CATCH #1540
DETECTED SEP 22, 2026 18:27 UTC
THE CATCHscore 10/10
EXHIBIT 1540 · FLASH
Sep 22, 2026 18:27 UTC
api_models+openapi+pages+pypi
openai
OpenAI's latest SDK update (3.18.0) and API spec changes reveal new model IDs 'gpt-6-luna' and 'gpt-6-sol', along with an explicit reference to 'gpt-4o-2024-08-06', and new beta features for 'realtime' and 'responses' connections.
✓ VERIFIED — BEAT THE ANNOUNCEMENT BY 0.2H · AUTO-VERIFIED AGAINST OPENAI NEWS
READY TO POST:
looks like openai is prepping gpt-6 'luna' and 'sol' models, spotted in their api spec and openrouter. could be what's next after gpt-4o!
openai's new sdk points to gpt-4o-2024-08-06 and potential 'realtime' and 'responses' beta features. new stuff brewing for developers.
EVIDENCE — the receipts
[MERGED across 4 sources: api_models, openapi, pages, pypi]
shared signal: gpt-4o-2024-08-06, gpt-6, gpt-6-luna, gpt-6-luna-pro, gpt-6-sol, gpt-6-sol-pro
--- api_models :: OpenRouter ---
New model id(s) appeared in OpenRouter's API model list:
https://openrouter.ai/api/v1/models
+ openai/gpt-6-luna
+ openai/gpt-6-luna-pro
+ openai/gpt-6-luna-pro:batch
+ openai/gpt-6-luna:batch
+ openai/gpt-6-sol
+ openai/gpt-6-sol-pro
+ openai/gpt-6-sol-pro:batch
+ openai/gpt-6-sol:batch
A model id in a provider's live API usually predates the public announcement. High-confidence pre-announcement signal.
--- openapi :: https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml ---
OpenAI API spec (https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml): 2 additions to the official API spec
[new models] (2)
+ gpt-6-luna
+ gpt-6-sol
--- pypi :: openai ---
openai 3.17.0 -> 3.18.0: +92 strings, -620 strings, 37 interesting
[model_id] (3)
+ gpt-6-luna
+ gpt-6-sol
+ py
with client.chat.completions.stream(
model="gpt-4o-2024-08-06",
messages=[...],
) as stream:
for event in stream:
if event.type == "content.delta":
print(event.delta, flush=True, end="")
[feature_flag] (4)
+ py
connection = client.beta.realtime.connect(...).enter()
# ...
connection.close()
+ py
connection = client.beta.responses.connect(...).enter()
# ...
connection.close()
+ py
connection = client.beta.realtime.connect(...).enter()
# ...
connection.close()
+ py
connection = client.beta.responses.connect(...).enter()
# ...
connection.close()
[sentence] (35)
+ py
with client.chat.completions.stream(
model="gpt-4o-2024-08-06",
messages=[...],
) as stream:
for event in stream:
if event.type == "content.delta":
caught by the 20-minute sweep ·
the live wire · all receipts