feat: add 5.5 models to gateway#5673
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
This pull request has been ignored for the connected project Preview Branches by Supabase. |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
|
This pull request has been ignored for the connected project Preview Branches by Supabase. |
|
Claude finished @H2Shami's task —— View job PR Review: Add 5.5 models to gatewayTodo List:
Score: 3/10 - Critical integration issue prevents models from being discoverable, plus several other important fixes needed. Critical Issues Found🚨 Models Not Integrated into RegistryFile:
// Add to imports
import { models as gpt55Models } from "./gpt-5.5/models";
import { endpoints as gpt55Endpoints } from "./gpt-5.5/endpoints";
// Add to model aggregation (line 47)
export const openaiModels = {
...gpt54Models,
...gpt55Models, // Add this line
...ossModels,
...gptImage1Models,
} satisfies Record<string, ModelConfig>;
// Add to endpoint aggregation (line 62)
export const openaiEndpointConfig = {
...gpt54Endpoints,
...gpt55Endpoints, // Add this line
...ossEndpoints,
...gptImage1Endpoints,
} satisfies Record<string, ModelProviderConfig>;Major IssuesInconsistent Model PatternFile:
export const models = {
"gpt-5.5": {
name: "OpenAI GPT-5.5",
// ... existing config
},
"gpt-5.5-2026-04-23": { // Add this entry
name: "OpenAI GPT-5.5",
author: "openai",
description: "GPT-5.5 is our newest frontier model for the most complex professional work...",
contextLength: 1_050_000,
maxOutputTokens: 128_000,
created: "2026-04-23T00:00:00.000Z",
modality: { inputs: ["text", "image"], outputs: ["text"] },
tokenizer: "GPT",
pinnedVersionOfModel: "gpt-5.5",
},
} satisfies Record<string, ModelConfig>;Type Name InconsistencyFiles:
import { GPT55ModelName } from "./models"; // Fix import nameMinor IssuesProvider Model ID InconsistencyFile:
Missing Provider SupportFile:
Code Quality NotesGood Practices Followed:
PTB Intentionally Disabled:
Security & Performance
Suggestions Summary:Critical (Must Fix):
Important (Should Fix):
Nice to Have:
|
There was a problem hiding this comment.
Pull request overview
This PR adds cost-model registry entries intended to introduce OpenAI GPT‑5.5 into Helicone’s packages/cost model catalog (models + provider endpoints) so the gateway/registry can price and route the model consistently.
Changes:
- Adds a new OpenAI author sub-registry for
gpt-5.5model metadata. - Adds provider endpoint configs for
gpt-5.5for OpenAI and OpenRouter, including pricing + supported parameter lists.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 7 comments.
| File | Description |
|---|---|
| packages/cost/models/authors/openai/gpt-5.5/models.ts | Introduces GPT‑5.5 model metadata entries. |
| packages/cost/models/authors/openai/gpt-5.5/endpoints.ts | Introduces provider endpoint configs (OpenAI/OpenRouter) for GPT‑5.5 including pricing/limits/params. |
Comments suppressed due to low confidence (1)
packages/cost/models/authors/openai/gpt-5.5/models.ts:20
- This gpt-5.5 models registry includes a "gpt-5.4-2026-03-05" entry, which appears to be copied from the gpt-5.4 folder and would incorrectly expose a 5.4 model under the 5.5 author path. Replace this with the appropriate gpt-5.5 versioned model key (e.g., "gpt-5.5-2026-04-23") and ensure pinnedVersionOfModel references "gpt-5.5".
"gpt-5.4-2026-03-05": {
name: "OpenAI GPT-5.4",
author: "openai",
description:
"GPT-5.4 is our frontier model for complex professional work. Reasoning.effort supports: none (default), low, medium, high and xhigh. Features a 1.05M context window and 128K max output tokens with improvements in general intelligence, instruction following, accuracy, multimodality, code generation, tool calling, and context management over GPT-5.2.",
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Ticket
Link to the ticket(s) this pull request addresses.
Component/Service
What part of Helicone does this affect?
Type of Change
Deployment Notes
Screenshots / Demos
Extra Notes
Any additional context, considerations, or notes for reviewers.
Context
Why are you making this change?
Screenshots / Demos