window and returns up to 4,096 tokens per response.
vertex_ai/claude-3-haiku.- Input
- $0.25 / 1M tokens
- Output
- $1.25 / 1M tokens
- Context window
- 200,000 tokens
- Max output
- 4,096 tokens
- Providers
- 2
- Added to LiteLLM
- March 2024
Claude 3 Haiku pricing by provider
3 listings across 2 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-haiku | $0.25 | $1.25 | – | – | 200K |
| Google Vertex AI | vertex_ai/claude-3-haiku@20240307 | $0.25 | $1.25 | – | – | 200K |
| Vercel AI Gateway | vercel_ai_gateway/anthropic/claude-3-haiku | $0.25 | $1.25 | $0.03 | $0.30 | 200K |
What Claude 3 Haiku costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Google Vertex AI | $1.125 |
| Vercel AI Gateway | $1.125 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Google Vertex AI | $2.75 |
| Vercel AI Gateway | $2.75 |
Claude 3 Haiku features
- Function calling
- Structured output
- Image input
Use Claude 3 Haiku with LiteLLM
Call Claude 3 Haiku 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="vertex_ai/claude-3-haiku",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: claude-3-haiku
litellm_params:
model: vertex_ai/claude-3-haiku
vertex_project: os.environ/VERTEX_PROJECT
vertex_location: os.environ/VERTEX_LOCATIONcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "claude-3-haiku",
"messages": [{"role": "user", "content": "Hello!"}]
}'Claude 3 Haiku FAQ
How much does Claude 3 Haiku cost?
Claude 3 Haiku costs $0.25 per 1M input tokens and $1.25 per 1M output tokens from Google Vertex AI, the lowest of 2 providers.
What is the context window of Claude 3 Haiku?
Claude 3 Haiku has a 200,000-token context window and returns up to 4,096 tokens per response.
Which providers offer Claude 3 Haiku?
Claude 3 Haiku is available from 2 providers through LiteLLM: Google Vertex AI and Vercel AI Gateway.
How do I call Claude 3 Haiku with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="vertex_ai/claude-3-haiku", 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 Haiku support?
Claude 3 Haiku supports function calling, structured output and image input.
When did LiteLLM add Claude 3 Haiku?
Claude 3 Haiku was added to LiteLLM's model price file in March 2024.
Is Claude 3 Haiku being deprecated?
Google Vertex AI deprecated vertex_ai/claude-3-haiku on August 23, 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.
LiteLLM docs: Google Vertex AI, Vercel AI Gateway.
Provider pages: Google Vertex AI, Vercel AI Gateway.