modelbenchmark.io

GPT-3.5 Turbo Instruct

OpenAI · gpt-3-5-turbo-instruct

Compare

Compact GPT model for low-latency assistance and high-volume workloads

Specification

most-agreed values

Context
4K
Max output
4K
Released
2023-09-21
Knowledge cutoff
2021-08
Retires
2026-09-28
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.50
Output
$2.00

Available from 8 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
poe$1.40$1.804K1K
azure$1.50$2.004K4K
azure_text$1.50$2.004K
azure-cognitive-services$1.50$2.004K4K
kilo$1.50$2.004K4K
openrouter$1.50$2.004K4K
text-completion-openai$1.50$2.008K
4K
4K
2026-09-28
vercel_ai_gateway · vercel-ai-gateway$1.50$2.008K4K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterInput$1.50
2026-09-06openrouterInput$1.50
2026-09-02openrouterOutput$2.00
2026-09-06openrouterOutput$2.00

Other listings of this model

same model, different key

More from OpenAI

most-hosted first