fix(byteplus): use standard ModelArk endpoint, not Coding Plan endpoint#2573
Open
blazingbunny wants to merge 1 commit into
Open
fix(byteplus): use standard ModelArk endpoint, not Coding Plan endpoint#2573blazingbunny wants to merge 1 commit into
blazingbunny wants to merge 1 commit into
Conversation
The byteplus provider is tagged category: "freeTier" but its transport.baseUrl points at /api/coding/v3/chat/completions, which requires a separate paid Coding Plan subscription (Lite $10/mo or Pro $50/mo). Accounts on the free "Free Credits Only Mode" (500k tokens/model) without a Coding Plan subscription get every request rejected with 400 InvalidSubscription, regardless of free quota remaining. The sibling volcengine-ark.js registry entry uses the same /api/coding/v3 path but is correctly tagged category: "apikey" -- byteplus.js looks copy-pasted from it without updating the endpoint for the free tier. Switching to /api/v3/chat/completions (the standard ModelArk Chat/inference endpoint, same host, same auth) makes the free per-model token pool usable with no Coding Plan subscription required. Verified against a live account: same API key, same model IDs, request succeeds end-to-end where the coding endpoint returned 400 InvalidSubscription.
7 tasks
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
byteplusprovider registry entry (open-sse/providers/registry/byteplus.js) is taggedcategory: "freeTier", but itstransport.baseUrlpoints at/api/coding/v3/chat/completions— an endpoint gated behind a separate paid Coding Plan subscription (Lite $10/mo or Pro $50/mo).400 InvalidSubscription, regardless of free quota remaining.volcengine-ark.jsentry uses the same/api/coding/v3path but is correctly taggedcategory: "apikey"— this file looks copy-pasted from it without updating the endpoint for the free tier.Fix
Switch to
/api/v3/chat/completions— the standard ModelArk Chat/inference endpoint, same host, same auth (Bearer API key). This makes the free per-model token pool actually usable with no Coding Plan subscription required.Verification
Tested against a live BytePlus account on Free Credits Only Mode with no Coding Plan subscription, same API key and model IDs (
seed-2-0-pro-260328):/api/coding/v3/chat/completions):400 {"error":{"code":"InvalidSubscription",...}}/api/v3/chat/completions): request succeeds end-to-end (verified via a duplicate custom OpenAI-compatible connector pointed at the fixed URL, before applying this change to the registry file directly).