feat(models): add GPT-6 Astra and refresh OpenAI model pricing

[waleedlatif1]

Summary

• add GPT-6 Astra as the recommended OpenAI model and refresh every OpenAI catalog entry against current provider documentation
• model long-context pricing as reusable request-size tiers and apply those rates correctly across uncached input, cache reads, cache writes, output, and multi-turn OpenAI executions
• remove truncated dynamic-provider descriptions, make comparison bars share a fixed plotting area, and surface tiered rates on model pages
• regenerate Agent block model documentation and add focused catalog, pricing, usage, and landing-page coverage

Testing

• bun run check
• bun run lint
• bun run type-check
• bun run check:audits
• bun run check:api-validation
• bun run docs-manifest:check
• bun run agent-stream-docs:check
• cd apps/sim && bunx vitest run providers/pricing.test.ts providers/cost-policy.test.ts providers/openai/usage.test.ts providers/models.test.ts providers/utils.test.ts "app/(landing)/models/utils.test.ts"

Change Type

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change
• Documentation update
• Code refactor
• Performance improvement
• Test update

Checklist

• My code follows the project's style guidelines
• I have performed a self-review of my code
• I have added tests that prove my fix is effective or that my feature works
• New and existing tests pass locally with my changes

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Actions	Updated
docs	Skipped		Sep 4, 2026 7:46pm UTC

[greptile-apps]

Greptile Summary

This PR adds GPT-6 Astra as OpenAI’s recommended model, refreshes OpenAI catalog metadata and pricing, introduces reusable long-context pricing tiers, and applies those tiers per provider request across normal, cached, and multi-turn usage. It also surfaces tiered rates on model pages, aligns model-comparison plotting areas, removes truncated provider descriptions, and regenerates related documentation and tests.

• Resolves pricing tiers according to each request’s complete input-token count.
• Preserves zero-cost handling for unregistered dynamic models.
• Replaces inline chart styles with SVG geometry and presentation attributes.
• Expands catalog, pricing, OpenAI usage, and landing-page test coverage.

Confidence Score: 5/5

The PR appears safe to merge; no outstanding correctness, security, or repository-rule violations were identified.

The prior inline-style finding is fully addressed by replacing style props with SVG geometry and presentation attributes, and the subsequent registered-pricing lookup changes preserve zero-cost behavior for unknown dynamic models without disrupting tiered pricing.

Important Files Changed

Filename	Overview
apps/sim/providers/models.ts	Adds GPT-6 Astra and refreshes OpenAI pricing, capabilities, recommendation, and lifecycle metadata.
apps/sim/providers/pricing.ts	Centralizes registered-model pricing lookup and resolves the highest applicable request-size tier.
apps/sim/providers/cost-policy.ts	Applies one resolved pricing tier consistently to uncached input, cache reads, cache writes, and output.
apps/sim/providers/openai/usage.ts	Retains and prices individual OpenAI turns so long-context thresholds are evaluated per provider request.
apps/sim/app/(landing)/models/components/model-comparison-charts.tsx	Replaces inline percentage styles with proportional SVG bars and uses fixed label plotting areas.
apps/sim/app/(landing)/models/utils.ts	Prioritizes recommended models and incorporates tiered rates into pricing bounds and generated FAQs.

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart LR
    U[Provider usage] --> T[Split usage by request]
    T --> P[Resolve registered model pricing]
    P --> S{Input exceeds tier threshold?}
    S -->|No| B[Use base token rates]
    S -->|Yes| L[Use highest matching tier]
    B --> C[Price input, cache, and output]
    L --> C
    C --> A[Aggregate execution cost]

Loading

_{Reviews (3): Last reviewed commit: "fix(models): address catalog review find..." | Re-trigger Greptile}

[cubic-dev-ai]

All reported issues were addressed across 17 files

<sub>Reply with feedback, questions, or to request a fix.

Fix all with cubic | Re-trigger cubic</sub>

[waleedlatif1]

@greptile

[waleedlatif1]

@cubic-dev-ai review this PR

[cubic-dev-ai]

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

[cubic-dev-ai]

All reported issues were addressed across 17 files

<sub>Reply with feedback, questions, or to request a fix.

Fix all with cubic | Re-trigger cubic</sub>

[waleedlatif1]

@greptile

[waleedlatif1]

@cubic-dev-ai review this PR

[cubic-dev-ai]

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

[cubic-dev-ai]

No issues found across 17 files

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

_{Re-trigger cubic}