---
type: "post"
id: "companion-deepseek-recipe-mit-handles-chat-completions-messages-eba1d4"
slug: "companion-deepseek-recipe-mit-handles-chat-completions-messages-eba1d4"
title: "Companion deepseek-recipe (MIT) handles Chat Completions, Messages, and Responses protocol parity with the official DeepSeek API."
description: "DeepSeek’s deepseek-recipe release makes conversion across Chat Completions, Messages, and Responses formats an explicit library responsibility."
retrieval_nugget: "DeepSeek’s deepseek-recipe release makes conversion across Chat Completions, Messages, and Responses formats an explicit library responsibility."
published_at: "2026-10-20"
updated_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "published_at"
topics: ["agent-protocols","api-design","interoperability"]
source_urls: ["https://github.com/deepseek-ai/deepseek-recipe"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:companion-deepseek-recipe-mit-handles-chat-completions-messages-eba1d4"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:83f29acf4f3b0915e9ea09845844a0e54f1afad250af8abdfb33f0717132f78a","reviewed_at":"2026-10-20T11:04:21.795Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":1,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"This release lowers integration work at the API-format boundary without removing the serving responsibilities of the integrator.","observed_facts":[{"text":"The repository describes Rust libraries and Python bindings converting Chat Completions, Messages, and Responses requests into a shared Conversation representation.","source_urls":["https://github.com/deepseek-ai/deepseek-recipe"]},{"text":"The README says callers provide model inference, tool execution, and HTTP transport.","source_urls":["https://github.com/deepseek-ai/deepseek-recipe"]},{"text":"The documented scope includes streaming and complete responses, tool calls, images, reasoning content, and structured output.","source_urls":["https://github.com/deepseek-ai/deepseek-recipe"]}],"mechanism":"The library converts request and response formats, renders prompts, and optionally encodes conversations, while callers provide inference, tool execution, and HTTP transport.","why_now":"The repository presents the project as a way to connect an inference backend to services that support multiple formats, making protocol conversion a practical concern for teams exposing DeepSeek models through existing interfaces.","implications":["Teams can assess deepseek-recipe as a reusable conversion layer, not a replacement for their inference or tool runtime."],"evidence_boundary":"The evidence is the public repository description and README; it does not establish production adoption, performance, or compatibility with every implementation of these formats.","watch_conditions":["Whether future releases expand documented format coverage or provide evidence of interoperability across real serving backends."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied for this project or release, so this starts a distinct analytical record."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/companion-deepseek-recipe-mit-handles-chat-completions-messages-eba1d4/","markdown":"https://newruntime.com/posts/companion-deepseek-recipe-mit-handles-chat-completions-messages-eba1d4.md","json":"https://newruntime.com/posts/companion-deepseek-recipe-mit-handles-chat-completions-messages-eba1d4.json"}
related_patterns: ["agent-protocols-become-interoperability-layer"]
---

# Companion deepseek-recipe (MIT) handles Chat Completions, Messages, and Responses protocol parity with the official DeepSeek API.

## Retrieval answer

DeepSeek’s deepseek-recipe release makes conversion across Chat Completions, Messages, and Responses formats an explicit library responsibility.

DeepSeek’s deepseek-recipe release makes conversion across Chat Completions, Messages, and Responses formats an explicit library responsibility. The repository describes Rust libraries and Python bindings that convert requests into a shared Conversation representation and render that conversation into prompts for DeepSeek models. This release lowers integration work at the API-format boundary without removing the serving responsibilities of the integrator.

The library converts request and response formats, renders prompts, and optionally encodes conversations, while callers provide inference, tool execution, and HTTP transport. The README documents support for streaming and complete responses, tool calls, images, reasoning content, and structured output. One concrete boundary is model-specific image handling: it says DeepSeek V4 does not accept images and conversion replaces them with an unsupported-image marker, while V4.1 has image preprocessing. The mechanism is a reusable adapter layer, not a turnkey multi-provider server.

The repository presents the project as a way to connect an inference backend to services that support multiple formats, making protocol conversion a practical concern for teams exposing DeepSeek models through existing interfaces. Teams can assess deepseek-recipe as a reusable conversion layer, not a replacement for their inference or tool runtime.

The evidence is the public repository description and README; it does not establish production adoption, performance, or compatibility with every implementation of these formats. Whether future releases expand documented format coverage or provide evidence of interoperability across real serving backends. This begins a distinct analytical record because no prior New Runtime record is supplied for this project or release.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Protocols](https://newruntime.com/topics/agent-protocols.md): Explore the agent-protocols topic hub.
- topic hub: [Api Design](https://newruntime.com/topics/api-design.md): Explore the api-design topic hub.
- topic hub: [Interoperability](https://newruntime.com/topics/interoperability.md): Explore the interoperability topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)