Switch to HopBase

Move from OpenAI, OpenRouter, or the Anthropic API to HopBase by changing three values.

Migrating changes three values: the Base URL, the key, and the model ID if needed. Request bodies, streaming code, and error handling stay the same.

What changes

	OpenAI	OpenRouter	Anthropic	HopBase
Base URL	`https://api.openai.com/v1`	`https://openrouter.ai/api/v1`	`https://api.anthropic.com`	OpenAI protocol: `https://api.hop-base.com/v1` Anthropic protocol: `https://api.hop-base.com` (no `/v1`)
Key	OpenAI key	One OpenRouter key for every model	Anthropic key	`sk-…` created under API Keys, including 1–10 groups
Model ID	`gpt-5.5`	`openai/gpt-5.5`, `anthropic/claude-sonnet-5`	`claude-sonnet-5`	Bare ID with no vendor prefix, exactly as `GET /v1/models` returns it: `gpt-5.5`, `claude-sonnet-5`

Which protocol each model family uses is listed in Base URLs and protocols.

A key calls the models of the groups you add to it.

Add the groups you need to the key. An OpenRouter key calls every model; a HopBase key calls the models of the groups it includes — 1 to 10, across platforms. GET /v1/models returns the union of those groups' models, and calling a model outside all of them returns 404 model_not_found. An app that calls Claude and GPT can use one key with a Claude group and the Codex Plus or Codex Pro group; each request is billed by the group that serves its model. Groups whose models overlap (such as Codex Plus and Codex Pro) cannot share a key (except GPT Official Direct (Azure) with a Codex group or GPT Image (all models); see Which group to choose), and a subscription group must be a key's only group.

OpenAI SDK

Set the Base URL and swap the key. OpenAI model IDs such as gpt-5.5 stay the same as long as your key's GET /v1/models lists them.

 import os
 from openai import OpenAI

 client = OpenAI(
-    api_key=os.environ["OPENAI_API_KEY"],
+    base_url="https://api.hop-base.com/v1",
+    api_key=os.environ["HOPBASE_OPENAI_API_KEY"],
 )

 resp = client.chat.completions.create(
     model="gpt-5.5",
     messages=[{"role": "user", "content": "Hello"}],
 )

Without touching code, both SDKs also read OPENAI_BASE_URL and OPENAI_API_KEY from the environment: set them to https://api.hop-base.com/v1 and your HopBase key. More examples are in OpenAI SDK.

Anthropic SDK

Claude keeps the Anthropic Messages API. Set the Base URL without /v1 and use a key from the Claude Max Enterprise group. Keys from Claude Max (ccmax) work only in the Claude Code client; SDK calls with them fail.

 import os
 from anthropic import Anthropic

 client = Anthropic(
-    api_key=os.environ["ANTHROPIC_API_KEY"],
+    base_url="https://api.hop-base.com",
+    api_key=os.environ["HOPBASE_CLAUDE_API_KEY"],
 )

 msg = client.messages.create(
     model="claude-sonnet-5",
     max_tokens=1024,
     messages=[{"role": "user", "content": "Hello"}],
 )

The environment-variable route works here too: ANTHROPIC_BASE_URL=https://api.hop-base.com. See Anthropic SDK.

OpenRouter

Change the Base URL and key, drop the vendor prefix from the model string, and remove the OpenRouter attribution headers — HopBase does not need them.

 import os
 from openai import OpenAI

 client = OpenAI(
-    base_url="https://openrouter.ai/api/v1",
-    api_key=os.environ["OPENROUTER_API_KEY"],
-    default_headers={"HTTP-Referer": "https://your-app.example", "X-Title": "Your App"},
+    base_url="https://api.hop-base.com/v1",
+    api_key=os.environ["HOPBASE_OPENAI_API_KEY"],
 )

 resp = client.chat.completions.create(
-    model="openai/gpt-5.5",
+    model="gpt-5.5",
     messages=[{"role": "user", "content": "Hello"}],
 )

If you reached Claude through OpenRouter's OpenAI-compatible endpoint, that path does not exist for Claude on HopBase: move those calls to the Anthropic SDK with a Claude-group key, as in the section above. Other families (Gemini, GLM, Qwen, DeepSeek, Kimi, Grok) stay on the OpenAI SDK, with a key that includes each family's group.

What is not supported

What you may be using	On HopBase
Claude through `/v1/chat/completions` or `/v1/responses`	404. Use Anthropic Messages — Anthropic SDK
Gemini through the native Gemini SDK path (`:generateContent`)	Supported on Gemini Official Direct (Enterprise): point the SDK's Base URL at `https://api.hop-base.com`. Gemini Value (AI Studio / Vertex) does not support it — Gemini chat
Kimi K3 through `/v1/responses` or `/v1/messages`	Chat Completions only — Kimi K3
Embeddings, audio transcription, Files, Batch, Assistants, fine-tuning, moderation	Not offered; these paths return 404
One key for every model	One key can include up to 10 groups across platforms, as long as their models do not overlap, except GPT Official Direct (Azure) with a Codex group or GPT Image (all models) (see above)
OpenRouter model fallback lists (`models`), `provider` routing, model suffixes such as `:online` or `:free`	Not supported; remove them and send a single model ID

The full list of endpoints is in Base URLs and protocols.

Quickstart: create a key and send the first request
Available models: find the model IDs available to a key
Account and catalog API: check the balance, usage, and model catalog over the API
Error codes and retries: what each error code means and whether to retry

What changes

OpenAI SDK

Anthropic SDK

OpenRouter

What is not supported

Check the switch

List the key's models

Send one small request

Check what the key can spend

Next steps

On this page