What does it mean that Claude Haiku 4.5 matches Sonnet 4 performance on coding and agent tasks?

Claude Haiku 4.5 delivers equivalent performance to Sonnet 4 on coding, computer use, and agent tasks at lower cost and faster speeds. Run your own benchmarks against your specific workloads to validate this for your use case.

How do I use Claude Haiku 4.5 in the AI SDK?

Set the model to `anthropic/claude-haiku-4.5` in your AI SDK v5 integration. No other code changes are required for the common case.

Which providers back Claude Haiku 4.5 on AI Gateway?

AI Gateway routes Claude Haiku 4.5 through Anthropic, Bedrock, Google Vertex AI, Claude Platform on AWS, with automatic failover.

Does Claude Haiku 4.5 support computer use?

Yes. Claude Haiku 4.5 matches Sonnet 4's performance on computer use tasks.

What latency should I expect for Claude Haiku 4.5 through AI Gateway?

See live performance metrics on this page for current throughput. AI Gateway surfaces real traffic data rather than published benchmark numbers.

Can I use Claude Haiku 4.5 as a drop-in replacement for Sonnet 4 in my agent pipeline?

For coding, computer use, and agent tasks where benchmarks align, Claude Haiku 4.5 may function as a drop-in with cost savings. Test against your specific workflows. General benchmark parity doesn't guarantee equivalent performance on every task profile.

What observability does AI Gateway provide for Claude Haiku 4.5 usage?

AI Gateway tracks usage and cost per request, enabling cost attribution across pipeline stages and budget management without additional instrumentation.

Anthropic

Claude Haiku 4.5

Claude Haiku 4.5 matches Claude Sonnet 4's performance on coding, computer use, and agent tasks at substantially lower cost and faster speeds, making it a high-capability model in the Haiku line for high-throughput agentic deployments. Your use is subject to Anthropic's Terms & Privacy Policies.

View API reference

Input and output price: Prices from: Input $1, Output $5, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'anthropic/claude-haiku-4.5',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Claude Haiku 4.5 by Anthropic. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

Claude Haiku 4.5

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Checking availability for your team

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Regional Inference	Free Tier	Release Date

Anthropic

Legal:Terms•Privacy

200K

64K

0.4 s

104 tps

$1/M

$5/M

Read$0.10/M

Write$1.25/M

$10/K

10/15/2025

Bedrock

Legal:Terms•Privacy

200K

64K

0.5 s

100 tps

$1/M+2 more

$5/M+2 more

Read$0.10/M

Write$1.25/M

—

10/15/2025

Google Vertex AI

Legal:Terms•Privacy

200K

64K

0.9 s

101 tps

$1/M+2 more

$5/M+2 more

Read$0.10/M

Write$1.25/M

$10/K

10/15/2025

Claude Platform on AWS

Legal:Terms•Privacy

200K

64K

0.9 s

95 tps

$1/M

$5/M

Read$0.10/M

Write$1.25/M

$10/K

10/15/2025

Getting started

Call Claude Haiku 4.5 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-haiku-4.5',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Claude Haiku 4.5 request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-haiku-4.5',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `anthropic/claude-haiku-4.5`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Claude Haiku 4.5 supports up to `64,000` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 200K-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens
PDF	—	URL, base64, Uint8Array	—	—	Sent as file parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK anthropic provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-haiku-4.5',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['anthropic', 'bedrock'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-haiku-4.5',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-haiku-4.5',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

PDF input

Attach PDFs as file parts. Their contents count as input tokens.

pdf-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-haiku-4.5',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Summarize this document.' },
          {
            type: 'file',
            mediaType: 'application/pdf',
            data: 'https://example.com/document.pdf',
          },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'anthropic/claude-haiku-4.5',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by Anthropic

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

anthropic/claude-fable-5.1

1.7 s

86 tps

$10/M

$50/M

Read$0.25/M

Write$12.50/M

$10/K

08/31/2026

anthropic/claude-opus-5

1.8 s

129 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

07/24/2026

anthropic/claude-sonnet-5

1.8 s

126 tps

$2/M

$10/M

Read$0.20/M

Write$2.50/M

$10/K

06/29/2026

anthropic/claude-opus-4.8

1.3 s

107 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

05/28/2026

anthropic/claude-sonnet-4.6

0.7 s

64 tps

$3/M

$15/M

Read$0.30/M

Write$3.75/M

$10/K

02/17/2026

anthropic/claude-opus-4.6

1.2 s

56 tps

$5/M+1 more

$25/M+1 more

Read$0.50/M

Write$6.25/M

$10/K

02/05/2026

Copy link to headingAbout Claude Haiku 4.5

Claude Haiku 4.5 became available on AI Gateway on October 15, 2025. It matches Sonnet 4's performance on coding, computer use, and agent tasks at lower cost and faster speeds. Earlier Haiku generations told a similar story relative to their era's highest-tier release; Claude Haiku 4.5 applies it to the Claude 4 generation.

Workloads that previously required a Sonnet 4 deployment can now be evaluated against Claude Haiku 4.5. For organizations running large agent fleets or high-frequency pipelines, the cost differential between Haiku and Sonnet tiers compounds at scale.

Access Claude Haiku 4.5 by setting the model string to anthropic/claude-haiku-4.5 in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. Through AI Gateway, you get observability for tracking usage and cost, bring-your-own-key support, and provider routing across Anthropic, Bedrock, Google Vertex AI, Claude Platform on AWS.

Claude Haiku 4.5 inherits the Claude 4 generation's improvements in agentic task execution and instruction following. For teams building with the AI SDK v5, the integration requires only the model string update. No other code changes are needed for the common case.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: For agentic pipelines that deploy Claude Haiku 4.5 as a sub-agent alongside a larger orchestrating model, AI Gateway per-request observability helps attribute token costs across each pipeline stage.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Claude Haiku 4.5

Best for

High-volume agentic pipelines: Cost per agent step is a primary architecture constraint and Sonnet 4-level capability is required at scale
Computer use tasks: Throughput where Sonnet 4 pricing becomes impractical
Sub-agent roles: Fast, capable, low-latency handling of defined subtasks in multi-model pipelines
Real-time user-facing features: Code completion, inline suggestions, and live chat where latency sensitivity rules out slower models
Coding workflows: Benchmark parity with Sonnet 4 on coding tasks means no capability sacrifice

Consider alternatives when

Deepest reasoning tasks: Claude Sonnet 4.5 or Opus 4-tier models handle the most complex multi-step problem solving
Extended or adaptive thinking: Thinking modes for harder reasoning are unavailable on this tier
Maximum context window: Check the context specs on this page against tasks processing extremely large inputs
Haiku-tier ceiling: Task profiles that exceed Haiku-tier capability require a larger model

Copy link to headingConclusion

Claude Haiku 4.5 shifts the speed-cost tradeoff in agentic deployments. It matches a more capable baseline (Sonnet 4) rather than serving as the affordable option. If you run agent infrastructure at scale, benchmark Claude Haiku 4.5 against Sonnet-tier deployments you run in production before assuming you need an upgrade tier.

Copy link to headingFrequently Asked Questions

What does it mean that Claude Haiku 4.5 matches Sonnet 4 performance on coding and agent tasks?
Claude Haiku 4.5 delivers equivalent performance to Sonnet 4 on coding, computer use, and agent tasks at lower cost and faster speeds. Run your own benchmarks against your specific workloads to validate this for your use case.
How do I use Claude Haiku 4.5 in the AI SDK?
Set the model to anthropic/claude-haiku-4.5 in your AI SDK v5 integration. No other code changes are required for the common case.
Which providers back Claude Haiku 4.5 on AI Gateway?
AI Gateway routes Claude Haiku 4.5 through Anthropic, Bedrock, Google Vertex AI, Claude Platform on AWS, with automatic failover.
Does Claude Haiku 4.5 support computer use?
Yes. Claude Haiku 4.5 matches Sonnet 4's performance on computer use tasks.
What latency should I expect for Claude Haiku 4.5 through AI Gateway?
See live performance metrics on this page for current throughput. AI Gateway surfaces real traffic data rather than published benchmark numbers.
Can I use Claude Haiku 4.5 as a drop-in replacement for Sonnet 4 in my agent pipeline?
For coding, computer use, and agent tasks where benchmarks align, Claude Haiku 4.5 may function as a drop-in with cost savings. Test against your specific workflows. General benchmark parity doesn't guarantee equivalent performance on every task profile.
What observability does AI Gateway provide for Claude Haiku 4.5 usage?
AI Gateway tracks usage and cost per request, enabling cost attribution across pipeline stages and budget management without additional instrumentation.

Claude Haiku 4.5

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Image input

PDF input

Tool calling

Copy link to headingMore models by Anthropic

Copy link to headingAbout Claude Haiku 4.5

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Claude Haiku 4.5

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions