Skip to content

feat: add GPT-5.3-Codex model for GitHub Copilot provider #954

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
emvnuel wants to merge 2 commits into from
+23 −0
Closed

feat: add GPT-5.3-Codex model for GitHub Copilot provider #954

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5442247
feat: add GPT-5.3-Codex model for GitHub Copilot provider
emvnuel Feb 18, 2026
e702a9f
add knowledge cutoff date for GPT-5.3-Codex
emvnuel Feb 18, 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
23 changes: 23 additions & 0 deletions providers/github-copilot/models/gpt-5.3-codex.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
name = "GPT-5.3-Codex"
family = "gpt-codex"
release_date = "2026-02-05"
last_updated = "2026-02-05"
attachment = false
reasoning = true
temperature = false
Copy link

Copilot AI Feb 18, 2026

Choose a reason for hiding this comment

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

Missing 'knowledge' field that is present in almost all other GitHub Copilot model configurations. This field specifies the knowledge cutoff date for the model's training data and should be added for consistency. For reference, gpt-5.2-codex has 'knowledge = "2025-08-31"' and gpt-5.1-codex has 'knowledge = "2024-09-30"'. The field should be placed between the 'temperature' and 'tool_call' fields following the established convention.

Suggested change
temperature = false
temperature = false
knowledge = "2026-02-05"

Copilot uses AI. Check for mistakes.
knowledge = "2025-08-31"
tool_call = true
structured_output = true
open_weights = false

[cost]
input = 0
output = 0

[limit]
context = 400_000
output = 128_000

[modalities]
input = ["text", "image"]
output = ["text"]