Add NEAR AI Cloud provider#1771
Closed
Evrard-Nil wants to merge 1 commit into
Closed
Conversation
Adds nearai as an OpenAI-compatible provider at https://cloud-api.near.ai/v1 serving 33 models. First-party mirrors (anthropic/openai/google) use `extends`; NEAR-hosted open-weight models (Qwen, GLM-5.1-FP8, gpt-oss, whisper, FLUX) have full definitions. Pricing and context limits sourced from cloud-api.near.ai/v1/models.
Contributor
Author
|
Reopening from the nearai org fork (nearai/models.dev) so the PR is owned by the NEAR AI organization. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds NEAR AI Cloud (
nearai) as a new OpenAI-compatible provider, serving 33 models athttps://cloud-api.near.ai/v1.Approach
anthropic/*,openai/*,google/*) useextendswith overrides only where cloud-api pricing or limits differ from canonical (per the README guidance — wrappers shouldn't duplicate first-party defs).zai-org/GLM-5.1-FP8,openai/gpt-oss-120b,openai/whisper-large-v3,black-forest-labs/FLUX.2-klein-4B) ship with full TOML definitions.Qwen/Qwen3.5-122B-A10B) usesextendsagainst the canonical alibaba entry, with cost/limit overrides for cloud-api pricing and context size.Pricing, context windows, and modalities are sourced from
GET https://cloud-api.near.ai/v1/models.Validation
bun validatepasses locally with exit code 0; the generatednearaientry materialises all 33 models with the expected pricing and limits.Test plan
bun installbun validate(exit 0)