modelbenchmark.io

GPT-3.5-turbo

OpenAI · gpt-3-5-turbo

Compare

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

Specification

openai listing

Context
16K
Max output
4K
Released
2023-03-01
Knowledge cutoff
2021-09-01
Retires
2026-10-23
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · openai list price

Input
$0.50
Output
$1.50
Cache read
free

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputopenai$0.25
Batch inputopenai$1.00
Batch outputopenai$0.75
Batch outputopenai$2.00

Batch input is 50% below the interactive input price at the same listing.

Quality

5 benchmarks · 1 source

Composite
7th
percentile of 344 scored models
Rank
320 / 344
±0.06 sd
Evidence
5 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning9th2/4 bench
math4th3/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Mystery Game Puzzles3.0 ±1.7defaultEpoch AI2026-08-27
MATH level 513.8 ±0.6default · 2 runsEpoch AI2025-01-27
OTIS Mock AIME 2024-20252.2 ±2.2defaultEpoch AI2026-08-07
GPQA diamond27.6 ±1.9default · 2 runsEpoch AI2025-01-27
FrontierMath-Tiers-1-3-v20.0 ±0.0defaultEpoch AI2026-08-27

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 11 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor
$0.50
$1.00
$1.50
$2.00
free—16K4K
2026-10-23
2026-09-28
poe$0.45$1.40——16K2K—
azure
$0.50
$1.00
$1.50
$2.00
——
16K
4K
4K—
azure-cognitive-services
$0.50
$1.00
$1.50
$2.00
——16K4K—
impossibl$0.50$1.50——16K4K—
merge-gateway$0.50$1.50——16K4K—
orcarouter$0.50$1.50free—16K4K—
vercel_ai_gateway · vercel-ai-gateway$0.50$1.50——16K4K—
kilo$1.00$2.00——4K4K—
openrouter$1.00$2.00——4K4K—
github_copilot · github-copilot————16K4K—

Price history

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

DateHostField$/M
2026-09-02azureInput$1.00
2026-09-24azureInput$0.50
2026-10-28azureInput$1.00
2026-10-31azureInput$0.50
2026-09-02azure-cognitive-servicesInput$0.50
2026-09-24azure-cognitive-servicesInput$1.00
2026-10-20azure-cognitive-servicesInput$0.50
2026-10-28azure-cognitive-servicesInput$1.00
2026-10-31azure-cognitive-servicesInput$0.50
2026-09-02kiloInput$0.50
2026-09-04kiloInput$1.00
2026-09-24kiloInput$0.50
2026-10-19kiloInput$1.00
2026-10-22kiloInput$0.50
2026-10-23kiloInput$1.00
2026-10-25kiloInput$1.00
2026-09-02openrouterInput$0.50
2026-09-04openrouterInput$1.00
2026-09-06openrouterInput$1.00
2026-09-19openrouterInput$1.00
2026-09-24openrouterInput$0.50
2026-10-10openrouterInput$0.50
2026-10-19openrouterInput$1.00
2026-10-22openrouterInput$0.50
2026-10-23openrouterInput$1.00
2026-10-25openrouterInput$1.00
2026-09-02azureOutput$2.00
2026-09-24azureOutput$1.50
2026-10-28azureOutput$2.00
2026-10-31azureOutput$1.50
2026-09-02azure-cognitive-servicesOutput$1.50
2026-09-24azure-cognitive-servicesOutput$2.00
2026-10-20azure-cognitive-servicesOutput$1.50
2026-10-28azure-cognitive-servicesOutput$2.00
2026-10-31azure-cognitive-servicesOutput$1.50
2026-09-02kiloOutput$1.50
2026-09-04kiloOutput$2.00
2026-09-24kiloOutput$1.50
2026-10-19kiloOutput$2.00
2026-10-22kiloOutput$1.50
2026-10-23kiloOutput$2.00
2026-10-25kiloOutput$2.00
2026-09-02openrouterOutput$1.50
2026-09-04openrouterOutput$2.00
2026-09-06openrouterOutput$2.00
2026-09-19openrouterOutput$2.00
2026-09-24openrouterOutput$1.50
2026-10-10openrouterOutput$1.50
2026-10-19openrouterOutput$2.00
2026-10-22openrouterOutput$1.50
2026-10-23openrouterOutput$2.00
2026-10-25openrouterOutput$2.00
2026-10-13aimlapiInput$0.65
2026-10-23aimlapiInput$0.50
2026-10-13aimlapiOutput$1.95
2026-10-23aimlapiOutput$1.50

Other listings of this model

same model, different key

More from OpenAI

most-hosted first