Anthropic: Claude 3 Haiku

anthropic/claude-3-haiku

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance.

See the launch announcement and benchmark results [here](https:/...

visiontools

MODALITIES

→

INPUT PRICE

$0.25per 1M

OUTPUT PRICE

$1.25per 1M

CONTEXT

200K

RELEASED

Mar 13, 2024

Provider				Cache	Uptime	Chat
FastAPI	—	$0.25	$1.25	Cache read$0.03

Capabilities

Input modalities

imagetext

Output modalities

text

Features

max_tokensstoptemperaturetool_choicetoolstop_ktop_p

Get your API key

Create an API key from the Keys page, then set it as an environment variable:

export ONLIST_API_KEY=sk-...

Make your first request

Endpoints

POSThttps://onlist.io/v1/chat/completions

OpenAI Chat Completions format

Request Headers

Authorization:Bearer $ONLIST_API_KEY

Content-Type:application/json

Model:anthropic/claude-3-haiku

POSThttps://onlist.io/v1/responses

OpenAI Responses format

Request Headers

Authorization:Bearer $ONLIST_API_KEY

Content-Type:application/json

Model:anthropic/claude-3-haiku

POSThttps://onlist.io/v1/messages

Anthropic Messages format

Request Headers

Authorization:Bearer $ONLIST_API_KEY

Content-Type:application/json

Model:anthropic/claude-3-haiku

Code samples

curl https://onlist.io/v1/chat/completions \
  -H "Authorization: Bearer $ONLIST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "model": "anthropic/claude-3-haiku",
       "messages": [
         {
           "role": "user",
           "content": "Explain quantum entanglement in one paragraph."
         }
       ]
     }'

Replace $ONLIST_API_KEY with the API key from your Keys page.

Authentication

All requests must include an Authorization: Bearer <TOKEN> header. Generate keys from the Keys page; keys can be scoped to specific models, groups, IP ranges, and rate limits.

Enable streaming

Add "stream": true to receive partial responses as server-sent events in real time.

Streaming example

curl https://onlist.io/v1/chat/completions \
  -H "Authorization: Bearer $ONLIST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "model": "anthropic/claude-3-haiku",
       "messages": [
         {
           "role": "user",
           "content": "Write a haiku about recursion."
         }
       ],
       "stream": true
     }'

Supported parameters

Name	Type	Description
`max_tokens`	integer	Maximum number of tokens to generate in the completion.
`stop`	string \| array	Up to 4 sequences where the API will stop generating tokens.
`temperature`	number	Sampling temperature between 0 and 2. Higher values make output more random.
`tool_choice`	string \| object	Controls which tool is called. "auto", "none", "required", or a specific function.
`tools`	array	A list of tools the model may call. Currently supports functions.
`top_k`	integer	Limits token selection to the k most likely candidates at each step.
`top_p`	number	Nucleus sampling. The model considers tokens with top_p probability mass.

These are the request parameters this model accepts. Parameter semantics follow the OpenAI Chat Completions specification.