feat(frontend): add GPT-5.6 models and pricing

[shay-wong]

Summary

• Add gpt-5.6, gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna to the bundled OpenAI model catalog.
• Include reasoning support, model families, release metadata, input modalities, 1.05M context windows, 922K input limits, and 128K maximum output.
• Include base pricing, cached-input pricing, cache-write pricing, long-context tier pricing, and fast/pro mode metadata in the provider catalog.
• Extend the provider schema so the bundled catalog preserves GPT-5.6 metadata such as structured output, tiered pricing, experimental modes, and extra capabilities.

Why

The GPT-5.6 family is available from OpenAI and already present in the upstream provider-pricing source, but it is missing from AxonHub's bundled developer catalog. As a result, these model IDs are not available in the Add Model selector when the remote catalog has not yet been synchronized.

Pricing

Base pricing in USD per 1M tokens:

Model	Input	Cached input	Cache write	Output
GPT-5.6 / GPT-5.6 Sol	$5.00	$0.50	$6.25	$30.00
GPT-5.6 Terra	$2.50	$0.25	$3.125	$15.00
GPT-5.6 Luna	$1.00	$0.10	$1.25	$6.00

Long-context tier pricing metadata is included for contexts over 272K tokens:

Model	Input	Cached input	Cache write	Output
GPT-5.6 / GPT-5.6 Sol	$10.00	$1.00	$12.50	$45.00
GPT-5.6 Terra	$5.00	$0.50	$6.25	$22.50
GPT-5.6 Luna	$2.00	$0.20	$2.50	$9.00

Cache writes are billed at 1.25x the uncached input-token rate.

Official reference: https://developers.openai.com/api/docs/models

Validation

• Parsed providers.json successfully.
• Confirmed exactly one entry for gpt-5.6, gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna.
• Confirmed base pricing, cached-input pricing, cache-write pricing, long-context tier pricing metadata, and fast/pro metadata.
• Confirmed provider schema preserves the newly added catalog metadata.
• Ran git diff --check.

[greptile-apps]

Greptile Summary

This PR adds GPT-5.6 models to the bundled OpenAI catalog. The main changes are:

• New GPT-5.6, Sol, Terra, and Luna model entries.
• Pricing metadata for base, cached, cache-write, and long-context usage.
• Schema support for richer provider catalog fields.

Confidence Score: 4/5

This is close, but the long-context pricing path should be fixed before merging.

• GPT-5.6 long-context rates are present in the catalog.
• The price generation path can still save only flat base rates.
• High-context GPT-5.6 usage can be billed below the configured catalog rate.

Provider pricing schema and channel price generation.

Important Files Changed

Filename	Overview
frontend/src/features/models/data/providers.json	Adds the GPT-5.6 family entries with limits, capabilities, modes, and pricing metadata.
frontend/src/features/models/data/providers.schema.ts	Extends provider validation so the new catalog metadata can be loaded.

_{Reviews (3): Last reviewed commit: "feat(frontend): add GPT-5.6 models and p..." | Re-trigger Greptile}

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: cf20d134f4

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".