Skip to content

Claude Haiku 4.5

anthropic/claude-haiku-4.5

Previous-generation Haiku from October 2025 (pinned snapshot claude-haiku-4-5-20251001), superseded by Claude Haiku 5.5. A small, fast model with a 200K-token context, 64K output and manual extended thinking.

API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-haiku-4.5",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Input Price
$0.85 / 1M tokens
Output Price
$4.25 / 1M tokens
Context
200K tokens
Output Cap
64K tokens

Capabilities

Explore what Claude Haiku 4.5 supports, then use the API section for a request tailored to this model.

Max tokensStopResponse formatStructured outputsToolsTool choiceParallel tool callsReasoningInclude reasoningTemperatureTop pTop k

Model Information

Provider
Anthropic
Product
Language Models
Release Date
Oct 15, 2025
Data Policy
Not specified
Region
Global
Input
Text, Image, File
Output
Text
Provider Documentation

Playground

Try Claude Haiku 4.5 by Anthropic. Requests use the selected workspace’s credits and API pricing.

Claude Haiku 4.5Credits —
Claude Haiku 4.5
⌘ / Ctrl + Enter to send

Providers

Compare available endpoints, pricing, and context limits for Claude Haiku 4.5.

ProviderContextOutput CapInput PriceOutput PriceEndpoint
Anthropic200K tokens64K tokens$0.85 / 1M tokens$4.25 / 1M tokens
claude-haiku-4-5-20251001

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max input tokens200000
Max output tokens64000

Provider Notes

General LLM inference is an integration preview. Managed billing and deployment acceptance must be enabled before requests can be served.

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-haiku-4.5",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modelanthropic/claude-haiku-4.5 — Required model identifier.
max_tokensView Accepted Values
stopView Accepted Values
response_formatView Accepted Values
structured_outputsView Accepted Values
toolsView Accepted Values
tool_choiceView Accepted Values
parallel_tool_callsView Accepted Values
reasoningView Accepted Values
include_reasoningView Accepted Values
temperatureView Accepted Values
top_pView Accepted Values
top_kView Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max input tokens200000
Max output tokens64000

Similar Models

Explore more language models and compare their capabilities.

ModelContextInput PriceOutput Price
Claude Haiku 5.5Anthropic1M tokens$0.085 / 1M tokens$0.425 / 1M tokens
Claude Sonnet 5.5Anthropic1M tokens$1.70 / 1M tokens$8.50 / 1M tokens
Claude Opus 5.5Anthropic1M tokens$3.40 / 1M tokens$17.00 / 1M tokens
Claude Fable 5.1Anthropic1M tokens$8.50 / 1M tokens$42.50 / 1M tokens
Claude Opus 5Anthropic1M tokens$4.25 / 1M tokens$21.25 / 1M tokens
Claude Sonnet 5Anthropic1M tokens$1.70 / 1M tokens$8.50 / 1M tokens
View All Language Models