Skip to content

fix: publish gitlab duo-chat-haiku-5-5 in v1 api #11473

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
vglafirov wants to merge 1 commit into from
Closed

fix: publish gitlab duo-chat-haiku-5-5 in v1 api #11473

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 1 addition & 2 deletions providers/gitlab/models/duo-chat-haiku-5-5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,11 +9,10 @@
# Toggle: thinking.type = adaptive|disabled (disabled only at high effort or below). Effort: output_config.effort = low|medium|high|xhigh|max.
# Cost: billed per model call in GitLab Credits ($1 each on demand; claude-haiku-5.5: 8.0 calls per credit, https://docs.gitlab.com/subscriptions/gitlab_credits/).
# v2 has no per-request unit, so token prices stay 0 (calls draw on the subscription's credits).
# New in v2 only (v2_only): added to models.yml on 2026-10-07 (https://gitlab.com/gitlab-org/modelops/applied-ml/code-suggestions/ai-assist/-/commit/f910322e) and mapped by gitlab-ai-provider 6.22.0.
# Added to models.yml on 2026-10-07 (https://gitlab.com/gitlab-org/modelops/applied-ml/code-suggestions/ai-assist/-/commit/f910322e) and mapped by gitlab-ai-provider 6.22.0. Published in v1 (not v2_only) so v1 consumers such as opencode can list it, like the other gitlab models.
# Mid-conversation flags unset: GitLab documents none, and no live test (no GitLab token).
# APIs: gitlab-ai-provider sends Claude to the AI gateway's /ai/v1/proxy/anthropic/v1/messages and OpenAI models to /ai/v1/proxy/openai/v1/chat/completions or /responses (sources in provider.toml).
schema = 2
v2_only = true
base_model = "anthropic/claude-haiku-5-5"
name = "Agentic Chat (Claude Haiku 5.5)"

Expand Down
Loading