Skip to content

GPT-4.1

GPT-4.1 is OpenAI's April 2025 general-purpose API model, purpose-built for coding and instruction following with a context window of 1.0M tokens, a 21-point SWE-bench gain over GPT-4o, and a 75% prompt caching discount, at a lower cost than its predecessor.

File InputTool UseVision (Image)
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'openai/gpt-4.1',
prompt: 'Why is the sky blue?'
})

More models by OpenAI

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
1M
3.8s
52tps
$5.00/M
$30.00/M
Read:
$0.5/M
Write:
$10.00/K
+ input costs
azure logo
openai logo
04/24/2026
400K
1.7s
248tps
$0.75/M$4.50/M
Read:$0.07/M
Write:
$10.00/K
+ input costs
azure logo
openai logo
03/17/2026
400K
0.7s
19tps
$0.20/M$1.25/M
Read:$0.02/M
Write:
$10.00/K
+ input costs
azure logo
openai logo
03/17/2026
1.1M
1.1s
59tps
$2.50/M
$15.00/M
Read:
$0.25/M
Write:
$10.00/K
+ input costs
azure logo
openai logo
03/05/2026
128K
0.6s
88tps
$1.25/M$10.00/M
Read:$0.13/M
Write:
$10.00/K
+ input costs
azure logo
openai logo
11/12/2025
131K
0.2s
1089tps
$0.35/M$0.75/M
Read:$0.25/M
Write:
baseten logo
bedrock logo
cerebras logo
+5
08/05/2025