feat: add Kyma API models (via OpenAI-compatible endpoint)#5019
Open
sonpiaz wants to merge 1 commit intoAider-AI:mainfrom
Open
feat: add Kyma API models (via OpenAI-compatible endpoint)#5019sonpiaz wants to merge 1 commit intoAider-AI:mainfrom
sonpiaz wants to merge 1 commit intoAider-AI:mainfrom
Conversation
Adds model metadata and behavioral settings for 8 Kyma API models. Kyma API (kymaapi.com) is an OpenAI-compatible LLM gateway serving open-source models under a single endpoint. Usage: set --openai-api-base https://kymaapi.com/v1 and use any of the model names listed below.
|
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Kyma API is an OpenAI-compatible LLM gateway that serves open-source models under a single unified endpoint. Users can access it by setting:
This PR adds model metadata and behavioral settings for 8 top Kyma models so that Aider can correctly price tokens, set context limits, and use optimal edit formats.
Models added
openai/qwen-3.6-plusopenai/deepseek-v3openai/deepseek-r1openai/kimi-k2.5openai/gemma-4-31bopenai/qwen-3-32bopenai/llama-3.3-70bopenai/minimax-m2.5Files changed
aider/resources/model-metadata.json— token costs, context limits, capability flagsaider/resources/model-settings.yml—diffedit format,use_repo_map: true,examples_as_sys_msg: true,max_tokens: 8192All models use
diffedit format and repo map, matching the pattern used for similar-tier models in the file.References
/v1/chat/completionsendpoint