OpenAI · The Long-Context Stretch
GPT-4 Turbo
128K context, knowledge cutoff updated, cost dropped 3×. The model that made GPT-4 accessible.
By C.W. Jameson · Published 19 May 2026 · Last reviewed 19 May 2026
GPT-4 Turbo landed in November 2023 with a tripled context window, a more recent knowledge cutoff, and a cost reduction that made frontier-quality capability economically viable for production. It was the first time operators could run GPT-4 class inference on high-volume workflows without watching the invoice with anxiety.
Field signature
128K context window on a single API call.
Specifications
| Released | 2023-11 |
|---|---|
| Context window | 128,000 tokens |
| Pricing | $10 / $30 per million tokens (historical; superseded) |
| Modalities | text · image |
| License | Commercial API only |
| Era | The Long-Context Stretch |
Strengths
- 128K context (2023)
- Cost reduction
- Knowledge cutoff
Weaknesses
- Superseded by GPT-4o and GPT-5
Authentication markers
The fingerprints by which GPT-4 Turbo can be identified from its output alone.
| Tell | Meaning |
|---|---|
| Returns 128K context window in the API listing. | GPT-4 Turbo or later. |
Notable works
- Made GPT-4-class inference viable for production volume
Market position
Superseded; was $10-$30 per million tokens
Partner offer
OpenAI's API surface remains the broadest commercial offering.
Try OpenAI →Affiliate link — see disclosure.
Primary sources
From the Almanac shop
The Operator's Compendium
Every agent harness, every routing pattern, every cost trick. 90-page PDF.
$29 — Coming soon