Open
Conversation
bigfluffycookie
commented
Mar 14, 2026
| @@ -4,22 +4,21 @@ import { LanguageModel } from 'ai'; | |||
| import { AiProvider } from '../providers'; | |||
|
|
|||
| const xaiModels = [ | |||
Contributor
Author
There was a problem hiding this comment.
it seems they do remove retired models, its just not super consistent
Contributor
There was a problem hiding this comment.
Pull request overview
Updates the configured model allowlists for multiple AI providers in openops to better align with the AI SDK’s currently-supported/expected model IDs (OPS-3907).
Changes:
- Refresh provider model lists (add new model IDs, remove deprecated/older ones).
- Add new model variants across OpenAI, xAI, Google/Gemini, Vertex, Mistral, Groq, DeepInfra, Cohere, Perplexity, Cerebras.
- Reduce/clean up TogetherAI and some other providers’ older entries.
Reviewed changes
Copilot reviewed 12 out of 12 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
| packages/openops/src/lib/ai/providers/xai.ts | Updates xAI model list (adds Grok 4 variants; removes older Grok 2/3 entries). |
| packages/openops/src/lib/ai/providers/together-ai.ts | Trims TogetherAI model list to a smaller set of currently used IDs. |
| packages/openops/src/lib/ai/providers/perplexity.ts | Adds sonar-deep-research to Perplexity models. |
| packages/openops/src/lib/ai/providers/openai.ts | Refreshes OpenAI model list (adds GPT-5.x and o-series entries; removes older ones). |
| packages/openops/src/lib/ai/providers/mistral.ts | Adds Magistral and Mistral Medium variants. |
| packages/openops/src/lib/ai/providers/groq.ts | Updates Groq model list (adds Llama 4 Maverick, Kimi, GPT-OSS, Qwen3; removes older Llama3/Mistral entries). |
| packages/openops/src/lib/ai/providers/google.ts | Replaces Gemini 1.5/exp entries with newer Gemini 2.x/3.x + latest aliases. |
| packages/openops/src/lib/ai/providers/google-vertex.ts | Updates Vertex model list for Claude + Gemini families (adds/removes entries). |
| packages/openops/src/lib/ai/providers/deep-infra.ts | Significantly expands and reorganizes DeepInfra model list; retains/updates Llama/Qwen/etc. entries. |
| packages/openops/src/lib/ai/providers/cohere.ts | Adds command-a-reasoning-08-2025. |
| packages/openops/src/lib/ai/providers/cerebras.ts | Replaces Cerebras model list with new set including GPT-OSS, Qwen-3, ZAI GLM models. |
| packages/openops/src/lib/ai/providers/anthropic.ts | Updates Anthropic list to newer Claude 4.x family entries (and Haiku 4.5). |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
You can also share your feedback on Copilot code review. Take the survey.
bigfluffycookie
commented
Mar 17, 2026
Contributor
Author
There was a problem hiding this comment.
idk the tests were stupid anyways, and for some reason we only had them for vertex?
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Part of OPS-3907