anomalyco / anomalyco/models.dev

Request: Add Volcengine Ark (火山方舟) as a provider for DeepSeek V4 Flash and other models

Open
#3,742 1 comment 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

Request: Add Volcengine Ark (火山方舟 / 火山引擎) as a provider

Provider name: Volcengine Ark (火山方舟)

Description:
Volcengine Ark (Volcano Engine / 火山方舟) is ByteDance's AI model inference platform. It offers both pay-as-you-go and subscription-based (Coding Plan, Agent Plan) pricing for various models including DeepSeek V4 Flash, DeepSeek V4 Pro, Qwen series, Kimi K2.5, and ByteDance's own Doubao models.

API details:

Reason:
Volcengine Ark is a major inference platform in China with significant market share, hosting both third-party models (DeepSeek, Kimi, Qwen, GLM) and first-party Doubao models. It offers competitive subscription-based pricing (Coding Plan at ¥40-200/month, Agent Plan) that provides significant discounts vs pay-as-you-go. Currently models.dev only lists Alibaba (China) and SiliconFlow (China) as Chinese providers.

Suggested provider ID: \ olcengine-ark\ or \ olcengine\

Sample models:

  • \deepseek-v4-flash\ (DeepSeek V4 Flash)
  • \deepseek-v4-pro\ (DeepSeek V4 Pro)
  • \kimi-k2.5\ (Moonshot Kimi K2.5)
  • \doubao-pro\ (Doubao Pro / 豆包)
  • \doubao-vision-pro\ (Doubao Vision Pro)
  • Various Qwen, GLM models

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 in the models.dev repository by comparing the existing Alibaba and SiliconFlow provider entries, then trace how provider models are represented. Add Volcengine Ark with the documented endpoints and requested sample models, and confirm the provider and model metadata is complete and consistent with those existing entries.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
ai, data
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.