feat: add Infer provider with Astra and Sol API options - #6925
Merged
rekram1-node merged 1 commit intoSep 14, 2026
Conversation
Contributor
|
No actionable findings. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Infer is missing from the provider catalog. This adds Infer by Flow7 with two currently available options, GPT-6 Astra and GPT-5.6 Sol, using their exact API selectors and the Responses API surface.
The entries inherit the underlying OpenAI model metadata and override Infer's current prices and serving limits: 271,999 context tokens and 128,000 output tokens. The model-name suffix matches Infer's
Official APIcatalog option. The native effort lists match the OpenAI entries and the same-model relay entries; Infer forwards the Responsesreasoning.effortfield. The provider uses@ai-sdk/openai,INFER_API_KEY, and a monochrome SVG of Infer's mark.Sources, checked September 12, 2026 UTC:
providers/openaiandproviders/openrouterentries for the same models: effort options and underlying model metadata.Validation:
bun validatepasses for the full catalog, and the staged patch passes Git whitespace checks. The generated Infer entries were checked against the retrieved public catalog. No paid inference request was made for this change. This is a provider-data contribution from Infer's side, not a claim of an official OpenCode partnership.