This repository was archived by the owner on May 15, 2026. It is now read-only.
feat: add Kyma API as built-in provider - #12097
Open
sonpiaz wants to merge 1 commit into
Open
Conversation
Kyma API (kymaapi.com) is an OpenAI-compatible LLM gateway with 20+ open-source models, free credits on signup, and pay-per-token billing. - Add KymaHandler extending BaseOpenAiCompatibleProvider - Register 8 top models (qwen-3.6-plus, deepseek-v3/r1, kimi-k2.5, gemma-4-31b, llama-3.3-70b, qwen-3-32b, minimax-m2.5) - Add kymaApiKey to provider settings schema and secret storage - Add Kyma settings UI component with API key input - Wire into buildApiHandler switch, PROVIDERS list, and model config
sonpiaz
requested review from
cte,
daniel-lxs,
hannesrudolph,
jr and
mrubens
as code owners
April 11, 2026 00:26
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 provides access to 20+ open-source models through a single endpoint, with free credits on signup and pay-per-token billing after.
https://kymaapi.com/v1ky-)/v1/chat/completions,/v1/models)What this PR adds
KymaHandlerextendingBaseOpenAiCompatibleProvider(same pattern as SambaNova/Fireworks)qwen-3.6-plus— top overall quality (128K ctx)deepseek-v3— GPT-4-class coding at very low cost, supports prompt caching (128K ctx)deepseek-r1— strong open reasoning model (128K ctx)kimi-k2.5— multimodal agentic model with tool use (131K ctx)gemma-4-31b— Google's latest multimodal open model (131K ctx)llama-3.3-70b— most popular open model (131K ctx)qwen-3-32b— top coding model (131K ctx)minimax-m2.5— SWE-bench 80.2% (131K ctx)kymaApiKeyadded to provider settings schema and secret storagebuildApiHandler,PROVIDERSlist, model config utils, anduseSelectedModelkymaApiKeyandgetKymaApiKeyWhy Kyma API
Test plan
pnpm --filter @roo-code/types build✅turbo check-types) ✅turbo lint) ✅ky-...API key and selecting a model works end-to-end🤖 Generated with Claude Code
Interactively review PR in Roo Code Cloud