Requesty
Sign in

identity

endpoint
Google LLC (Vertex AI) logo

claude-haiku-4-5Google LLC (Vertex AI)

in /1M$1.00input tokens
out /1M$5.00output tokens
context200K64K out
median ttft477msmeasured
api
chat
hosting
US
model lab
Anthropic
weights
closed
added
October 2025
model id
vertex/claude-haiku-4-5

capabilities 7/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

3 providers serve claude-haiku-4-5. This page is one of them. Compare all endpoints

pricing

no markup
input
$1.00
output
$5.00
cache write
$1.25
cache read
$0.10

worked cost

Estimated cost for three request volumes
volumecost
100K in + 10K out$0.15
1M in + 100K out$1.50
10M in + 1M out$15.00

Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing

provider price, passed throughper 1M tokens

measured

through Sep 12
median ttft
477ms
median tok/s
127.0
blended /1M
$0.61
cache hit
67.8%
answered
99.90%

Weekly aggregates from production traffic routed through Requesty to this endpoint. A metric with no qualifying sample is left out rather than filled in. Compare against the other providers

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
Math Index83.7
AIME 202583.7
MMLU Pro76.0
GPQA Diamond67.2
LiveCodeBench61.5
τ²-Bench54.7
Coding Index43.9
SciCode42.2
Terminal-Bench Hard27.3
Intelligence Index17.6
Humanity's Last Exam10.4
11 evalsmean51.7

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-10-15.

policy

data terms
retention
none
trains on prompts
no
hosted in
US

Terms are the provider's, not Requesty's: routing a request here puts it under them. Vertex AI Data Governance

Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.

quickstart

openai compatible
vertex/claude-haiku-4-5

this id pins the google llc (vertex ai) deployment, with no routing and no failover. the managed id on the canonical page routes across all 3 providers instead

main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="vertex/claude-haiku-4-5",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models

notes

reference

Claude Haiku 4.5 is Anthropic's fastest and most cost-effective AI model, offering near-frontier intelligence. It matches the coding and computer-use performance of older flagship models like Sonnet 4, but runs at a fraction of the price.

questions 6

How much does claude-haiku-4-5 cost?
claude-haiku-4-5 is priced at $1.00 per million input tokens and $5.00 per million output tokens when accessed via Requesty. Prompt caching is supported, which can cut effective input cost by up to 90% on repeated context. Requesty charges exactly what the upstream provider charges, we don't add markup.
What is the context window of claude-haiku-4-5?
claude-haiku-4-5 has a context window of 200K tokens, with a maximum output of 64K tokens per response. That is roughly 267 words of input you can fit in a single prompt.
How does claude-haiku-4-5 perform on benchmarks?
claude-haiku-4-5 scores 83.7% on Math Index, 83.7% on AIME 2025, 76.0% on MMLU Pro. The benchmarks pane shows every published result, each normalised to 100.
What can claude-haiku-4-5 do?
claude-haiku-4-5 supports vision input, tool calling, extended reasoning, prompt caching, web search, structured outputs (JSON schema), computer use. You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use claude-haiku-4-5 with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "vertex/claude-haiku-4-5". The quickstart pane shows Python, JavaScript and cURL snippets.
Can I run claude-haiku-4-5 through Requesty?
Yes. claude-haiku-4-5 runs through Requesty's OpenAI-compatible API, served from Google LLC (Vertex AI). You do not host the model yourself: point base_url at Requesty, set the model to "vertex/claude-haiku-4-5", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.

more from google llc (vertex ai) 8

Other Google LLC (Vertex AI) endpoints
endpointctxin /M
gemini-3.8-flash1.0M$0.75
gemini-3.8-flash1.0M$0.83
claude-fable-5.11M$11.00
claude-fable-5.11M$10.00
gemini-3.7-flash1.0M$0.83
gemini-3.7-flash1.0M$0.75
claude-opus-51M$5.00
claude-opus-51M$5.50

call claude-haiku-4-5 through one endpoint

One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology

claude-haiku-4-5google llc (vertex ai)in $1.00 /1Mout $5.00 /1Mctx 200Kttft 477mshosted US3 providers serve this model