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

# OpenRouter

> Run models from Anthropic, OpenAI, Google, Meta, DeepSeek, Qwen, Moonshot AI, and Z.ai in Guild through one OpenRouter API key.

OpenRouter is a third-party inference provider. It routes to models from every publisher Guild supports, so one OpenRouter key can reach all of them. Guild calls OpenRouter with your API key, and OpenRouter bills the calls to your account.

| | |
| - | - |
| **Inference provider** in the app | OpenRouter |
| Authentication | An OpenRouter API key |
| Model IDs | Mapped from canonical names for you |

## Publishers on OpenRouter

| Publisher | OpenRouter namespace | Page |
| - | - | - |
| Anthropic | `anthropic/` | [Anthropic](/platform/models/anthropic) |
| OpenAI | `openai/` | [OpenAI](/platform/models/openai) |
| Gemini | `google/` | [Gemini](/platform/models/gemini) |
| Meta | `meta/` for Muse, `meta-llama/` for Llama | [Meta](/platform/models/meta) |
| DeepSeek | `deepseek/` | [DeepSeek](/platform/models/deepseek) |
| Alibaba | `qwen/` | [Qwen](/platform/models/qwen) |
| Moonshot AI | `moonshotai/` | [Moonshot AI](/platform/models/moonshot) |
| Z.ai | `z-ai/` | [Z.ai](/platform/models/zai) |

Guild refreshes its list from OpenRouter's public model catalog every day, keeping the text models in these namespaces. Variants with a suffix after a colon, such as `:free`, aren't listed. To see what's available, browse [OpenRouter's models](https://openrouter.ai/models) and drop the namespace: `qwen/qwen3-coder` becomes `qwen3-coder`.

## Connect OpenRouter

<Steps>
  <Step title="Create a key">In your OpenRouter account, create an API key.</Step>
  <Step title="Start the credential">In Guild, click **Access & setup** in the left nav, then **Models & providers**. Click **Add API key** and choose **OpenRouter** from the menu.</Step>
  <Step title="Name it and paste the key">Give the credential a **Name**, such as `Production`, and paste the key into **API key**.</Step>
  <Step title="Choose publishers">Under **Models**, check each publisher this credential should reach. Keep or change the default model next to each one.</Step>
  <Step title="Save">Click **Add Key**.</Step>
</Steps>

One OpenRouter credential can reach every publisher at once. Check them all to use a single key for everything.

## Model IDs

Write canonical model names, such as `claude-sonnet-4-6` or `deepseek-r1`, in policies and `llmPreferences`, without the OpenRouter namespace. Guild adds the namespace for you. OpenRouter spells Claude versions with dots, so Guild maps `claude-sonnet-4-6` to `anthropic/claude-sonnet-4.6`.

## Pricing

OpenRouter bills your OpenRouter account at its own rates, and those rates change as OpenRouter and the model publishers update them. For current prices, check each model's page on [OpenRouter's models list](https://openrouter.ai/models), and see [OpenRouter pricing](https://openrouter.ai/pricing) for how OpenRouter charges.

Guild's [Usage](/insights/usage) pages estimate spend from Guild's own price list, which can lag behind OpenRouter's. For a model Guild hasn't priced yet, the estimate uses a fallback rate. Your OpenRouter account is the source of truth for what you paid.

## Related pages

* [Models & providers](/platform/llm-settings) for credentials, model policies, and the daily token limit
* [AWS Bedrock](/platform/providers/aws-bedrock) and [Fireworks AI](/platform/providers/fireworks), the other third-party providers