Verified claim · AI-ML · 100% confidence
GPT-4 Turbo context window tokens: 128000.
Last verified 2026-05-16 · Methodology veritas-v0.1 · 26314e3164e18b24
Structured fields
- Subject
- GPT-4 Turbo
- Predicate
context_window_tokens- Object
- 128000
- Confidence
- 100%
- Tags
- gpt-4-turbo · context · openai · 128k · devday
Sources (2)
[1] official blog · OpenAI · 2023-11-06
New models and developer products announced at DevDay“GPT-4 Turbo … supports up to 128K tokens of context — equivalent to more than 300 pages of text in a single prompt.”
[2] docs · OpenAI
OpenAI GPT-4 Turbo model documentation
Cite this claim
Ready-to-paste citation (Markdown / plain text):
GPT-4 Turbo context window tokens: 128000. — SourceScore Claim 26314e3164e18b24 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/26314e3164e18b24.jsonEmbed this claim
Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.
<iframe src="https://sourcescore.org/embed/claim/26314e3164e18b24/" width="100%" height="360" frameborder="0" loading="lazy" title="GPT-4 Turbo context window tokens: 128000."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
GPT-4o context window tokens: 128000.
118226d52c6f7491 · 100% confidence · shares 3 tags (context, openai, 128k)
InstructGPT methodology introduced in paper: Training language models to follow instructions with human feedback (Ouyang et al., 2022).
5da8f8dffc038b8e · 100% confidence · shares 1 tag (openai)
CLIP (Contrastive Language-Image Pretraining) introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021).
85a3ca745eaf4ee0 · 100% confidence · shares 1 tag (openai)
ChatGPT released on: 2022-11-30.
8d653880c519a8ef · 100% confidence · shares 1 tag (openai)
GPT-4 released on: 2023-03-14.
09eea8fb1a8ccebf · 100% confidence · shares 1 tag (openai)
Use this claim in your code
Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.
cURL
curl https://sourcescore.org/api/v1/claims/26314e3164e18b24.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/26314e3164e18b24.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "GPT-4 Turbo context window tokens: 128000."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/26314e3164e18b24.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "GPT-4 Turbo context window tokens: 128000."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_gpt_4_turbo_fact() -> dict:
"""Fetch the verified SourceScore claim for GPT-4 Turbo."""
r = httpx.get("https://sourcescore.org/api/v1/claims/26314e3164e18b24.json")
return r.json()