feat(models): add GPT-5 Pro model definition #994
Conversation
Added definitions for the new GPT-5 Pro model, including pricing, provider details, and capabilities.
❗ Preview Environment deployment failed on BunnyshellSee: Environment Details | Pipeline Logs Available commands (reply to this comment):
|
WalkthroughAdds a new OpenAI model configuration entry with id Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Pre-merge checks and finishing touches✅ Passed checks (3 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
📜 Recent review detailsConfiguration used: CodeRabbit UI Review profile: CHILL Plan: Pro 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (9)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
packages/models/src/models/openai.ts(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{ts,tsx}: This is a pure TypeScript project—do not useanyoras anyunless absolutely necessary
Always use top-level ES imports; never userequireor dynamicimport()
Files:
packages/models/src/models/openai.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Always use top-level import; never use require() or dynamic import()
Files:
packages/models/src/models/openai.ts
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (9)
- GitHub Check: e2e-shards (4)
- GitHub Check: e2e-shards (5)
- GitHub Check: e2e-shards (2)
- GitHub Check: e2e-shards (1)
- GitHub Check: test / run
- GitHub Check: generate / run
- GitHub Check: build / run
- GitHub Check: lint / run
- GitHub Check: autofix
🔇 Additional comments (2)
packages/models/src/models/openai.ts (2)
577-593: Verify whether a second provider should be added.Other GPT-5 family models (gpt-5, gpt-5-mini, gpt-5-nano) have two providers: "openai" and "routeway-discount". This model only has one provider. Please confirm whether this is intentional or if the "routeway-discount" provider should be added for consistency.
If a second provider should be added, refer to the pattern used in gpt-5 (lines 397-421) for the structure.
571-595: Validate GPT-5 Pro pricing and capacity
- Pricing matches official API: $15 / 1M input, $120 / 1M output
- ContextSize 400 000 and maxOutput 272 000 tokens aren’t documented publicly—please confirm in the official model spec docs.
| { | ||
| test: "only", | ||
| providerId: "openai", | ||
| modelName: "gpt-5-pro", | ||
| inputPrice: 15 / 1e6, | ||
| outputPrice: 120.0 / 1e6, | ||
| requestPrice: 0, | ||
| contextSize: 400000, | ||
| maxOutput: 272000, | ||
| streaming: true, | ||
| reasoning: true, | ||
| reasoningOutput: "omit", | ||
| vision: true, | ||
| tools: true, | ||
| }, |
There was a problem hiding this comment.
Add cachedInputPrice consistent with other GPT-5 models.
All other GPT-5 family models (gpt-5, gpt-5-mini, gpt-5-nano) define cachedInputPrice. This model should follow the same pattern if cached input pricing is available.
Apply this diff to add the missing field (assuming 10% of input price as per gpt-5 pattern):
{
test: "only",
providerId: "openai",
modelName: "gpt-5-pro",
inputPrice: 15 / 1e6,
outputPrice: 120.0 / 1e6,
+ cachedInputPrice: 1.5 / 1e6,
requestPrice: 0,📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| { | |
| test: "only", | |
| providerId: "openai", | |
| modelName: "gpt-5-pro", | |
| inputPrice: 15 / 1e6, | |
| outputPrice: 120.0 / 1e6, | |
| requestPrice: 0, | |
| contextSize: 400000, | |
| maxOutput: 272000, | |
| streaming: true, | |
| reasoning: true, | |
| reasoningOutput: "omit", | |
| vision: true, | |
| tools: true, | |
| }, | |
| { | |
| test: "only", | |
| providerId: "openai", | |
| modelName: "gpt-5-pro", | |
| inputPrice: 15 / 1e6, | |
| outputPrice: 120.0 / 1e6, | |
| cachedInputPrice: 1.5 / 1e6, | |
| requestPrice: 0, | |
| contextSize: 400000, | |
| maxOutput: 272000, | |
| streaming: true, | |
| reasoning: true, | |
| reasoningOutput: "omit", | |
| vision: true, | |
| tools: true, | |
| }, |
🤖 Prompt for AI Agents
In packages/models/src/models/openai.ts around lines 578 to 592, the gpt-5-pro
model object is missing the cachedInputPrice field used by other GPT-5 entries;
add cachedInputPrice with the same 10%-of-input-price convention (i.e., set
cachedInputPrice to 1.5 / 1e6 given inputPrice is 15 / 1e6) so the model follows
the same pricing pattern as gpt-5, gpt-5-mini, and gpt-5-nano.
Add supportedParameters array consistent with other GPT-5 models.
All other GPT-5 family models (gpt-5, gpt-5-mini, gpt-5-nano) include a supportedParameters array documenting which API parameters are supported. This model should follow the same pattern.
Apply this diff to add the missing field:
vision: true,
tools: true,
+ supportedParameters: [
+ "temperature",
+ "top_p",
+ "frequency_penalty",
+ "presence_penalty",
+ "response_format",
+ "tools",
+ "tool_choice",
+ ],
},📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| { | |
| test: "only", | |
| providerId: "openai", | |
| modelName: "gpt-5-pro", | |
| inputPrice: 15 / 1e6, | |
| outputPrice: 120.0 / 1e6, | |
| requestPrice: 0, | |
| contextSize: 400000, | |
| maxOutput: 272000, | |
| streaming: true, | |
| reasoning: true, | |
| reasoningOutput: "omit", | |
| vision: true, | |
| tools: true, | |
| }, | |
| { | |
| test: "only", | |
| providerId: "openai", | |
| modelName: "gpt-5-pro", | |
| inputPrice: 15 / 1e6, | |
| outputPrice: 120.0 / 1e6, | |
| requestPrice: 0, | |
| contextSize: 400000, | |
| maxOutput: 272000, | |
| streaming: true, | |
| reasoning: true, | |
| reasoningOutput: "omit", | |
| vision: true, | |
| tools: true, | |
| supportedParameters: [ | |
| "temperature", | |
| "top_p", | |
| "frequency_penalty", | |
| "presence_penalty", | |
| "response_format", | |
| "tools", | |
| "tool_choice", | |
| ], | |
| }, |
🤖 Prompt for AI Agents
In packages/models/src/models/openai.ts around lines 578 to 592, the gpt-5-pro
model entry is missing the supportedParameters array present on other GPT-5
models; add a supportedParameters field for this model immediately inside the
object with the same parameter names and values used by the other GPT-5 family
entries (gpt-5, gpt-5-mini, gpt-5-nano) so the list of supported API parameters
is consistent and follows the same format as those models.
Removed the 'test' property from the OpenAI provider configuration.
1 participant
Added definitions for the new GPT-5 Pro model, including pricing, provider details, and capabilities.
Summary by CodeRabbit
New Features
Chores