Enterprise DNAEnterprise DNA
Anthropic logo

Models · Best cheap

Claude Haiku 4.5

by Anthropic

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.

Visit Anthropic ↗

Our verdict

Not reviewed yet

We have not reviewed Claude Haiku 4.5 yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.

Best for

Cheap fast steps in multi-model agent pipelines

Use cases

  • classification
  • draft PRs
  • triage
  • tool-routing

Enterprise DNA angle

Omni defaults bulk steps to Haiku-class models and escalates only when eval gates fail.

Notes

Claude Haiku 4.5 is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Fast and cheap for high-volume agent steps
  • Good enough coding for drafts and simple refactors
  • Vision support without frontier pricing

Cons

  • Trails Sonnet/Opus on hard reasoning
  • Closed weights

Key facts

What we have checked

Input price
$1.00 per million tokens
Checked OpenRouter models API
Output price
$5.00 per million tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.100 per million cached input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$1.00 per million input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$5.00 per million output tokens
Checked OpenRouter models API
Price on anthropic
$0.100 per million cached input tokens
Checked OpenRouter models API
Price on anthropic
$1.00 per million input tokens
Checked OpenRouter models API
Price on anthropic
$5.00 per million output tokens
Checked OpenRouter models API
Price on azure
$0.100 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
71.2% (for 15 Oct 2025)
Checked Epoch AI (CC BY 4.0)
Terminal bench
35.5% (for 15 Oct 2025)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
13.2% (for 15 Oct 2025)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `anthropic/claude-haiku-4.5`.

  • openrouter · anthropic/claude-haiku-4.5 · Docs

OpenRouter id: anthropic/claude-haiku-4.5

Price

What Claude Haiku 4.5 costs, over time

Input price

$1.00 to $1.00

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$5.00 to $5.00

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
amazon-bedrockCached input$0.100 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
amazon-bedrockInput$1.00 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
amazon-bedrockOutput$5.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
anthropicCached input$0.100 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
anthropicInput$1.00 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
anthropicOutput$5.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureCached input$0.100 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureInput$1.00 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureOutput$5.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexCached input$0.100 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexInput$1.00 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexOutput$5.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Claude Haiku 4.5 is used

Tokens served a day

26.1B to 39.7B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Claude Haiku 4.5 scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index7.4indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index43.9indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index8indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,397EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena web development rating (Elo)1,330EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)1,137EloAs of 10 Nov 2026Design Arena via OpenRouter
Arc agi (best-across-versions)47.7percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)4percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Balrog (best-across-versions)31.2percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)8percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Deepresearch bench (best-across-versions)45.5percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)73.6percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Show 10 more scores
ScoreValueSourceChecked
Exploitbench (best-across-versions)13.7percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Frontiermath 2025 02 28 private (best-across-versions)5.9percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Frontiermath tier 4 2025 07 01 private (best-across-versions)2.1percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)71.2percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Lmca (best-across-versions)30.9percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Math level 5 (best-across-versions)96.4percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated66.7percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)13.2percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Terminal bench (best-across-versions)35.5percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)45.4percentAs of 15 Oct 2025Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

In the AI Pulse

Recent daily briefs from the Enterprise DNA AI Pulse that mention this. The short daily read on what is actually happening in AI.

See today's AI Pulse →

USAGE / OPENROUTER

How much Claude Haiku 4.5 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
178B ▲40%
Requests, last 7 days
27.7M
Tool calls, last 7 days
4M
Intelligence score
7.4
People's vote
1397
Average cost per request
43.7¢
Price per million tokens
$1 in · $5 out
050B100B19 Sept: 26.1B tokens, 4.3M requests20 Sept: 23.5B tokens, 3.4M requests21 Sept: 35.2B tokens, 5M requests22 Sept: 39B tokens, 5.7M requests23 Sept: 39.1B tokens, 6.3M requests24 Sept: 40.7B tokens, 5.7M requests25 Sept: 35.6B tokens, 5.2M requests26 Sept: 25.3B tokens, 3.8M requests27 Sept: 25.7B tokens, 3.8M requests28 Sept: 37.6B tokens, 5.4M requests29 Sept: 40.4B tokens, 5.8M requests30 Sept: 38.6B tokens, 5.9M requests1 Oct: 40.4B tokens, 5.7M requests2 Oct: 36.4B tokens, 5M requests3 Oct: 27B tokens, 3.7M requests4 Oct: 25.9B tokens, 3.7M requests5 Oct: 39.4B tokens, 5.6M requests6 Oct: 51.5B tokens, 7M requests7 Oct: 46.8B tokens, 7.5M requests8 Oct: 37.8B tokens, 7.7M requests9 Oct: 33.1B tokens, 6M requests10 Oct: 19.5B tokens, 4.3M requests11 Oct: 16.8B tokens, 3.5M requests12 Oct: 26.6B tokens, 5.5M requests13 Oct: 28B tokens, 5.8M requests14 Oct: 26.4B tokens, 5.5M requests15 Oct: 27.5B tokens, 6.4M requests16 Oct: 24B tokens, 5.5M requests17 Oct: 15.4B tokens, 4.1M requests18 Oct: 15.5B tokens, 4.1M requests19 Oct: 21.9B tokens, 5.3M requests20 Oct: 25.3B tokens, 5.8M requests21 Oct: 23.7B tokens, 5.4M requests22 Oct: 26.6B tokens, 5.5M requests23 Oct: 22.1B tokens, 4.9M requests24 Oct: 15B tokens, 3.4M requests25 Oct: 15.2B tokens, 3.8M requests26 Oct: 26.9B tokens, 5.4M requests27 Oct: 22B tokens, 4.9M requests28 Oct: 22.5B tokens, 4.8M requests29 Oct: 21.1B tokens, 4.5M requests30 Oct: 18.2B tokens, 4.1M requests31 Oct: 11.8B tokens, 2.8M requests1 Nov: 13.5B tokens, 2.9M requests2 Nov: 19.3B tokens, 4.1M requests3 Nov: 20.6B tokens, 4.4M requests4 Nov: 23.3B tokens, 4.2M requests5 Nov: 24.3B tokens, 4.1M requests6 Nov: 31.6B tokens, 4.3M requests7 Nov: 17.5B tokens, 2.9M requests8 Nov: 12.5B tokens, 2.8M requests9 Nov: 29B tokens, 4.5M requests10 Nov: 39.7B tokens, 5M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Claude Haiku 4.5.

Listed specifications; no reviewed EDNA task evaluation yet. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperAnthropic
Exact model identifieranthropic/claude-haiku-4.5
Inputtext, image, file
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
200K tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
15 Oct 2025
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

anthropic/claude-haiku-4.5: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-07
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Build an appWorkflow & starter prompt ↗Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 7.4 (2026-11-09) ↗Coding Index: 43.9 (2026-11-09) ↗Agentic Index: 8 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →