chore: update berget.ai models - prices and Gemma 4#1489
Merged
rekram1-node merged 1 commit intoanomalyco:devfrom Apr 19, 2026
Merged
chore: update berget.ai models - prices and Gemma 4#1489rekram1-node merged 1 commit intoanomalyco:devfrom
rekram1-node merged 1 commit intoanomalyco:devfrom
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Updates the Berget.AI model catalog by refreshing token pricing, adding the Gemma 4 31B Instruct model, and removing models that are not relevant for coding workflows.
Changes:
- Updated per‑million token pricing for GLM‑4.7, Llama‑3.3‑70B‑Instruct, Mistral‑Small‑3.2‑24B‑Instruct‑2506, and GPT‑OSS‑120B.
- Added Google Gemma 4 31B Instruct model definition.
- Removed reranking/embedding/speech models and deprecated entries from the Berget model set.
Reviewed changes
Copilot reviewed 9 out of 9 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
| providers/berget/models/zai-org/GLM-4.7.toml | Updates input/output token pricing. |
| providers/berget/models/openai/gpt-oss-120b.toml | Updates input/output token pricing. |
| providers/berget/models/mistralai/Mistral-Small-3.2-24B-Instruct-2506.toml | Updates input/output token pricing. |
| providers/berget/models/meta-llama/Llama-3.3-70B-Instruct.toml | Updates input/output token pricing. |
| providers/berget/models/google/gemma-4-31B-it.toml | Adds Gemma 4 31B Instruct model configuration. |
| providers/berget/models/intfloat/multilingual-e5-large.toml | Removes an embedding model definition. |
| providers/berget/models/intfloat/multilingual-e5-large-instruct.toml | Removes an embedding model definition. |
| providers/berget/models/KBLab/kb-whisper-large.toml | Removes a speech-to-text model definition. |
| providers/berget/models/BAAI/bge-reranker-v2-m3.toml | Removes a reranker model definition. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
- Add Google Gemma 4 31B Instruct model - Update prices for existing models (EUR to USD conversion) - Remove non-coding models (bge-reranker, multilingual-e5 embeddings, kb-whisper) - Remove deprecated Llama-3.1-8B-Instruct Updated models: - GLM-4.7: 0.77/2.75 USD/M (was 0.7/2.3) - Llama-3.3-70B: 0.99/0.99 USD/M (was 0.9/0.9) - Mistral-Small-3.2: 0.33/0.33 USD/M (was 0.3/0.3) - GPT-OSS-120B: 0.44/0.99 USD/M (was 0.3/0.9) New models: - Gemma-4-31B-it: 0.275/0.55 USD/M Removed models (not relevant for coding): - BAAI/bge-reranker-v2-m3 (reranker) - intfloat/multilingual-e5-large/* (embeddings) - KBLab/kb-whisper-large (speech-to-text) - meta-llama/Llama-3.1-8B-Instruct (deprecated)
irony
force-pushed
the
update/berget-prices-gemma4
branch
from
6430d8e to
71c59b4
Compare
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.
Summary
Updated models:
New models:
Removed models (not relevant for coding):