feat: add cost and rendering support for gpt-image-1 and gpt-image-1.5

[chitalian]

• Add mapper type detection for gpt-image-1* models to render as openai-image type
• Add cost configuration for gpt-image-1 and gpt-image-1.5 models
• Set ptbEnabled: false for both image models as requested
• Pricing: gpt-image-1.5 at $5/1M input, $10/1M output
• Pricing: gpt-image-1 at $6.25/1M input, $12.50/1M output

[vercel]

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

Project	Deployment	Review	Updated (UTC)
helicone	Ready	Preview, Comment	Jan 21, 2026 8:12pm
helicone-bifrost	Ready	Preview, Comment	Jan 21, 2026 8:12pm
helicone-eu	Ready	Preview, Comment	Jan 21, 2026 8:12pm

[greptile-apps]

Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.

[supabase]

This pull request has been ignored for the connected project bolqqmqbrciybnypvklh because there are no changes detected in supbase/supabase directory. You can change this behaviour in Project Integrations Settings ↗︎.

---

Preview Branches by Supabase.
Learn more about Supabase Branching ↗︎.

[supabase]

This pull request has been ignored for the connected project lmahfbbnchpworytrrqk because there are no changes detected in .supabase/supabase directory. You can change this behaviour in Project Integrations Settings ↗︎.

---

Preview Branches by Supabase.
Learn more about Supabase Branching ↗︎.

[claude]

Claude finished @chitalian's task —— View job

---

PR Review - GPT Image Model Support

Todo List:

• Read and analyze all changed files
• Review cost configuration implementation
• Check mapper type detection logic
• Validate test snapshots
• Provide comprehensive feedback with confidence score

Score: 7/10 - Minor improvements suggested, generally ready to merge

Analysis Summary

This PR adds support for OpenAI's new gpt-image-1 and gpt-image-1.5 models, implementing cost tracking and proper mapper type detection. The implementation follows existing patterns well.

Issues Found:

1. Pricing Inconsistency (Minor)

The snapshot test shows only gpt-image-1.5 pricing, but both models are defined:

In endpoints.ts:

• gpt-image-1: $6.25/$12.50 per 1M tokens
• gpt-image-1.5: $5.00/$10.00 per 1M tokens

In registrySnapshots.test.ts.snap:

"openai/gpt-image-1": {
  "openai": [
    {
      "input": 0.000005,    // This is gpt-image-1.5 pricing
      "output": 0.00001,    // This is gpt-image-1.5 pricing
      "threshold": 0,
    },
  ],
}

Recommendation: The snapshot should include both models' pricing or be regenerated to reflect the actual implementation.

2. Missing Context Information (Minor)

The models have identical specs except pricing:

• contextLength: 8192
• maxOutputTokens: 4096
• rateLimits: { rpm: 500, tpm: 1000000 }

Question: Are these the correct specifications for image generation models? Image models typically have different context/token limitations than chat models.

3. Model Creation Dates (Minor)

In models.ts:

• gpt-image-1: "2025-04-01T00:00:00.000Z"
• gpt-image-1.5: "2025-12-01T00:00:00.000Z"

Recommendation: Verify these are the actual release dates from OpenAI.

Positive Aspects:

✅ Proper Architecture: Follows the established pattern with separate models.ts and endpoints.ts files
✅ Correct Mapper Integration: Added to getMapperType.ts with proper pattern matching for gpt-image-1*
✅ Comprehensive Integration: Properly exported in openai/index.ts
✅ Disabled PTB: Correctly set ptbEnabled: false as requested
✅ Type Safety: Uses proper TypeScript types and satisfies constraints

Code Quality:

• Clean, readable implementation
• Follows existing patterns and conventions
• Proper imports and exports
• Good type definitions

Suggestions:

1. Regenerate test snapshots to ensure they match the actual pricing configuration
2. Verify model specifications (context length, rate limits) with OpenAI documentation
3. Consider adding a comment explaining the different pricing tiers between the two models

Security/Performance:

• No security concerns identified
• No performance implications
• Standard cost calculation patterns used

Ready to merge with minor snapshot validation recommended.