GPT-3.5 Turbo Instruct
Compact GPT model for low-latency assistance and high-volume workloads
Context
4,096
Max output
4,096
Input / 1M
$1.40
Output / 1M
$1.80
Providers
5
01Profile
Profile
Released
2023-09-21
Last updated
2023-09-28
Knowledge cutoff
2021-08
Weights
Closed
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
No
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 5 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
11+ recent events since 2023-09-21
2026-08-25ContextkiloMax output4,096→ 3,685
2026-08-25ContextopenrouterMax output4,096→ 3,685
2026-07-25DeprecatedazureStatus—→ deprecated
2026-07-14Removedvercelofferingremoved→ new
2026-05-15Addedopenrouteroffering→ new
2026-02-16Addedkilooffering→ new
2026-01-10Addedverceloffering→ new
2025-11-20Price uppoeinput / 1M$1.30→ $1.40
2025-11-12ContextpoeContext window4,096→ 3,500
2025-11-10Addedpoeoffering→ new
2025-06-11Addedazureoffering→ new