TypingMind

Add OneProvider to TypingMind as a custom model. TypingMind wants the full endpoint address, not a base URL.

TypingMind has no base URL field: its custom model form takes the full endpoint address and sends requests to it exactly as typed, appending nothing. The built-in Claude (Anthropic) API key field talks to Anthropic directly, so a OneProvider key works there only as a custom model.

1. Add a custom model

1. In TypingMind open Models in the left sidebar, click Add custom model and stay on Create Manually.
2. Name: any label, for example OneProvider claude-opus-5-5.
3. Model ID: the exact id from the models page , for example claude-opus-5-5. The display name “Claude Opus 5.5” is not an id.
4. Context Length: the model’s context window from the same page.

2. API Type, Endpoint URL and key

On the Authentication tab pick one of the two API types and fill the fields exactly as below. The same OneProvider key works for both.

Claude Messages API (Claude models)

API Type: Claude Messages API
Endpoint URL: https://api.oneprovider.dev/v1/messages
Authentication Type: API Key via HTTP Header
Header Key: x-api-key
Header Value: sk-your-key-here
Model ID: claude-opus-5-5

OpenAI Chat Completions API (GPT and Claude models)

API Type: OpenAI Chat Completions API
Endpoint URL: https://api.oneprovider.dev/v1/chat/completions
Authentication Type: API Key via HTTP Header
Header Key: Authorization
Header Value: Bearer sk-your-key-here
Model ID: gpt-6.1-terra

Header Value is the word Bearer, a space, then your whole key. Claude ids such as claude-sonnet-5-5 work on this route too.

3. Temperature and request options

• Leave temperature at the default. Claude 5.x models answer 400 to a non-default temperature; if you changed it in TypingMind’s model or chat settings, reset it.
• Route requests via TypingMind Cloud is not needed: our API accepts requests straight from the browser (CORS).

4. Test & Save

Click Test & Save, then pick the new model in a chat.

Each model is a separate custom model: repeat the steps for every id you want, with the same Endpoint URL and key.

Which model to choose

claude-opus-5-5 suits long, demanding chats, claude-sonnet-5-5 is the balanced default and claude-haiku-5-5 is the fast, cheap choice; GPT models such as gpt-6.1-terra go through the OpenAI Chat Completions API type. Type the id exactly as on the models page ; rates are on the pricing page .

Common errors and fixes

404 Not Found

The Endpoint URL is a base URL (https://api.oneprovider.dev/v1 or https://api.oneprovider.dev). Use https://api.oneprovider.dev/v1/messages for the Claude Messages API type or https://api.oneprovider.dev/v1/chat/completions for the OpenAI Chat Completions API type.

The model is not found or not available

Model ID must be the exact id, for example claude-opus-5-5, not the model’s display name. Copy it from the models page .

400 about temperature

Claude 5.x models accept only the default temperature. Reset temperature in TypingMind to the default and send the message again.

401 authentication_error

Claude Messages API: Header Key x-api-key and the whole key as the value. OpenAI Chat Completions API: Header Key Authorization and Bearer sk-... as the value.

The key does not work in TypingMind’s built-in Claude field

That field sends requests to Anthropic, which does not know a OneProvider key. Add OneProvider as a custom model as shown above.

FAQ

Does TypingMind want a base URL or the full endpoint?

The full endpoint. TypingMind does not append a route, so the address must end with /v1/messages or /v1/chat/completions.

Do I need Route requests via TypingMind Cloud?

No. Our API accepts requests from the browser (CORS), so TypingMind can call it directly.

Can I use GPT models?

Yes: choose the OpenAI Chat Completions API type and a GPT id such as gpt-6.1-terra.

Can one entry cover all models?

No. Each model is a separate custom model with the same Endpoint URL and key.

Quick answers

Which base URL do I use?

Claude Code and Anthropic SDKs use https://api.oneprovider.dev. OpenAI SDKs and OpenAI-compatible clients use https://api.oneprovider.dev/v1. One key works behind both; the model list is on the models page ; rates are on the pricing page .

How do I authenticate?

Send the raw sk-… key in x-api-key or Authorization: Bearer: one of them, never both. Keep the key in an environment variable, not in a file that gets committed. More on authentication .

Where do I get a key?

Open your cabinet in the Telegram bot @oneprovider_robot or at app.oneprovider.dev, top up the balance and press “Issue a key”. Each key can carry its own spend limit. Cabinet & API keys .

What do 401, 404 and 429 mean?

401: the key is missing, mistyped or sent in the wrong header; paste the whole key without quotes or spaces. 404: usually a wrong base URL, for example a missing or doubled /v1. 429 with “Insufficient balance”: the cabinet balance or the key’s spend limit is used up, so top up instead of retrying; any other 429 is a rate limit, so wait for Retry-After. Details: error codes and troubleshooting .

Why do streams cut off or reset?

VPN and VLESS proxies often buffer SSE or break HTTP/2 negotiation. OneProvider has no regional restrictions and does not buffer streams, so turn the proxy off and retry.

Where do I ask if this is not enough?

Message @Oneproviderhelpbot on Telegram or open “Support” in the web cabinet, with the HTTP status code and the exact error message. How support works .