feat(llmgateway): add provider - #458
Open
steebchen wants to merge 1 commit into
Open
Conversation
Adds LLM Gateway (https://llmgateway.io) as a provider, with a generator that builds the model list from its public models endpoint. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
steebchen
added a commit
to theopenco/llmgateway
that referenced
this pull request
Jul 22, 2026
Assume charmbracelet/catwalk#458 is merged: built-in provider flow is the primary path, manual crush.json config demoted to an optional customization section. Merge once the native integration is live. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This adds LLM Gateway as a provider.
LLM Gateway is an open-source (AGPLv3, llmgateway/llmgateway) LLM API gateway that routes OpenAI-compatible requests across all major providers with automatic fallback, caching, and cost analytics. It currently processes 100B+ tokens monthly and is SOC 2 Type II compliant; revenue is publicly verifiable via TrustMRR.
Follows the same shape as #407 (Baseten):
cmd/llmgateway/main.go— generator that builds the model list from the public models endpoint (https://api.llmgateway.io/v1/models). The endpoint requires no API key, so the 6-hourly update workflow needs no repo secret.internal/providers/configs/llmgateway.json— generated config (129 models). The generator keeps only tool-capable, text-in/text-out models with ≥20k context, drops deprecated/deactivated and unstable models, maps per-token pricing to per-1M costs, and carries reasoning levels (none…max) and image support.internal/providers/providers.go,pkg/catwalk/provider.go,Taskfile.yaml(task gen:llmgateway), and.github/workflows/update.yml.Auth uses
$LLMGATEWAY_API_KEYwithtype: openai-compat; defaults areclaude-sonnet-5(large) andgpt-5-mini(small).Verified:
go build ./... && go test ./...pass (includingTestValidDefaultModels), and the generator output is idempotent across runs.🤖 Generated with Claude Code