Claude Haiku 4.5

by Anthropic

Released 16 days after Claude Sonnet 4.5 · All Anthropic releases

Claude Haiku 4.5 delivers coding performance similar to Claude Sonnet 4 while running more than twice as fast at roughly a third of the cost. It scores 73.3% on SWE-bench Verified, ranking among the strongest coding models for its class, and surpasses Sonnet 4 on certain tasks such as computer use. As the first Haiku model to support extended thinking, Haiku 4.5 brings controllable reasoning depth to the family, performing notably better on complex coding and multi-step reasoning when extended thinking is enabled. It supports a 200K token context window and shows a statistically significantly lower overall rate of misaligned behaviors than larger Claude models. Haiku 4.5 is well suited to chat assistants, customer service agents, and pair programming, offering near-frontier performance at strong cost efficiency.

Call Claude Haiku 4.5 on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Key info

Input
Output
Features
Context window
200K
Max output
64K
Input price
$1.00 /1M$0.10 cache read · $1.25 write
Output price
$5.00 /1M
Released
  • EU residency available
  • US residency available
  • Zero data retention on pay-as-you-go
  • No training by default
  • GDPR DPA available

Available routes

Claude Haiku 4.5 runs on 7 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by AWS Bedrock (France), Azure (Sweden) and Google Cloud (Belgium, EU multi-region). See every Claude model hosted in the EU.

ProviderRegionZero data retentionTrainingInputOutputCache read
USNo$1.00$5.00$0.10$1.25 write
EUNo$1.10$5.50$0.11$1.38 write
EUNo$1.00$5.00$0.10$1.25 write
USNo$1.00$5.00$0.10$1.25 write
EUNo$1.10$5.50$0.11$1.38 write
MultiNo$1.00$5.00$0.10$1.25 write
EUNo$1.10$5.50$0.11$1.38 write

Uptime and availability

Claude Haiku 4.5 runs on 4 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days
Averaged across these routes on their own, a single provider reached 96.00% over the same window.
Daily status through the gateway, which serves each request from whichever route is healthy.
4 monitored providers serve Claude Haiku 4.5.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Claude Haiku 4.5 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Anthropic — United States🇺🇸

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention
With abuse monitoring, window not stated.
Training
No training on customer data.
Logging
Abuse monitoring
Abuse monitoring
On by default, holds flagged content, 730 days, a person can view samples
Caching
Content cached for replay
GDPR DPA
DPA available
Transfer mechanism
SCCs

AWS Bedrock — France🇫🇷

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.

Zero data retention
Yes. Nothing is logged, held for abuse monitoring or used for training.
Training
No training on customer data.
Logging
None
Abuse monitoring
Always on, keeps nothing
GDPR DPA
DPA available
Transfer mechanism
Not applicable — data stays in EU

Azure — Sweden🇸🇪

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. EU; DPA available.

Zero data retention
With abuse monitoring, flagged content held.
Training
No training on customer data.
Logging
None
Abuse monitoring
On by default, holds flagged content, 730 days, a person can view samples
Caching
Content cached for replay
GDPR DPA
DPA available
Transfer mechanism
Not applicable — data stays in EU

Google Cloud — United States🇺🇸

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention
With abuse monitoring, window not stated.
Training
No training on customer data.
Logging
Abuse monitoring
Abuse monitoring
On by default, holds flagged content, 90 days, stored in United States, a person can view samples
Caching
Content cached for replay
GDPR DPA
DPA available
Transfer mechanism
SCCs

Google Cloud — Belgium🇧🇪

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. EU; DPA available.

Zero data retention
With abuse monitoring, window not stated.
Training
No training on customer data.
Logging
Abuse monitoring
Abuse monitoring
On by default, holds flagged content, 90 days, stored in Belgium, a person can view samples
Caching
Content cached for replay
GDPR DPA
DPA available
Transfer mechanism
Not applicable — data stays in EU

Google Cloud — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention
With abuse monitoring, window not stated.
Training
No training on customer data.
Logging
Abuse monitoring
Abuse monitoring
On by default, holds flagged content, 90 days, a person can view samples
GDPR DPA
DPA available
Transfer mechanism
SCCs

Google Cloud — European Union🇪🇺

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. EU; DPA available.

Zero data retention
With abuse monitoring, window not stated.
Training
No training on customer data.
Logging
Abuse monitoring
Abuse monitoring
On by default, holds flagged content, 90 days, a person can view samples
GDPR DPA
DPA available
Transfer mechanism
Not applicable — data stays in EU

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#245 of 665 LLMs
TierEfficient
Output speed111 tok/s
First token13.41s
Intelligence Index16.9
Coding Index43.9
Math Index83.7
Reasoning & knowledge
MMLU-Pro
76%
GPQA Diamond
67%
Humanity's Last Exam
10%
Long-context reasoning
74%
Coding
LiveCodeBench
62%
SciCode
42%
Agentic & tool use
Terminal-Bench Hard
27%
τ²-Bench Telecom
55%
Math & instruction following
AIME 2025
84%
IFBench
54%

Get started

Call Claude Haiku 4.5 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Claude Haiku 4.5 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "claude-haiku-4-5",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Use Claude Haiku 4.5 in your apps

Pick your tool to see how to run it on Claude Haiku 4.5 through Opper.

Compare Claude Haiku 4.5 with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Anthropic

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation