Provider proposal: ModelFold preset and setup documentation

Open
#13,476 2 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 8 days

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
55/100
Issue type
Documentation
Clarity
Mostly clear
Activity status
Active
Tech stack
typescript
Domain
ai, documentation

Research direction

Read the CONTRIBUTING guide and the existing provider implementations under core/llm/llms and setup guides under docs/customize/model-providers/more. Map the three documented API surfaces and their model discovery paths to the repository’s provider patterns; validate capabilities per endpoint before documenting them. Done means maintainers approve the proposal and the guide describes verified setup and capabilities without implying universal feature parity.

Written by the indexing model from the issue text.

Description

Proposed enhancement

Please consider a ModelFold provider preset/setup guide, subject to maintainer approval. Your CONTRIBUTING guide asks for an issue before code and documents new providers in core/llm/llms plus setup docs in docs/customize/model-providers/more.

The issue chooser points feature requests to Discussions, but the repository currently exposes no discussion categories through GitHub's API. I am using the CONTRIBUTING guide's explicit issue route rather than submitting an unsolicited implementation. A custom OpenAI/Anthropic configuration remains the alternative. Coding-agent tool calls and streaming must be validated per endpoint before enabling those capabilities.

Submitted from ModelFold's brand account (AIModelFold), with AI assistance; this is a provider-affiliated request.

ModelFold is a third-party API aggregator. Public documentation: https://modelfold.ai/docs/ ; published chat catalog: https://modelfold.ai/docs/models/chat/ .

  • OpenAI-style Chat Completions: base URL https://modelfold.ai/v1, POST /chat/completions.
  • Anthropic Messages: base URL https://modelfold.ai/anthropic, POST /v1/messages.
  • OpenAI Responses is a separate surface: base URL https://modelfold.ai/openai/v1, POST /responses.
  • Model discovery requires the user's own ModelFold key: GET /v1/models, /anthropic/v1/models, or /openai/v1/models, respectively. The catalogs are not interchangeable. The public chat catalog includes gpt-5-2 and claude-sonnet-4-6; these are published examples, not a live authenticated model-list verification.

Scope/verification: documentation returned HTTP 200; unauthenticated GET /v1/models returned HTTP 401 as expected. No paid inference or end-to-end client test was performed for this request. Chat Completions streaming varies by model/route; please do not infer universal streaming, tools, embeddings, or full OpenAI feature parity. Any eventual preset should advertise only verified model/endpoint capabilities.

Dominant language
TypeScript
Stars
36.5k
Forks
5.6k
PR merge metrics
No merged PRs in 30d

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from continuedev/continue

All issues in continuedev/continue

Similar issues

More TypeScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.