anomalyco / anomalyco/models.dev

Add BytePlus ModelArk Coding Plan provider (international ap-southeast-1)

Open
#5,857 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
6.9k
Forks
1.7k
Avg merge
3h 21m
Merged PRs (30d)
873

Description

Provider

Please add the international BytePlus ModelArk Coding Plan as a provider distinct from volcengine-coding-plan.

Suggested provider ID: byteplus-coding-plan

  • Name: BytePlus ModelArk Coding Plan
  • OpenAI-compatible API: https://ark.ap-southeast.bytepluses.com/api/coding/v3
  • Anthropic-compatible API: https://ark.ap-southeast.bytepluses.com/api/coding
  • Region: BytePlus international ap-southeast-1 (Johor)
  • Suggested environment variable: BYTEPLUS_CODING_PLAN_API_KEY
  • Suggested npm adapter: @ai-sdk/openai-compatible

This must remain separate from the China Volcengine Coding Plan (https://ark.cn-beijing.volces.com/api/coding/v3) and BytePlus pay-as-you-go ModelArk (https://ark.ap-southeast.bytepluses.com/api/v3). BytePlus warns that the pay-as-you-go base does not consume Coding Plan quota and incurs separate billing.

Official supported aliases

  • dola-seed-2.0-pro
  • dola-seed-2.0-lite
  • dola-seed-2.0-code
  • bytedance-seed-code
  • glm-5.2
  • glm-5.1
  • kimi-k2.5
  • gpt-oss-120b
  • deepseek-v4-flash
  • deepseek-v4-pro
  • ark-code-latest (automatic effect/speed routing)

Sources:

Runtime verification

On 2026-08-30, minimal authenticated calls to the international Coding Plan Anthropic messages endpoint succeeded for every official alias above. ark-code-latest currently resolved to dola-seed-2.0-code.

GET /api/coding/v1/models returns a 55-item general account inventory, not a Coding Plan eligibility catalog:

  • 34 entries were LLM/VLM.
  • 14 versioned LLM/VLM IDs accepted a minimal Coding Plan messages request.
  • 20 versioned LLM/VLM IDs explicitly returned “The requested model does not support the coding plan feature.”
  • Eligible and ineligible entries have the same metadata shape and no plan-eligibility tag.
  • The remaining entries are image, video, embedding, or 3D models.

The official supported-alias list should therefore be authoritative. /v1/models can provide supporting metadata plus authenticated callability checks, but must not be imported unfiltered.

No API keys, account identifiers, response IDs, or quota data are included in this report.

Contributor guide

No contributing guide indexed for this repository

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.

Research direction

Start by locating the existing volcengine-coding-plan provider and the provider/model entry points that define aliases and endpoints. Add the distinct byteplus-coding-plan configuration using the official aliases and verify that it remains separate from the China and pay-as-you-go providers; no specific test file is named in the issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
api, backend
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
68/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.