Skip to content

docs(snowflake): comprehensive rewrite of Snowflake Cortex provider page#25

Open
navnitshukla wants to merge 2 commits intoBerriAI:mainfrom
navnitshukla:docs/snowflake-cortex-provider-page
Open

docs(snowflake): comprehensive rewrite of Snowflake Cortex provider page#25
navnitshukla wants to merge 2 commits intoBerriAI:mainfrom
navnitshukla:docs/snowflake-cortex-provider-page

Conversation

@navnitshukla
Copy link
Copy Markdown

Summary

Rewrites the Snowflake Cortex provider docs page from ~110 words to ~1,200 words, matching the coverage level of Databricks, Bedrock, and OpenRouter.

What's new

  • Authentication: PAT , JWT, Auth
  • Streaming: SDK + Proxy examples
  • Tool / Function Calling: SDK + Proxy examples (auto-transforms to Snowflake tool_spec format)
  • Thinking / Reasoning: Claude 3.7, Claude 4 Opus, DeepSeek R1 with reasoning_effort
  • Prompt Caching: OpenAI implicit, Claude explicit, 90% discount at ≥1,024 tokens
  • Embeddings: Arctic Embed models
  • Full model table: 20+ models with capability flags (function calling, vision, caching)
  • Updated endpoints: New OpenAI-compatible /api/v2/cortex/v1/chat/completions + Anthropic Messages API

Before → After

Before After
Word count ~110 ~1,200
Sections 3 10+
Models listed 1 (mistral-7b) 20+
SDK + Proxy tabs No Yes
Streaming No Yes
Tool calling No Yes
Thinking/reasoning No Yes
Prompt caching No Yes

References

## Summary

Rewrites the Snowflake Cortex provider docs page from ~110 words to ~1,200 words,
matching the coverage level of Databricks, Bedrock, and OpenRouter.

## What's new

- **Authentication**: PAT (recommended), JWT, pass-as-params — with examples
- **Streaming**: SDK + Proxy examples
- **Tool / Function Calling**: SDK + Proxy examples (auto-transforms to Snowflake tool_spec format)
- **Thinking / Reasoning**: Claude 3.7, Claude 4 Opus, DeepSeek R1 with `reasoning_effort`
- **Prompt Caching**: OpenAI implicit, Claude explicit, 90% discount at ≥1,024 tokens
- **Embeddings**: Arctic Embed models
- **Full model table**: 20+ models with capability flags (function calling, vision, caching)
- **Updated endpoints**: New OpenAI-compatible `/api/v2/cortex/v1/chat/completions` + Anthropic Messages API

## Before → After

| | Before | After |
|---|---|---|
| Word count | ~110 | ~1,200 |
| Sections | 3 | 10+ |
| Models listed | 1 (mistral-7b) | 20+ |
| SDK + Proxy tabs | No | Yes |
| Streaming | No | Yes |
| Tool calling | No | Yes |
| Thinking/reasoning | No | Yes |
| Prompt caching | No | Yes |

## References

- [Cortex REST API docs](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api)
- [Service Consumption Table (pricing)](https://www.snowflake.com/legal-files/CreditConsumptionTable.pdf)
@navnitshukla navnitshukla requested a review from a team April 27, 2026 16:00
@vercel
Copy link
Copy Markdown

vercel Bot commented Apr 27, 2026

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
litellm Ready Ready Preview, Comment Apr 27, 2026 5:44pm

Request Review

Included 

import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
@sfc-gh-nashukla
Copy link
Copy Markdown

Hi team, friendly follow-up. The Vercel preview is passing and deployed successfully. This rewrites the Snowflake Cortex REST API provider page from ~110 words to ~1,200 words with full coverage (streaming, tool calling, thinking/reasoning, prompt caching, embeddings, 20+ models). Would appreciate a review when you get a chance. Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants