Add The Grid custom provider integration guide - #374
Open
CastilloLuis wants to merge 1 commit into
Open
CastilloLuis wants to merge 1 commit into
CastilloLuis wants to merge 1 commit into
Conversation
CastilloLuis
force-pushed
the
thegridai/thegrid-integration
branch
from
September 6, 2026 14:53
04d2cab to
cd13b8b
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds a The Grid setup guide under Custom Providers, following the existing
xai-integration/exa-integrationpages.features/thegrid-integration.mdx(new)docs.json, in the Custom Providers groupfeatures/custom-providers.mdxso the "Example Integrations" list points at itThe Grid is an OpenAI-compatible inference marketplace, so this documents it as an OpenAI-client custom provider — the same shape as the xAI page. Not claiming native-provider status; that's OpenRouter's page and would need work on your side.
Verification
Everything in the guide was checked against the live API:
https://api.thegrid.ai/v1works with an OpenAI client — chat, streaming, and tool callsGET /v1/modelsreturns a spec-shaped{object: "list", data: [...]}, currently 17 instrumentsreasoning_effortvalues listed per tier come from that catalog, not from marketing copyThe one non-obvious thing I documented is a warning: instruments reason before answering, and reasoning tokens count toward
max_tokenswithout appearing in the response. Measured on a short prompt,text-standardspent 114 of a 250-token budget on reasoning andagent-maxhit the cap and returnedfinish_reason: "length". That surprised me while testing, so it seemed worth saving your users the same debugging.Disclosure: I work on The Grid — happy to trim the framing if it reads too vendor-ish.