Spark
Sign In
Skill

Proxy OpenAI/Anthropic APIs to GigaChat

gpt2giga is a proxy that maps OpenAI and Anthropic API requests to GigaChat, enabling existing OpenAI-compatible or Anthropic-compatible apps to use GigaChat

Get skill
Works with openaianthropic
NeuralDeep
Maintainer?
91
Spark score
out of 100
Updated last month
Version 1.0.0
Add to Favorites

Why it matters

Seamlessly migrate your applications from OpenAI or Anthropic APIs to GigaChat without requiring any code modifications. This asset acts as a direct proxy, ensuring compatibility and simplifying your transition to a new AI platform.

Outcomes

What it gets done

01

Map OpenAI API calls to GigaChat endpoints.

02

Proxy Anthropic API requests to GigaChat.

03

Enable code-free migration between AI models.

04

Maintain existing application logic during platform transition.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/gpt2giga | bash

Overview

GPT2Giga Proxy

A proxy configuration skill that maps OpenAI and Anthropic API requests to GigaChat for compatibility scenarios. Use when you need to preserve existing OpenAI or Anthropic client integrations while connecting to GigaChat; skip for new native applications.

What it does

gpt2giga runs and configures a proxy that maps OpenAI API and Anthropic Messages API requests to GigaChat. It allows you to plug GigaChat into existing applications built for OpenAI or Anthropic without rewriting the client integration.

When to use - and when NOT to

Use gpt2giga when the task is compatibility, migration, or proxy deployment. Use it when you need to plug GigaChat into existing OpenAI-compatible or Anthropic-compatible applications without rewriting the client integration.

Do NOT use gpt2giga for new native applications - build directly against GigaChat APIs instead. Do not rely on this skill to teach raw SDK usage; use gigachat-sdk-* skills for that.

Inputs and outputs

You provide your deployment preference (local development, Docker, or production), proxy authentication configuration separate from GigaChat auth, and the API family you want to preserve (OpenAI or Anthropic). The skill covers .env and CLI configuration, OpenAI-compatible and Anthropic-compatible endpoints, proxy auth and pass-through auth, streaming and model routing behavior, and production hardening.

Integrations

The proxy provides OpenAI-compatible and Anthropic-compatible endpoints. If the client must keep its OpenAI or Anthropic SDK, point it at the proxy base URL. If the client should carry its own GigaChat credentials, use pass-token mode.

Who it's for

gpt2giga is for users working on compatibility, migration, or proxy deployment tasks. It treats the proxy as a compatibility layer rather than the default for new native apps, explicitly states which API family is being preserved (OpenAI or Anthropic), and clarifies that outer orchestration still owns full multi-step tool execution when behavior differs from native OpenAI or Anthropic APIs.

Source README

gpt2giga

Use this skill when the task is compatibility, migration, or proxy deployment.

What this skill covers

  • local or Docker startup
  • .env and CLI configuration
  • OpenAI-compatible and Anthropic-compatible endpoints
  • proxy auth and pass-through auth
  • streaming and model routing behavior
  • production hardening

Workflow

  1. Decide whether the user wants local development, Docker, or production deployment.
  2. Configure proxy auth separately from GigaChat auth.
  3. If the client must keep its OpenAI or Anthropic SDK, point it at the proxy base URL.
  4. If the client should carry its own GigaChat credentials, use pass-token mode.
  5. In production, enable proxy API-key auth and avoid DEV-only endpoints.
  6. When behavior differs from native OpenAI or Anthropic APIs, explain the mapping rather than hiding it.
  7. Prefer the smallest compatibility setup that preserves the client API the user already has.

Read these references as needed

  • For env vars, ports, auth, and startup: references/config.md
  • For endpoint compatibility and client behavior: references/compatibility.md

Default output

  • treat gpt2giga as a compatibility layer, not as the default for new native apps
  • state which API family is being preserved: OpenAI or Anthropic
  • call out that outer orchestration still owns full multi-step tool execution

Boundaries

  • Do not teach raw SDK usage here; use gigachat-sdk-*.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.