feat: add T-Systems LLMHub as a provider#1383
Open
ashwinnair14 wants to merge 6 commits into
Open
Conversation
ashwinnair14
force-pushed
the
feat/add-t-systems-provider
branch
from
3d268bc to
a1a4c8a
Compare
Author
|
Could I request a review @rekram1-node ? |
Add T-Systems (AI Foundation Services) with 38 models including LLMs, embeddings, audio, and image generation models accessible through their GDPR-compliant, EU-hosted OpenAI-compatible API.
Convert 26 of 38 T-Systems models to inherit from canonical definitions
in providers/{anthropic,openai,google,mistral,llama,alibaba}/ per
README rule 3a. Local overrides preserve T-Systems pricing markup and
any spec differences; omit removes fields not applicable to the wrapper
(cache pricing, context-tier pricing, etc.).
Verified via bun run compare:migrations: generated JSON is
byte-identical before and after for every changed model.
Net: -446/+91 lines across 26 files.
ashwinnair14
force-pushed
the
feat/add-t-systems-provider
branch
from
0c0304f to
3ec0426
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #1626
Summary
Adds T-Systems LLMHub (AI Foundation Services) as a new provider with 38 models, served via
@ai-sdk/openai-compatibleagainsthttps://llm-server.llmhub.t-systems.net/v2. T-Systems offers GDPR-compliant, EU-hosted access to both open-source and proprietary models.Models included
Implementation notes
extends(README rule 3a): 26 of 38 models inherit from canonical definitions inproviders/{anthropic,openai,google,mistral,llama,alibaba}/. Local overrides preserve T-Systems pricing markup (Standard1000 plan tier) and any provider-specific spec differences (e.g., GPT-5 acceptingtemperature);omitremoves fields not applicable to the wrapper such as cache-read pricing and gemini context-tier pricing.Pricing
Pricing sourced from T-Systems documentation (Standard1000 plan tier). Open-source models on T-Cloud Germany use flat-rate pricing; proprietary models have per-token input/output rates.
Data sources
Test plan
bun installsucceedsbun run validateexits 0 — all 38 models pass Zod schemabun run compare:migrationsshows zero diff —extendsconversions produce byte-identical generated JSONapifield for@ai-sdk/openai-compatiblecurrentColorwith no fixed sizesdev