Repository navigation
Conversation
Prices are taken from Prentis's published pay-as-you-go rate card, converted to cents per token as CONTRIBUTING.md asks. Companion to the provider PR Portkey-AI/gateway#1880. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Contributor
There was a problem hiding this comment.
🟡 Changes recommended
The pricing calculation omits cached-input charges for 15 models, and the gateway’s default deepseek-v4.1-flash model ID lacks a matching nonzero pricing entry.
2 open issues
What changed in this PR
Adds Prentis pricing data to support cost attribution for the provider proposed in Portkey-AI/gateway#1880.
Changes:
- Adds USD pay-as-you-go input and output rates for 16 models, expressed in cents per token.
- Defines separate cached-input rates for 15 models.
- Includes a zero-price default and shared calculation block; defers general provider configuration.
| File | Description |
|---|---|
pricing/prentis.json |
Adds Prentis model rates and default cost-calculation configuration. |
Review effort: Balanced
Comment on lines
+4
to
+23
| "pay_as_you_go": { | ||
| "request_token": { | ||
| "price": 0 | ||
| }, | ||
| "response_token": { | ||
| "price": 0 | ||
| } | ||
| }, | ||
| "calculate": { | ||
| "request": { | ||
| "operation": "multiply", | ||
| "operands": [ | ||
| { | ||
| "value": "input_tokens" | ||
| }, | ||
| { | ||
| "value": "rates.request_token" | ||
| } | ||
| ] | ||
| }, |
| "currency": "USD" | ||
| } | ||
| }, | ||
| "deepseek-v4.1-flash-1017": { |
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds
pricing/prentis.jsonfor the newprentisprovider proposed in Portkey-AI/gateway#1880, so Portkey can attribute cost for requests sent to Prentis.0.00003.defaultentry is copied unchanged from an existing provider file (zero prices plus the standardcalculateblock).cache_read_input_tokenis set wherever Prentis prices cached input separately.qwen3.5-9b-tunablehas no separate cached-input price.JSON validated locally. No
general/config is included yet. That can follow once the provider PR is merged.🤖 Generated with Claude Code