CrossModel
Claude Haiku 4.5
anthropic/claude-haiku-4-5
Back to model catalog

Anthropic · Model guide

Claude Haiku 4.5

Compare
anthropic/claude-haiku-4-5

The small, fast Claude with a 200k context window and 64k output. It is the only model in this family that still uses extended thinking with an explicit token budget instead of adaptive thinking, and the effort parameter does not apply to it at all. Anthropic positions it for real-time work such as chat assistants, customer service agents and pair programming.

Modalities
TextImageText
Context
200K
Max output
64K
Price / 1M tokens
$ 1.00in$ 5.00out
StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorThe fastest model with near-frontier intelligence.source

Best for

  • Real-time, low-latency tasks · Anthropic names chat assistants, customer service agents and pair programming.(vendor claim)source

  • High-volume workloads · Anthropic positions it as frontier-level coding at a third of the cost and twice the speed of Sonnet 4.(vendor claim)source

Neighbouring models
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 1.00
Output$ 5.00
Cache read$ 0.10
Cache write$ 1.25
Estimate a request
$ 0.0200
Estimated cost per request
10.0K × $ 1.00
+ 2.0K × $ 5.00
≈ $ 20.00 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
200.0K tokens
Max output
64.0K tokens
Input / output modalities
Text + Image → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· can be turned off
Thinking budget
1.0K – 0 tokens
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsplatform.claude.comCapabilitiesplatform.claude.com 1platform.claude.com 2platform.claude.com 3platform.claude.com 4

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Terminal-Bench
    pass_rate·Anthropic · 2025-10-15setup not fully disclosed

    Anthropic's launch table names the benchmark without a version.

    41%
Coding
  • SWE-Bench Verified
    resolved_rate·Anthropic · 2025-10-15setup not fully disclosed
    73.3%
Computer use
  • OSWorld
    success_rate·Anthropic · 2025-10-15setup not fully disclosed
    50.7%
Math reasoning
  • AIME 2025
    accuracy·Anthropic · 2025-10-15setup not fully disclosed

    No tools. Anthropic also reports 96.3% with Python tool use.

    80.7%
Multilingual
  • MMMLU
    accuracy·Anthropic · 2025-10-15setup not fully disclosed
    83%
Multimodal reasoning
  • MMMU
    accuracy·Anthropic · 2025-10-15setup not fully disclosed

    Validation split.

    73.2%
Scientific reasoning
  • GPQA Diamond
    accuracy·Anthropic · 2025-10-15setup not fully disclosed
    73%
Tool use
  • τ2-bench Retail
    score·Anthropic · 2025-10-15setup not fully disclosed
    83.2%
  • τ2-bench Telecom
    score·Anthropic · 2025-10-15setup not fully disclosed
    83%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is Claude Haiku 4.5?
Claude Haiku 4.5 is available on CrossModel as anthropic/claude-haiku-4-5. It has a 200K-token context window and can return up to 64K tokens per request.
How much does Claude Haiku 4.5 cost?
Currently $ 1.00 per 1M input tokens and $ 5.00 per 1M output tokens. Cached input is billed at $ 0.10 per 1M.
Does Claude Haiku 4.5 support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.