Merge pull request #31 from teremterem/transparent-anthropic-proxy
Add "transparent Anthropic proxy" mode with PREFERRED_PROVIDER=anthropic
This commit is contained in:
Winston Du
GitHub
commit
a6ccde39e7
3 changed files with 30 additions and 8 deletions
|
|
@ -4,8 +4,9 @@ OPENAI_API_KEY="sk-..."
|
|||
GEMINI_API_KEY="your-google-ai-studio-key"
|
||||
|
||||
# Optional: Provider Preference and Model Mapping
|
||||
# Controls which provider (google or openai) is preferred for mapping haiku/sonnet.
|
||||
# Controls which provider (google, openai, or anthropic) is preferred for mapping haiku/sonnet.
|
||||
# Defaults to openai if not set.
|
||||
# Set to "anthropic" for "just an Anthropic proxy" mode (no remapping)
|
||||
PREFERRED_PROVIDER="openai"
|
||||
OPENAI_BASE_URL="https://api.openai.com/v1"
|
||||
|
||||
|
|
@ -13,6 +14,7 @@ OPENAI_BASE_URL="https://api.openai.com/v1"
|
|||
# If PREFERRED_PROVIDER=google, these MUST be valid Gemini model names known to the server.
|
||||
# Defaults to gemini-2.5-pro-preview-03-25 and gemini-2.0-flash if PREFERRED_PROVIDER=google.
|
||||
# Defaults to gpt-4.1 and gpt-4.1-mini if PREFERRED_PROVIDER=openai.
|
||||
# These are IGNORED when PREFERRED_PROVIDER=anthropic (models are not remapped).
|
||||
# BIG_MODEL="gpt-4.1"
|
||||
# SMALL_MODEL="gpt-4.1-mini"
|
||||
|
||||
|
|
@ -20,3 +22,7 @@ OPENAI_BASE_URL="https://api.openai.com/v1"
|
|||
# PREFERRED_PROVIDER="google"
|
||||
# BIG_MODEL="gemini-2.5-pro-preview-03-25"
|
||||
# SMALL_MODEL="gemini-2.0-flash"
|
||||
|
||||
# Example "just an Anthropic proxy" mode:
|
||||
# PREFERRED_PROVIDER="anthropic"
|
||||
# (BIG_MODEL and SMALL_MODEL are ignored in this mode)
|
||||
|
|
|
|||
23
README.md
23
README.md
|
|
@ -1,8 +1,8 @@
|
|||
# Anthropic API Proxy for Gemini & OpenAI Models 🔄
|
||||
|
||||
**Use Anthropic clients (like Claude Code) with Gemini or OpenAI backends.** 🤝
|
||||
**Use Anthropic clients (like Claude Code) with Gemini, OpenAI, or direct Anthropic backends.** 🤝
|
||||
|
||||
A proxy server that lets you use Anthropic clients with Gemini or OpenAI models via LiteLLM. 🌉
|
||||
A proxy server that lets you use Anthropic clients with Gemini, OpenAI, or Anthropic models themselves (a transparent proxy of sorts), all via LiteLLM. 🌉
|
||||
|
||||
|
||||
|
||||
|
|
@ -39,13 +39,14 @@ A proxy server that lets you use Anthropic clients with Gemini or OpenAI models
|
|||
* `ANTHROPIC_API_KEY`: (Optional) Needed only if proxying *to* Anthropic models.
|
||||
* `OPENAI_API_KEY`: Your OpenAI API key (Required if using the default OpenAI preference or as fallback).
|
||||
* `GEMINI_API_KEY`: Your Google AI Studio (Gemini) API key (Required if PREFERRED_PROVIDER=google).
|
||||
* `PREFERRED_PROVIDER` (Optional): Set to `openai` (default) or `google`. This determines the primary backend for mapping `haiku`/`sonnet`.
|
||||
* `BIG_MODEL` (Optional): The model to map `sonnet` requests to. Defaults to `gpt-4.1` (if `PREFERRED_PROVIDER=openai`) or `gemini-2.5-pro-preview-03-25`.
|
||||
* `SMALL_MODEL` (Optional): The model to map `haiku` requests to. Defaults to `gpt-4.1-mini` (if `PREFERRED_PROVIDER=openai`) or `gemini-2.0-flash`.
|
||||
* `PREFERRED_PROVIDER` (Optional): Set to `openai` (default), `google`, or `anthropic`. This determines the primary backend for mapping `haiku`/`sonnet`.
|
||||
* `BIG_MODEL` (Optional): The model to map `sonnet` requests to. Defaults to `gpt-4.1` (if `PREFERRED_PROVIDER=openai`) or `gemini-2.5-pro-preview-03-25`. Ignored when `PREFERRED_PROVIDER=anthropic`.
|
||||
* `SMALL_MODEL` (Optional): The model to map `haiku` requests to. Defaults to `gpt-4.1-mini` (if `PREFERRED_PROVIDER=openai`) or `gemini-2.0-flash`. Ignored when `PREFERRED_PROVIDER=anthropic`.
|
||||
|
||||
**Mapping Logic:**
|
||||
- If `PREFERRED_PROVIDER=openai` (default), `haiku`/`sonnet` map to `SMALL_MODEL`/`BIG_MODEL` prefixed with `openai/`.
|
||||
- If `PREFERRED_PROVIDER=google`, `haiku`/`sonnet` map to `SMALL_MODEL`/`BIG_MODEL` prefixed with `gemini/` *if* those models are in the server's known `GEMINI_MODELS` list (otherwise falls back to OpenAI mapping).
|
||||
- If `PREFERRED_PROVIDER=anthropic`, `haiku`/`sonnet` requests are passed directly to Anthropic with the `anthropic/` prefix without remapping to different models.
|
||||
|
||||
4. **Run the server**:
|
||||
```bash
|
||||
|
|
@ -132,7 +133,17 @@ PREFERRED_PROVIDER="google"
|
|||
# SMALL_MODEL="gemini-2.0-flash" # Optional, it's the default for Google pref
|
||||
```
|
||||
|
||||
**Example 3: Use Specific OpenAI Models**
|
||||
**Example 3: Use Direct Anthropic ("Just an Anthropic Proxy" Mode)**
|
||||
```dotenv
|
||||
ANTHROPIC_API_KEY="sk-ant-..."
|
||||
PREFERRED_PROVIDER="anthropic"
|
||||
# BIG_MODEL and SMALL_MODEL are ignored in this mode
|
||||
# haiku/sonnet requests are passed directly to Anthropic models
|
||||
```
|
||||
|
||||
*Use case: This mode enables you to use the proxy infrastructure (for logging, middleware, request/response processing, etc.) while still using actual Anthropic models rather than being forced to remap to OpenAI or Gemini.*
|
||||
|
||||
**Example 4: Use Specific OpenAI Models**
|
||||
```dotenv
|
||||
OPENAI_API_KEY="your-openai-key"
|
||||
GEMINI_API_KEY="your-google-key"
|
||||
|
|
|
|||
|
|
@ -208,8 +208,13 @@ class MessagesRequest(BaseModel):
|
|||
|
||||
# --- Mapping Logic --- START ---
|
||||
mapped = False
|
||||
if PREFERRED_PROVIDER == "anthropic":
|
||||
# Don't remap to big/small models, just add the prefix
|
||||
new_model = f"anthropic/{clean_v}"
|
||||
mapped = True
|
||||
|
||||
# Map Haiku to SMALL_MODEL based on provider preference
|
||||
if 'haiku' in clean_v.lower():
|
||||
elif 'haiku' in clean_v.lower():
|
||||
if PREFERRED_PROVIDER == "google" and SMALL_MODEL in GEMINI_MODELS:
|
||||
new_model = f"gemini/{SMALL_MODEL}"
|
||||
mapped = True
|
||||
|
|
|
|||
Loading…
Reference in a new issue