Add ai& provider#3327
Open
jethac wants to merge 1 commit into
Open
Conversation
ai& (https://aiand.com) serves open-weight LLMs through an OpenAI-compatible API at https://api.aiand.com/v1, authenticated with a standard Bearer AIAND_API_KEY. Adds the provider plus 9 models verified against ai&'s live catalog page (https://docs.aiand.com/models/catalog/): openai/gpt-oss-120b, qwen/qwen3.6-27b, deepseek-ai/deepseek-v4-flash, deepseek-ai/deepseek-v4-pro, google/gemma-4-31b-it, moonshotai/kimi-k2.6, moonshotai/kimi-k2.7-code, zai-org/glm-5.1, and zai-org/glm-5.2. Each entry reuses existing shared model metadata via base_model and overrides only cost (and, where confirmed, modalities) with figures read from the live catalog table and JSON examples. reasoning_options on every model mirrors the reasoning_effort values ai&'s own Chat Completions docs list (none/minimal/low/medium/high/xhigh). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Contributor
|
Let me check the base model metadata files for reasoning capability and other details. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
ai&(https://aiand.com), which serves open-weight LLMs through an OpenAI-compatible API athttps://api.aiand.com/v1, authenticated with a standard BearerAIAND_API_KEY.openai/gpt-oss-120b,qwen/qwen3.6-27b,deepseek-ai/deepseek-v4-flash,deepseek-ai/deepseek-v4-pro,google/gemma-4-31b-it,moonshotai/kimi-k2.6,moonshotai/kimi-k2.7-code,zai-org/glm-5.1, andzai-org/glm-5.2.base_modeland overrides onlycost(and, where confirmed,modalities) with figures read from the live catalog table.reasoning_optionsmirrors thereasoning_effortvalues documented on ai&'s Chat Completions page (none/minimal/low/medium/high/xhigh).glm-5.1, shown only as a rounded "203K" in the catalog table), the field is left inherited from the shared base model rather than guessed — see the source comment in that file.Test plan
base_modelreference resolves to an existing file undermodels/.bun validate— could not get a clean full-repo run locally: it fails on an unrelated pre-existing broken symlink (providers/zhipuai/models/glm-4.6v-flash.toml→../../zai/models/glm-4.6v-flash.toml, whose target 404s on GitHub too), not on anything in this PR. Happy to re-run once that's fixed, or if there's a way to scope validation to a single provider.🤖 Generated with Claude Code