Add QuickSilver Pro provider (DeepSeek V3 + R1)#5659
Open
raullenchai wants to merge 1 commit into
Open
Conversation
QuickSilver Pro (https://quicksilverpro.io) is an OpenAI-compatible inference API reselling open-source LLMs. Adds: - packages/cost/models/providers/quicksilverpro.ts — BaseProvider impl - Registered in providers/index.ts, priorities.ts (priority 4), provider-helpers.ts lookup, and getUsageProcessor.ts (OpenAI-compat) - deepseek-v3:quicksilverpro — $0.24 in / $0.70 out per 1M tokens - deepseek-reasoner:quicksilverpro — $0.40 in / $1.70 out per 1M tokens ptbEnabled: false — no pass-through billing partnership; users bring their own QuickSilver Pro API key (BYOK). Qwen3.5-35B-A3B endpoint is also offered upstream but omitted here — Helicone's model registry doesn't yet include Qwen3.5-35B-A3B. Happy to add it in a follow-up if the maintainers want the Qwen entry created under authors/alibaba/. Disclosure: I help operate QuickSilver Pro. Submitting per the reseller-friendly precedent set by DeepInfra / Novita / Chutes / Cerebras entries already in the registry.
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
|
@raullenchai is attempting to deploy a commit to the Helicone Team on Vercel. A member of the Team first needs to authorize it. |
|
The latest updates on your projects. Learn more about Vercel for GitHub. 1 Skipped Deployment
|
Author
|
Hi @colegottdank / @chitalian — friendly nudge. Looks like the Vercel preview is pending team authorization. Happy to rebase if needed. The addition slots alongside the existing DeepInfra / Chutes / Novita / Cerebras budget-reseller entries. Thanks! |
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
Adds QuickSilver Pro as a provider in the Model Registry v2, so Helicone users who route DeepSeek V3 or DeepSeek R1 traffic through QuickSilver Pro get correct cost attribution.
QuickSilver Pro is an OpenAI-compatible inference API reselling open-source LLMs at 20% below the per-token rates of OpenRouter / Together AI / Fireworks AI / DeepInfra on the same models.
What this PR adds
packages/cost/models/providers/quicksilverpro.ts— `BaseProvider` implementation. OpenAI-compatible endpoint at `https://api.quicksilverpro.io/v1/chat/completions\`, Bearer auth.What this PR does NOT add
Disclosure
I help operate QuickSilver Pro (MachineFi Inc., Menlo Park, CA). Submitting per the reseller-friendly precedent set by the existing DeepInfra / Novita / Chutes / Cerebras / Baseten entries. Happy to iterate on naming or scope.
Test plan