docs(cognition): add the Cognition provider page - #822
Merged
Conversation
Cognition is now its own provider route on LiteLLM instead of the generic OpenAI-compatible one, so document the cognition/ models, COGNITION_API_KEY, and COGNITION_API_BASE. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Contributor
Author
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
4 tasks
…per-customer endpoints
…he 5x one Cognition's model list at https://docs.devin.ai/desktop/models has uid swe-1-7 at $0.50 in / $2.50 out per million with $0.20 cache reads, and uid swe-1-7-lightning at $2.50 / $12.50 with $1.00. The page had the Lightning numbers under the plain swe-1.7 row and no row for Lightning itself. Matches the cost map correction in BerriAI/litellm#37763.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Companion docs for BerriAI/litellm#37743, which gives Cognition its own provider identity instead of routing it as
custom_llm_provider: openai. Addsdocs/providers/cognition.md(thecognition/route, the SWE model pricing table, SDK and proxy usage, the Anthropic Messages path, and theapi_baseoverride), the sidebar entry, andCOGNITION_API_KEY/COGNITION_API_BASErows in the config settings reference.Pricing on the page matches Cognition's own model list at https://docs.devin.ai/desktop/models, which embeds it as raw JSON: swe-1.7 at $0.50 in / $2.50 out per million with $0.20 cache reads, swe-1.7-lightning at $2.50 / $12.50 with $1.00, swe-1.6 at $0.50 / $2.50 with $0.20. An earlier revision of this page had the Lightning numbers on the plain swe-1.7 row and no row for Lightning at all; BerriAI/litellm#37763 makes the same correction in the cost map. The retired swe-1.5 is not listed. The page also notes that Cognition serves per-customer endpoints, so
api_baseis usually set per deployment.The original PR body said this had to merge before the code PR's CI could pass, via
tests/documentation_tests/test_env_keys.py. That is not true for the current code diff: the test only collects env var names passed as string literals toos.getenv/get_secret*in.pyfiles underlitellm/, and the code PR reads the key throughjson_provider.api_key_env, with the literalCOGNITION_API_KEYliving inproviders.json. The two PRs can land in either order, though docs reading correctly only once the provider ships argues for merging this one alongside or just after the code PR.Link to Devin session: https://app.devin.ai/sessions/c27f086d609843cdb6380708ecd31b2f
Requested by: @shivamrawat1