Add Novita as a fourth LLM fallback provider - #475
Conversation
Both smart-ingest and entity-extraction-worker already fall back through OpenRouter -> OpenAI -> Anthropic. Add Novita as a fourth option using its OpenAI-compatible chat completions endpoint, so users who prefer or already hold a Novita key can configure it without needing OpenRouter/OpenAI/Anthropic as well.
The models listed for Novita were older ids that no longer reflect what the platform leads with. Point the recommendations at the three current flagships instead, each verified against api.novita.ai: moonshotai/kimi-k3 1M context, native vision zai-org/glm-5.2 1M context, long-horizon agentic work deepseek/deepseek-v4-flash-0731 1M context, cheapest of the three Context windows, output limits, input modalities and pricing were taken from the live /openai/v1/models response rather than carried over.
deepseek/deepseek-v4-flash-0731 is no longer the live catalog's current DeepSeek general flagship; deepseek/deepseek-v4-pro is.
|
Hey @jax-novita — welcome to Open Brain Source! 👋 Thanks for submitting your first PR. The automated review will run shortly and check things like metadata, folder structure, and README completeness. If anything needs fixing, the review comment will tell you exactly what. Once the automated checks pass, a human admin will review for quality and clarity. Expect a response within a few days. If you have questions, check out CONTRIBUTING.md or open an issue. |
|
Hi, I checked the failed The failure appears to come from the repository workflow rather than from this PR's code. The workflow is triggered by
There are also warnings about the Node.js 20 runtime used by Could you please take a look at the workflow configuration? I believe the PR should be re-run after the workflow is adjusted. I have not changed the application code since the failure is occurring before the review checks can run. |
Contribution Type
/integrations)What does this do?
Adds Novita as a fourth LLM fallback provider (alongside OpenRouter, OpenAI, Anthropic) in
integrations/smart-ingestandintegrations/entity-extraction-worker. Novita exposes an OpenAI-compatible chat completions endpoint, so the newcallNovita()follows the same structure as the existingcallOpenAI().Requirements
NOVITA_API_KEY), optional — only needed if you want Novita as one of your configured LLM providers.Checklist
README.mdwith prerequisites, step-by-step instructions, and expected outcome (updated existing READMEs to mention Novita)metadata.jsonhas all required fields (unchanged; this PR extends an existing integration rather than adding a new one)deno checkanddeno lintpass with no new errors/warnings in both integrations)