Models / OpenAI / GPT-3.5-turbo

OpenAI · gpt

GPT-3.5-turbo

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

$0.50 in · $1.50 out

per 1M tokens · first-party price. Reference price from OpenAI, the lab's own listing.

Provider input prices run from $0.50 to $0.65 per 1M tokens. Output prices run from $1.50 to $1.95.

Context
16,385
Max output
4,096
Cache read
$0
Cache write
—
Reasoning
No
Tool calls
No
Structured output
No
Vision
No
Open weights
No
License
—
Released
Mar 1, 2023
Updated in source
Nov 6, 2023
Knowledge
2021-09-01
Providers
12

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
DevPass$0.50$1.50$0——
Eden AI$0.50$1.50———
Impossibl$0.50$1.50———
Kilo Gateway$0.50$1.50———
LLM Gateway$0.50$1.50———
Merge Gateway$0.50$1.50———
NanoGPT$0.50$1.50———
OpenAIreference$0.50$1.50$0—deprecated
OpenRouter$0.50$1.50———
OrcaRouter$0.50$1.50$0——
Vercel AI Gateway$0.50$1.50———
AI/ML API$0.65$1.95———