Skip to content

feat(openai): add new models [bot] #978

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
models-bot wants to merge 3 commits into from
Closed

feat(openai): add new models [bot] #978

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e546875
feat(openai): add new models [bot]
May 8, 2026
39abcc2
feat(openai): update model YAMLs [bot]
May 8, 2026
728ac78
change mode
harshiv-26 May 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 35 additions & 0 deletions providers/openai/gpt-realtime-2.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
costs:
- cache_read_input_audio_token_cost: 4e-7
cache_read_input_token_cost: 4e-7
input_cost_per_audio_token: 0.000032
input_cost_per_image_token: 0.000005
input_cost_per_token: 0.000004
output_cost_per_audio_token: 0.000064
output_cost_per_token: 0.000024
region: "*"
features:
- function_calling
- system_messages
- tool_choice
- prompt_caching
limits:
context_window: 128000
max_output_tokens: 32000
max_tokens: 32000
modalities:
input:
- text
- audio
- image
output:
- text
- audio
mode: realtime
model: gpt-realtime-2
Comment thread
cursor[bot] marked this conversation as resolved.
Comment thread
cursor[bot] marked this conversation as resolved.
provisioning: serverless
sources:
- https://developers.openai.com/api/docs/models/gpt-realtime-2
status: active
supportedModes:
- realtime
thinking: true
Copy link
Copy Markdown

@cursor cursor Bot May 8, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thinking model missing removeParams and max_completion_tokens config

Medium Severity

gpt-realtime-2 sets thinking: true but lacks removeParams and a params entry for max_completion_tokens. Every other OpenAI thinking model (o1, o3, o4-mini, gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-codex, gpt-5-pro, computer-use-preview) removes at least max_tokens and usually temperature/top_p via removeParams, and adds max_completion_tokens to params. Without these, the model inherits temperature, max_tokens, top_p, n, etc. from default.yaml, which thinking/reasoning models typically don't support.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 39abcc2. Configure here.

27 changes: 27 additions & 0 deletions providers/openai/gpt-realtime-translate.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
costs:
- input_cost_per_second: 0.0005666666666666667
region: "*"
limits:
context_window: 16000
max_output_tokens: 2000
max_tokens: 2000
modalities:
input:
- audio
output:
- audio
- text
mode: realtime
model: gpt-realtime-translate
params:
- defaultValue: 128
key: max_tokens
maxValue: 2000
minValue: 1
provisioning: serverless
sources:
- https://developers.openai.com/api/docs/models/gpt-realtime-translate
status: active
supportedModes:
- realtime
- audio_translation
Copy link
Copy Markdown

@cursor cursor Bot May 8, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Translation model missing removeParams for tool-related parameters

Medium Severity

gpt-realtime-translate has no features (no function calling) and no removeParams, so it inherits tool_choice and parallel_tool_calls from default.yaml. Every other OpenAI audio model without function calling — including gpt-realtime-whisper added in this same PR, plus whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe, and gpt-4o-transcribe-diarize — removes these params via removeParams. This translation-only model shouldn't expose tool-related parameters.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 39abcc2. Configure here.

25 changes: 25 additions & 0 deletions providers/openai/gpt-realtime-whisper.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
costs:
- input_cost_per_second: 0.0002833333333333333
region: "*"
limits:
context_window: 16000
max_output_tokens: 2000
max_tokens: 2000
modalities:
input:
- text
- audio
output:
- text
mode: realtime
model: gpt-realtime-whisper
provisioning: serverless
removeParams:
- tool_choice
- parallel_tool_calls
Comment thread
harshiv-26 marked this conversation as resolved.
sources:
- https://developers.openai.com/api/docs/models/gpt-realtime-whisper
status: active
supportedModes:
- audio_transcription
- realtime
Loading