Requesty
Sign in

identity

endpoint
AWS Bedrock logo

gpt-5.4AWS Bedrock @us-east-1

in /1M$2.75input tokens
out /1M$16.50output tokens
context1.1M128K out
median ttft1.49smeasured
api
chat
hosting
US
model lab
OpenAI
weights
closed
added
March 2026
model id
bedrock/gpt-5.4@us-east-1

capabilities 5/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

3 providers serve gpt-5.4. This page is one of them. Compare all endpoints

pricing

no markup
input
$2.75
output
$16.50
cache write
-
cache read
$0.28

worked cost

Estimated cost for three request volumes
volumecost
100K in + 10K out$0.44
1M in + 100K out$4.40
10M in + 1M out$44.00

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
1.49s
median tok/s
82.0
blended /1M
$2.75
cache hit
23.4%
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
GPQA Diamond92.0
τ²-Bench87.1
Coding Index71.1
Terminal-Bench Hard57.6
Humanity's Last Exam43.7
Intelligence Index39.0
6 evalsmean65.1

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 2026-03-05.

policy

data terms
retention
none
trains on prompts
no
hosted in
US
deployment
us-east-1

Terms are the provider's, not Requesty's: routing a request here puts it under them. AWS Privacy Notice

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

quickstart

openai compatible
bedrock/gpt-5.4@us-east-1

this id pins the aws bedrock 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="bedrock/gpt-5.4@us-east-1",    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

GPT-5.4 is OpenAI's latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.

questions 7

How much does gpt-5.4 cost?
gpt-5.4 is priced at $2.75 per million input tokens and $16.50 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 gpt-5.4?
gpt-5.4 has a context window of 1.1M tokens, with a maximum output of 128K tokens per response. That is roughly 1,400 words of input you can fit in a single prompt.
How does gpt-5.4 perform on benchmarks?
gpt-5.4 scores 92.0% on GPQA Diamond, 87.1% on τ²-Bench, 71.1% on Coding Index. The benchmarks pane shows every published result, each normalised to 100.
What can gpt-5.4 do?
gpt-5.4 supports vision input, tool calling, extended reasoning, prompt caching, structured outputs (JSON schema). You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use gpt-5.4 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 "bedrock/gpt-5.4@us-east-1". The quickstart pane shows Python, JavaScript and cURL snippets.
Can I run gpt-5.4 through Requesty?
Yes. gpt-5.4 runs through Requesty's OpenAI-compatible API, served from AWS Bedrock in us-east-1. You do not host the model yourself: point base_url at Requesty, set the model to "bedrock/gpt-5.4@us-east-1", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.
What region is this deployment?
This variant of gpt-5.4 is deployed in us-east-1. Region-specific endpoints matter for data residency, latency to your users, and compliance requirements such as GDPR and HIPAA. Other regions for the same model are listed on the canonical model page.

more from aws bedrock 8

Other AWS Bedrock endpoints
endpointctxin /M
claude-opus-51M$5.50
claude-opus-51M$5.50
claude-opus-51M$5.50
claude-opus-51M$5.50
claude-opus-51M$5.00
gpt-5.6-sol1.1M$4.40
gpt-5.6-terra1.1M$2.20
gpt-5.6-terra1.1M$2.20

call gpt-5.4 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

gpt-5.4aws bedrockin $2.75 /1Mout $16.50 /1Mctx 1.1Mttft 1.49shosted US3 providers serve this model