Skip to content
Claude Haiku 4.5 logo

Claude Haiku 4.5

Verified

Efficient multimodal model for text, image, and file tasks.

AnthropicMultimodalClosed
Vision
Model page
Updated 2026-06-14

About Claude Haiku 4.5

Claude Haiku 4.5 integrates text, image, and file processing in a single multimodal system. Its 200,000-token context window enables coherent handling of lengthy combined inputs. As a proprietary model from Anthropic, it emphasizes controlled API access rather than open weights.

The design prioritizes efficiency across modalities while maintaining broad input compatibility. Strengths include seamless multi-format analysis without separate preprocessing steps. Typical usage covers document review with visuals, mixed-media content creation, and file-based research queries.

Capabilities

Long-context reasoning
Vision and image understanding
File and document processing
Fast text generation
Multimodal instruction following
Code analysis

How Claude Haiku 4.5 compares

Claude Haiku 4.5 (striped bar) vs other multimodal on intelligence, speed and price.

Price

USD per 1M output tokens · Lower is better · Claude Haiku 4.5 ranks #56 of 100

$3.4
MoonshotAI Kimi Latest
$3.4
MoonshotAI Kimi Latest
$3.4
Kimi K2.6
$3.5
Kimi K2.7 Code
$4.5
GPT-5.4 Mini
$4.5
OpenAI GPT Mini Latest
$5.0
Claude Haiku 4.5
$5.0
Anthropic Claude Haiku Latest
$6.0
Grok 4.20 Multi-Agent
$7.5
Mistral Medium 3.5
$8.0
o4 Mini Deep Research
$9.0
Gemini 3.5 Flash
$9.0
Google Gemini Flash Latest

Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).

Best for

Long document analysis

Handles extended research papers or legal contracts up to 200000 tokens with sustained reasoning across multiple sections.

Image and diagram interpretation

Processes visual content from charts, photos, and technical diagrams alongside accompanying text for multimodal tasks.

Rapid code review

Delivers fast code analysis and suggestions for debugging or refactoring while following detailed instructions.

Strengths & limitations

Strengths

  • +High speed and low latency
  • +Cost-efficient for routine tasks
  • +Strong safety alignment
  • +Reliable on straightforward queries

Limitations

  • Less capable on complex reasoning than larger models
  • May underperform on highly creative or nuanced tasks
  • Dependent on input quality for multimodal results

Cost calculator

Estimate what Claude Haiku 4.5 would cost for your usage.

$0.00350
per request
$35
estimated / month

Based on Claude Haiku 4.5's $1.00/1M input · $5.00/1M output. Estimate only — actual cost varies by provider and caching.

Quick start

OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.

JavaScript · openai
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "anthropic/claude-haiku-4.5",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

Model slug: anthropic/claude-haiku-4.5

Editor's verdict

Our take on Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic's proprietary multimodal with a 200K-token context window.

At $5.00 per 1M output tokens, it is premium-priced for its class.

It is available through Anthropic's API and aggregators like OpenRouter.

Best suited to high speed and low latency and cost-efficient for routine tasks.

Did you find this helpful?

Frequently asked questions

The model provides a 200000-token context window for processing long inputs.

User reviews

Real, verified reviews from the community shape this model's rating.

Loading reviews…

Sign in to review

Other Claude models

Sibling versions in the Claude family from Anthropic.

Promote Claude Haiku 4.5

Add this badge to your website, or share the tool.

DFeatured on DhanasviClaude Haiku 4.5 1