docs: refresh model examples across provider pages - #1222
Open
ZHCHJ888 wants to merge 1 commit into
Open
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Several provider pages identified in #1160 still lead with model IDs and catalog tables that are one or more generations behind. The most visible cases are Together AI and DeepInfra, which still use Llama 2 examples, and Cerebras, whose only example uses an old Llama 3 model.
This PR refreshes SDK, streaming, and proxy examples across 15 provider pages. It replaces the long static tables on Together AI, DeepInfra, and NVIDIA NIM with a small set of current examples plus links to each provider's live catalog. It also corrects a mislabeled Claude Haiku row in the Bedrock table and raises the 10-token output limits that would truncate responses from current reasoning models.
No LiteLLM runtime behavior or pricing metadata changes in this PR.
Model ID verification
Literal model IDs were cross-checked against LiteLLM's upstream
model_prices_and_context_window.jsonand the providers' official model catalogs. For Cohere, DeepInfra, and NVIDIA NIM models that are not yet represented in the price map, the examples use an explicit provider prefix so routing remains unambiguous; adding their pricing and capability metadata remains a separate main-repository change.OpenAI and Azure OpenAI do not need edits here because their examples already resolve to current models after #1201. The SambaNova
E5-Mistral-7B-Instructembedding example is intentionally retained because SambaNova's current API documentation still uses that exact ID.Validation
python3 scripts/check-docs.py docspasses for all 785 documentation pages.node scripts/check-writing-style.js docs/providerspasses for all 183 provider pages.git diff --checkpasses.Addresses #1160.