Open Cowork

Open Cowork is an AI-powered workspace. Configuration is UI-only — no config file to edit.

1. Open Settings

Click the gear icon in the bottom-left corner of the Open Cowork interface.

2. API Settings

1. In the left sidebar, select API Settings.
2. Click More Models to add a custom provider.
3. Paste your OneProvider key in the API Key field.
4. Set Protocol to Anthropic from the dropdown.

3. Base URL and Model

1. Scroll to the Base URL field and enter: https://api.oneprovider.dev — without /v1: Open Cowork appends /v1/messages itself.
2. In Model, enter the exact id:
   • claude-fable-5 — Claude Fable 5, frontier tier
   • claude-haiku-4-5 — Claude Haiku 4.5, speed tier
   • claude-haiku-4-5-20251001 — Claude Haiku 4.5 20251001, speed tier
   • claude-haiku-4-5-20251001-thinking — Claude Haiku 4.5 20251001 Thinking, speed tier
   • claude-haiku-4-5-thinking — Claude Haiku 4.5 Thinking, speed tier
   • claude-opus-4-7 — Claude Opus 4.7, frontier tier
   • claude-opus-4-8 — Claude Opus 4.8, flagship tier
   • claude-opus-5 — Claude Opus 5, flagship tier
   • claude-opus-5-5 — Claude Opus 5.5, flagship tier
   • claude-sonnet-5-5 — Claude Sonnet 5.5, balanced tier
   • claude-haiku-5-5 — Claude Haiku 5.5, speed tier
   • claude-opus-5-thinking — Claude Opus 5 Thinking, frontier tier
   • claude-sonnet-4-6 — Claude Sonnet 4.6, balanced tier
   • claude-sonnet-5 — Claude Sonnet 5, balanced tier
   • claude-sonnet-5-thinking — Claude Sonnet 5 Thinking, frontier tier
   • claude-fable-5-1 — Claude Fable 5.1, frontier tier
3. Click Save.

Which model to choose

Type the model id exactly as listed above. claude-sonnet-5-5 is the balanced default for everyday tasks, claude-opus-5-5 suits long, complex work, and claude-haiku-5-5 is the fast and cheap choice. You can change the id in API Settings at any time; the next request uses it. Rates are on the pricing page .

Common errors and fixes

404

The Base URL must be https://api.oneprovider.dev without /v1: Open Cowork appends /v1/messages.

401

The key is truncated or has a space around it. Paste the whole key and make sure Protocol is set to Anthropic.

“Model not found”

The id has a typo. Copy it from the list above; it is case-sensitive.

429 “Insufficient balance”

Balance or key limit is used up. Top up the cabinet.

FAQ

Do I need to restart after changing the model?

No. The next request uses the new id.

Which protocol do I pick?

Anthropic.

Where do I see usage?

In the dashboard Usage page of the 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 .