> ## Documentation Index
> Fetch the complete documentation index at: https://docs.uncensoredgpt.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Use with coding agents

> Connect OpenCode, Pi, Claude Code, or any OpenAI-compatible coding agent to the UncensoredGPT API.

Coding agents work out of the box with UncensoredGPT — every model in the catalog supports tool calling, and the API speaks both the OpenAI and Anthropic formats. Setup takes about a minute.

## The universal recipe

Any agent that accepts a custom OpenAI-compatible provider needs exactly three things:

1. **Base URL** — `https://api.uncensoredgpt.ai/v1`

2. **API key** — create one in the [Console](https://console.uncensoredgpt.ai) and export it as an environment variable:

   ```bash theme={null}
   export UNCENSOREDGPT_API_KEY="sk-..."
   ```

3. **Model ID** — the exact IDs returned by [List models](https://docs.uncensoredgpt.ai/api-reference/endpoints/models/list-models.md), e.g. `uncensoredgpt/qwen3.8-27b-uncensored`. Never invent or shorten them.

That's it. If your agent isn't listed below, point it at the base URL with your key and pick a model — it will just work.

## Guides per agent

| Agent | API format | Guide |
| - | - | - |
| **[OpenCode](https://opencode.ai)** (Recommended) | OpenAI-compatible | [Connect OpenCode](https://docs.uncensoredgpt.ai/api-reference/agents/opencode.md) |
| **[Pi](https://pi.dev)** | OpenAI-compatible | [Connect Pi](https://docs.uncensoredgpt.ai/api-reference/agents/pi.md) |
| **[Claude Code](https://claude.com/claude-code)** | Anthropic-compatible | [Connect Claude Code](https://docs.uncensoredgpt.ai/api-reference/agents/claude-code.md) |
| [Cline](https://cline.bot), [Roo Code](https://roocode.com), [Aider](https://aider.chat), [Cursor](https://cursor.com), … | OpenAI-compatible | Use the universal recipe above |

> [!NOTE]
>
> We recommend starting with [OpenCode](https://opencode.ai) — it's free and open source, connects to UncensoredGPT with a single config file, and supports all ten models out of the box.

## Available models

All `uncensoredgpt/` models run on our own infrastructure — no filters, no logs, and your code never leaves our servers.

| Model ID | Context | Tool calling | Reasoning |
| - | - | - | - |
| `uncensoredgpt/qwen3.8-27b-uncensored` | 262,000 | ✓ | ✓ |
| `uncensoredgpt/qwen3.6-35b-a3b-uncensored` | 262,000 | ✓ | ✓ |
| `uncensoredgpt/gemma4-31b-uncensored` | 131,072 | ✓ | ✓ |
| `uncensoredgpt/gemma4-26b-a4b-uncensored` | 131,072 | ✓ | ✓ |
| `uncensoredgpt/uncensoredgpt` | 262,000 | ✓ | ✓ |
| `uncensoredgpt/qwen3.8-flash-next-cybersecurity` | 262,000 | ✓ | ✓ |
| `uncensoredgpt/deepseek-v4.1-flash-uncensored` | 1,000,000 | ✓ | ✓ |
| `uncensoredgpt/glm-5.3-flash-uncensored` | 1,000,000 | ✓ | ✓ |
| `uncensoredgpt/glm-5.3-uncensored` | 1,000,000 | ✓ | ✓ |
| `uncensoredgpt/neuralnet-free-model` | 200,000 | ✓ | — |

> [!NOTE]
>
> The free model is for testing our servers — it is not uncensored and reliability is not guaranteed. For agent work, pick one of the uncensored models. The full catalog — including third-party and free models — is on the [Model catalog](https://docs.uncensoredgpt.ai/api-reference/model-catalog.md) page.

## Good to know

* **Tool calling** is required by agents and supported by every model above.
* **Streaming** is supported and enabled by agents automatically.
* **Per-key limits** (requests/minute, tokens/minute) apply to agent usage too — see [Rate limits](https://docs.uncensoredgpt.ai/api-reference/rate-limits.md). Agents retry on `429`, but raise your limits if you run long sessions.
* **Costs** are per token and visible per request in the Console's [Usage](https://docs.uncensoredgpt.ai/console/usage.md) page. Long agent sessions consume a lot of context — the 1M-context models are a good fit.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.