Skip to content

docs: FAQ entry for custom model pricing in agentic workflow frontmatter#44450

Merged
pelikhan merged 1 commit into
mainfrom
copilot/example-custom-model-pricing
Jul 9, 2026
Merged

docs: FAQ entry for custom model pricing in agentic workflow frontmatter#44450
pelikhan merged 1 commit into
mainfrom
copilot/example-custom-model-pricing

Conversation

Copilot AI commented Jul 9, 2026

Copy link
Copy Markdown
Contributor

No documentation existed for the models.providers frontmatter field, leaving users without guidance on how to supply pricing for custom, private, or enterprise models missing from the models.dev catalog.

Changes

docs/src/content/docs/reference/faq.md — new entry under Costs & Usage:

  • Explains when to use models.providers (unknown models, pricing overrides)
  • Shows the full YAML structure with per-token cost values in scientific notation
  • Engine → provider key mapping table (copilotgithub-copilot, claudeanthropic, etc.)
  • Notes runtime merge behavior and propagation through shared workflow imports

.github/workflows/daily-model-inventory.md — adds models.providers to frontmatter as a working example:

models:
  providers:
    openai:
      models:
        gpt-5-enterprise:
          cost:
            input: "3.75e-06"     # $3.75/M input tokens
            output: "1.5e-05"     # $15.00/M output tokens
            cache_read: "9.375e-07"
            cache_write: "3.75e-06"

Compiles cleanly alongside the existing 259-workflow corpus (0 errors).

…l-inventory example

- Add "How do I supply pricing for a custom or private model?" to the
  Costs & Usage section of faq.md, covering the models.providers YAML
  syntax, per-token cost format, engine-to-provider mapping, and merge
  behavior
- Add models.providers example to daily-model-inventory.md frontmatter
  to demonstrate the feature and ensure it compiles correctly

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
@pelikhan pelikhan marked this pull request as ready for review July 9, 2026 02:24
Copilot AI review requested due to automatic review settings July 9, 2026 02:24
@pelikhan pelikhan merged commit d3fcb9b into main Jul 9, 2026
1 check passed
@pelikhan pelikhan deleted the copilot/example-custom-model-pricing branch July 9, 2026 02:25

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Pull request overview

Adds missing documentation for models.providers so users can supply or override per-token pricing when a model is absent from the embedded models.dev catalog, and includes a workflow frontmatter example to demonstrate compilation/propagation into GH_AW_INFO_MODEL_COSTS.

Changes:

  • Documented models.providers usage and structure in the FAQ, including provider-key mapping and merge behavior.
  • Added a models.providers example block to daily-model-inventory.md frontmatter.
  • Regenerated the compiled .lock.yml to include the serialized GH_AW_INFO_MODEL_COSTS overlay.
Show a summary per file
File Description
docs/src/content/docs/reference/faq.md Adds an FAQ entry explaining how to supply custom model pricing via models.providers.
.github/workflows/daily-model-inventory.md Adds a frontmatter models.providers example to demonstrate custom pricing overlays.
.github/workflows/daily-model-inventory.lock.yml Updates compiled metadata/env to reflect the new frontmatter overlay.

Review details

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

  • Files reviewed: 3/3 changed files
  • Comments generated: 3
  • Review effort level: Low

cache_write: "3.75e-06" # optional
```

Cost values are **per-token USD in scientific notation** (e.g. `3.75e-06` = $0.00000375/token = $3.75 per million tokens). Omit `cache_read` and `cache_write` if the model doesn't support prompt caching.
Comment on lines +29 to +31
# Supply pricing for a private/enterprise model not yet in the models.dev catalog.
# Cost values are per-token USD in scientific notation (e.g. 3e-06 = $3 per million tokens).
# Entries are merged with the built-in models.json at runtime and fill gaps for unknown models.
Comment on lines +32 to +36
models:
providers:
openai:
models:
gpt-5-enterprise:
@github-actions

github-actions Bot commented Jul 9, 2026

Copy link
Copy Markdown
Contributor

🎉 This pull request is included in a new release.

Release: v0.82.7

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants