diff --git a/docs/providers/arcee.md b/docs/providers/arcee.md index a085fa47d3d..a7fdee17582 100644 --- a/docs/providers/arcee.md +++ b/docs/providers/arcee.md @@ -12,58 +12,89 @@ read_when: Arcee AI models can be accessed directly via the Arcee platform or through [OpenRouter](/providers/openrouter). -- Provider: `arcee` -- Auth: `ARCEEAI_API_KEY` (direct) or `OPENROUTER_API_KEY` (via OpenRouter) -- API: OpenAI-compatible -- Base URL: `https://api.arcee.ai/api/v1` (direct) or `https://openrouter.ai/api/v1` (OpenRouter) +| Property | Value | +| -------- | ------------------------------------------------------------------------------------- | +| Provider | `arcee` | +| Auth | `ARCEEAI_API_KEY` (direct) or `OPENROUTER_API_KEY` (via OpenRouter) | +| API | OpenAI-compatible | +| Base URL | `https://api.arcee.ai/api/v1` (direct) or `https://openrouter.ai/api/v1` (OpenRouter) | -## Quick start +## Getting started -1. Get an API key from [Arcee AI](https://chat.arcee.ai/) or [OpenRouter](https://openrouter.ai/keys). + + + + + Create an API key at [Arcee AI](https://chat.arcee.ai/). + + + ```bash + openclaw onboard --auth-choice arceeai-api-key + ``` + + + ```json5 + { + agents: { + defaults: { + model: { primary: "arcee/trinity-large-thinking" }, + }, + }, + } + ``` + + + -2. Set the API key (recommended: store it for the Gateway): + + + + Create an API key at [OpenRouter](https://openrouter.ai/keys). + + + ```bash + openclaw onboard --auth-choice arceeai-openrouter + ``` + + + ```json5 + { + agents: { + defaults: { + model: { primary: "arcee/trinity-large-thinking" }, + }, + }, + } + ``` -```bash -# Direct (Arcee platform) -openclaw onboard --auth-choice arceeai-api-key + The same model refs work for both direct and OpenRouter setups (for example `arcee/trinity-large-thinking`). + + -# Via OpenRouter -openclaw onboard --auth-choice arceeai-openrouter -``` + + -3. Set a default model: +## Non-interactive setup -```json5 -{ - agents: { - defaults: { - model: { primary: "arcee/trinity-large-thinking" }, - }, - }, -} -``` + + + ```bash + openclaw onboard --non-interactive \ + --mode local \ + --auth-choice arceeai-api-key \ + --arceeai-api-key "$ARCEEAI_API_KEY" + ``` + -## Non-interactive example - -```bash -# Direct (Arcee platform) -openclaw onboard --non-interactive \ - --mode local \ - --auth-choice arceeai-api-key \ - --arceeai-api-key "$ARCEEAI_API_KEY" - -# Via OpenRouter -openclaw onboard --non-interactive \ - --mode local \ - --auth-choice arceeai-openrouter \ - --openrouter-api-key "$OPENROUTER_API_KEY" -``` - -## Environment note - -If the Gateway runs as a daemon (launchd/systemd), make sure `ARCEEAI_API_KEY` -(or `OPENROUTER_API_KEY`) is available to that process (for example, in -`~/.openclaw/.env` or via `env.shellEnv`). + + ```bash + openclaw onboard --non-interactive \ + --mode local \ + --auth-choice arceeai-openrouter \ + --openrouter-api-key "$OPENROUTER_API_KEY" + ``` + + ## Built-in catalog @@ -75,13 +106,41 @@ OpenClaw currently ships this bundled Arcee catalog: | `arcee/trinity-large-preview` | Trinity Large Preview | text | 128K | $0.25 / $1.00 | General-purpose; 400B params, 13B active | | `arcee/trinity-mini` | Trinity Mini 26B | text | 128K | $0.045 / $0.15 | Fast and cost-efficient; function calling | -The same model refs work for both direct and OpenRouter setups (for example `arcee/trinity-large-thinking`). - + The onboarding preset sets `arcee/trinity-large-thinking` as the default model. + ## Supported features -- Streaming -- Tool use / function calling -- Structured output (JSON mode and JSON schema) -- Extended thinking (Trinity Large Thinking) +| Feature | Supported | +| --------------------------------------------- | ---------------------------- | +| Streaming | Yes | +| Tool use / function calling | Yes | +| Structured output (JSON mode and JSON schema) | Yes | +| Extended thinking | Yes (Trinity Large Thinking) | + + + + If the Gateway runs as a daemon (launchd/systemd), make sure `ARCEEAI_API_KEY` + (or `OPENROUTER_API_KEY`) is available to that process (for example, in + `~/.openclaw/.env` or via `env.shellEnv`). + + + + When using Arcee models via OpenRouter, the same `arcee/*` model refs apply. + OpenClaw handles routing transparently based on your auth choice. See the + [OpenRouter provider docs](/providers/openrouter) for OpenRouter-specific + configuration details. + + + +## Related + + + + Access Arcee models and many others through a single API key. + + + Choosing providers, model refs, and failover behavior. + + diff --git a/docs/providers/github-copilot.md b/docs/providers/github-copilot.md index 3b01947253f..f18942f904f 100644 --- a/docs/providers/github-copilot.md +++ b/docs/providers/github-copilot.md @@ -8,73 +8,107 @@ title: "GitHub Copilot" # GitHub Copilot -## What is GitHub Copilot? - GitHub Copilot is GitHub's AI coding assistant. It provides access to Copilot models for your GitHub account and plan. OpenClaw can use Copilot as a model provider in two different ways. ## Two ways to use Copilot in OpenClaw -### 1) Built-in GitHub Copilot provider (`github-copilot`) + + + Use the native device-login flow to obtain a GitHub token, then exchange it for + Copilot API tokens when OpenClaw runs. This is the **default** and simplest path + because it does not require VS Code. -Use the native device-login flow to obtain a GitHub token, then exchange it for -Copilot API tokens when OpenClaw runs. This is the **default** and simplest path -because it does not require VS Code. + + + ```bash + openclaw models auth login-github-copilot + ``` -### 2) Copilot Proxy plugin (`copilot-proxy`) + You will be prompted to visit a URL and enter a one-time code. Keep the + terminal open until it completes. + + + ```bash + openclaw models set github-copilot/gpt-4o + ``` -Use the **Copilot Proxy** VS Code extension as a local bridge. OpenClaw talks to -the proxy’s `/v1` endpoint and uses the model list you configure there. Choose -this when you already run Copilot Proxy in VS Code or need to route through it. -You must enable the plugin and keep the VS Code extension running. + Or in config: -Use GitHub Copilot as a model provider (`github-copilot`). The login command runs -the GitHub device flow, saves an auth profile, and updates your config to use that -profile. + ```json5 + { + agents: { defaults: { model: { primary: "github-copilot/gpt-4o" } } }, + } + ``` + + -## CLI setup - -```bash -openclaw models auth login-github-copilot -``` - -You'll be prompted to visit a URL and enter a one-time code. Keep the terminal -open until it completes. - -### Optional flags + + + + Use the **Copilot Proxy** VS Code extension as a local bridge. OpenClaw talks to + the proxy's `/v1` endpoint and uses the model list you configure there. + + + Choose this when you already run Copilot Proxy in VS Code or need to route + through it. You must enable the plugin and keep the VS Code extension running. + + + + + +## Optional flags + +| Flag | Description | +| --------------- | --------------------------------------------------- | +| `--yes` | Skip the confirmation prompt | +| `--set-default` | Also apply the provider's recommended default model | ```bash +# Skip confirmation openclaw models auth login-github-copilot --yes -``` -To also apply the provider's recommended default model in one step, use the -generic auth command instead: - -```bash +# Login and set the default model in one step openclaw models auth login --provider github-copilot --method device --set-default ``` -## Set a default model + + + The device-login flow requires an interactive TTY. Run it directly in a + terminal, not in a non-interactive script or CI pipeline. + -```bash -openclaw models set github-copilot/gpt-4o -``` + + Copilot model availability depends on your GitHub plan. If a model is + rejected, try another ID (for example `github-copilot/gpt-4.1`). + -### Config snippet + + Claude model IDs use the Anthropic Messages transport automatically. GPT, + o-series, and Gemini models keep the OpenAI Responses transport. OpenClaw + selects the correct transport based on the model ref. + -```json5 -{ - agents: { defaults: { model: { primary: "github-copilot/gpt-4o" } } }, -} -``` + + The login stores a GitHub token in the auth profile store and exchanges it + for a Copilot API token when OpenClaw runs. You do not need to manage the + token manually. + + -## Notes + +Requires an interactive TTY. Run the login command directly in a terminal, not +inside a headless script or CI job. + -- Requires an interactive TTY; run it directly in a terminal. -- Copilot model availability depends on your plan; if a model is rejected, try - another ID (for example `github-copilot/gpt-4.1`). -- Claude model IDs use the Anthropic Messages transport automatically; GPT, o-series, - and Gemini models keep the OpenAI Responses transport. -- The login stores a GitHub token in the auth profile store and exchanges it for a - Copilot API token when OpenClaw runs. +## Related + + + + Choosing providers, model refs, and failover behavior. + + + Auth details and credential reuse rules. + + diff --git a/docs/providers/kilocode.md b/docs/providers/kilocode.md index 51d984062ea..378d9d3684e 100644 --- a/docs/providers/kilocode.md +++ b/docs/providers/kilocode.md @@ -11,25 +11,73 @@ read_when: Kilo Gateway provides a **unified API** that routes requests to many models behind a single endpoint and API key. It is OpenAI-compatible, so most OpenAI SDKs work by switching the base URL. -## Getting an API key +| Property | Value | +| -------- | ---------------------------------- | +| Provider | `kilocode` | +| Auth | `KILOCODE_API_KEY` | +| API | OpenAI-compatible | +| Base URL | `https://api.kilo.ai/api/gateway/` | -1. Go to [app.kilo.ai](https://app.kilo.ai) -2. Sign in or create an account -3. Navigate to API Keys and generate a new key +## Getting started -## CLI setup + + + Go to [app.kilo.ai](https://app.kilo.ai), sign in or create an account, then navigate to API Keys and generate a new key. + + + ```bash + openclaw onboard --auth-choice kilocode-api-key + ``` -```bash -openclaw onboard --auth-choice kilocode-api-key -``` + Or set the environment variable directly: -Or set the environment variable: + ```bash + export KILOCODE_API_KEY="" # pragma: allowlist secret + ``` -```bash -export KILOCODE_API_KEY="" # pragma: allowlist secret -``` + + + ```bash + openclaw models list --provider kilocode + ``` + + -## Config snippet +## Default model + +The default model is `kilocode/kilo/auto`, a provider-owned smart-routing +model managed by Kilo Gateway. + + +OpenClaw treats `kilocode/kilo/auto` as the stable default ref, but does not +publish a source-backed task-to-upstream-model mapping for that route. Exact +upstream routing behind `kilocode/kilo/auto` is owned by Kilo Gateway, not +hard-coded in OpenClaw. + + +## Available models + +OpenClaw dynamically discovers available models from the Kilo Gateway at startup. Use +`/models kilocode` to see the full list of models available with your account. + +Any model available on the gateway can be used with the `kilocode/` prefix: + +| Model ref | Notes | +| -------------------------------------- | ---------------------------------- | +| `kilocode/kilo/auto` | Default — smart routing | +| `kilocode/anthropic/claude-sonnet-4` | Anthropic via Kilo | +| `kilocode/openai/gpt-5.4` | OpenAI via Kilo | +| `kilocode/google/gemini-3-pro-preview` | Google via Kilo | +| ...and many more | Use `/models kilocode` to list all | + + +At startup, OpenClaw queries `GET https://api.kilo.ai/api/gateway/models` and merges +discovered models ahead of the static fallback catalog. The bundled fallback always +includes `kilocode/kilo/auto` (`Kilo Auto`) with `input: ["text", "image"]`, +`reasoning: true`, `contextWindow: 1000000`, and `maxTokens: 128000`. + + +## Config example ```json5 { @@ -42,48 +90,47 @@ export KILOCODE_API_KEY="" # pragma: allowlist secret } ``` -## Default model + + + Kilo Gateway is documented in source as OpenRouter-compatible, so it stays on + the proxy-style OpenAI-compatible path rather than native OpenAI request shaping. -The default model is `kilocode/kilo/auto`, a provider-owned smart-routing -model managed by Kilo Gateway. + - Gemini-backed Kilo refs stay on the proxy-Gemini path, so OpenClaw keeps + Gemini thought-signature sanitation there without enabling native Gemini + replay validation or bootstrap rewrites. + - Kilo Gateway uses a Bearer token with your API key under the hood. -OpenClaw treats `kilocode/kilo/auto` as the stable default ref, but does not -publish a source-backed task-to-upstream-model mapping for that route. + -## Available models + + Kilo's shared stream wrapper adds the provider app header and normalizes + proxy reasoning payloads for supported concrete model refs. -OpenClaw dynamically discovers available models from the Kilo Gateway at startup. Use -`/models kilocode` to see the full list of models available with your account. + + `kilocode/kilo/auto` and other proxy-reasoning-unsupported hints skip reasoning + injection. If you need reasoning support, use a concrete model ref such as + `kilocode/anthropic/claude-sonnet-4`. + -Any model available on the gateway can be used with the `kilocode/` prefix: + -``` -kilocode/kilo/auto (default - smart routing) -kilocode/anthropic/claude-sonnet-4 -kilocode/openai/gpt-5.4 -kilocode/google/gemini-3-pro-preview -...and many more -``` + + - If model discovery fails at startup, OpenClaw falls back to the bundled static catalog containing `kilocode/kilo/auto`. + - Confirm your API key is valid and that your Kilo account has the desired models enabled. + - When the Gateway runs as a daemon, ensure `KILOCODE_API_KEY` is available to that process (for example in `~/.openclaw/.env` or via `env.shellEnv`). + + -## Notes +## Related -- Model refs are `kilocode/` (e.g., `kilocode/anthropic/claude-sonnet-4`). -- Default model: `kilocode/kilo/auto` -- Base URL: `https://api.kilo.ai/api/gateway/` -- Bundled fallback catalog always includes `kilocode/kilo/auto` (`Kilo Auto`) with - `input: ["text", "image"]`, `reasoning: true`, `contextWindow: 1000000`, - and `maxTokens: 128000` -- At startup, OpenClaw tries `GET https://api.kilo.ai/api/gateway/models` and - merges discovered models ahead of the static fallback catalog -- Exact upstream routing behind `kilocode/kilo/auto` is owned by Kilo Gateway, - not hard-coded in OpenClaw -- Kilo Gateway is documented in source as OpenRouter-compatible, so it stays on - the proxy-style OpenAI-compatible path rather than native OpenAI request shaping -- Gemini-backed Kilo refs stay on the proxy-Gemini path, so OpenClaw keeps - Gemini thought-signature sanitation there without enabling native Gemini - replay validation or bootstrap rewrites. -- Kilo's shared stream wrapper adds the provider app header and normalizes - proxy reasoning payloads for supported concrete model refs. `kilocode/kilo/auto` - and other proxy-reasoning-unsupported hints skip that reasoning injection. -- For more model/provider options, see [/concepts/model-providers](/concepts/model-providers). -- Kilo Gateway uses a Bearer token with your API key under the hood. + + + Choosing providers, model refs, and failover behavior. + + + Full OpenClaw configuration reference. + + + Kilo Gateway dashboard, API keys, and account management. + + diff --git a/docs/providers/qianfan.md b/docs/providers/qianfan.md index b87d949299e..bf00d7fc668 100644 --- a/docs/providers/qianfan.md +++ b/docs/providers/qianfan.md @@ -6,31 +6,51 @@ read_when: title: "Qianfan" --- -# Qianfan Provider Guide +# Qianfan -Qianfan is Baidu's MaaS platform, provides a **unified API** that routes requests to many models behind a single +Qianfan is Baidu's MaaS platform, providing a **unified API** that routes requests to many models behind a single endpoint and API key. It is OpenAI-compatible, so most OpenAI SDKs work by switching the base URL. -## Prerequisites +| Property | Value | +| -------- | --------------------------------- | +| Provider | `qianfan` | +| Auth | `QIANFAN_API_KEY` | +| API | OpenAI-compatible | +| Base URL | `https://qianfan.baidubce.com/v2` | -1. A Baidu Cloud account with Qianfan API access -2. An API key from the Qianfan console -3. OpenClaw installed on your system +## Getting started -## Getting Your API Key + + + Sign up or log in at the [Qianfan Console](https://console.bce.baidu.com/qianfan/ais/console/apiKey) and ensure you have Qianfan API access enabled. + + + Create a new application or select an existing one, then generate an API key. The key format is `bce-v3/ALTAK-...`. + + + ```bash + openclaw onboard --auth-choice qianfan-api-key + ``` + + + ```bash + openclaw models list --provider qianfan + ``` + + -1. Visit the [Qianfan Console](https://console.bce.baidu.com/qianfan/ais/console/apiKey) -2. Create a new application or select an existing one -3. Generate an API key (format: `bce-v3/ALTAK-...`) -4. Copy the API key for use with OpenClaw +## Available models -## CLI setup +| Model ref | Input | Context | Max output | Reasoning | Notes | +| ------------------------------------ | ----------- | ------- | ---------- | --------- | ------------- | +| `qianfan/deepseek-v3.2` | text | 98,304 | 32,768 | Yes | Default model | +| `qianfan/ernie-5.0-thinking-preview` | text, image | 119,000 | 64,000 | Yes | Multimodal | -```bash -openclaw onboard --auth-choice qianfan-api-key -``` + +The default bundled model ref is `qianfan/deepseek-v3.2`. You only need to override `models.providers.qianfan` when you need a custom base URL or model metadata. + -## Config snippet +## Config example ```json5 { @@ -74,17 +94,40 @@ openclaw onboard --auth-choice qianfan-api-key } ``` -## Notes + + + Qianfan runs through the OpenAI-compatible transport path, not native OpenAI request shaping. This means standard OpenAI SDK features work, but provider-specific parameters may not be forwarded. + -- Default bundled model ref: `qianfan/deepseek-v3.2` -- Default base URL: `https://qianfan.baidubce.com/v2` -- Bundled catalog currently includes `deepseek-v3.2` and `ernie-5.0-thinking-preview` -- Add or override `models.providers.qianfan` only when you need custom base URL or model metadata -- Qianfan runs through the OpenAI-compatible transport path, not native OpenAI request shaping + + The bundled catalog currently includes `deepseek-v3.2` and `ernie-5.0-thinking-preview`. Add or override `models.providers.qianfan` only when you need a custom base URL or model metadata. -## Related Documentation + + Model refs use the `qianfan/` prefix (for example `qianfan/deepseek-v3.2`). + -- [OpenClaw Configuration](/gateway/configuration) -- [Model Providers](/concepts/model-providers) -- [Agent Setup](/concepts/agent) -- [Qianfan API Documentation](https://cloud.baidu.com/doc/qianfan-api/s/3m7of64lb) + + + + - Ensure your API key starts with `bce-v3/ALTAK-` and has Qianfan API access enabled in the Baidu Cloud console. + - If models are not listed, confirm your account has the Qianfan service activated. + - The default base URL is `https://qianfan.baidubce.com/v2`. Only change it if you use a custom endpoint or proxy. + + + +## Related + + + + Choosing providers, model refs, and failover behavior. + + + Full OpenClaw configuration reference. + + + Configuring agent defaults and model assignments. + + + Official Qianfan API documentation. + + diff --git a/docs/providers/xiaomi.md b/docs/providers/xiaomi.md index 0d2c8c8b724..3c098728bef 100644 --- a/docs/providers/xiaomi.md +++ b/docs/providers/xiaomi.md @@ -9,31 +9,53 @@ title: "Xiaomi MiMo" # Xiaomi MiMo Xiaomi MiMo is the API platform for **MiMo** models. OpenClaw uses the Xiaomi -OpenAI-compatible endpoint with API-key authentication. Create your API key in the -[Xiaomi MiMo console](https://platform.xiaomimimo.com/#/console/api-keys), then configure the -bundled `xiaomi` provider with that key. +OpenAI-compatible endpoint with API-key authentication. -## Built-in catalog +| Property | Value | +| -------- | ------------------------------- | +| Provider | `xiaomi` | +| Auth | `XIAOMI_API_KEY` | +| API | OpenAI-compatible | +| Base URL | `https://api.xiaomimimo.com/v1` | -- Base URL: `https://api.xiaomimimo.com/v1` -- API: `openai-completions` -- Authorization: `Bearer $XIAOMI_API_KEY` +## Getting started -| Model ref | Input | Context | Max output | Notes | -| ---------------------- | ----------- | --------- | ---------- | ---------------------------- | -| `xiaomi/mimo-v2-flash` | text | 262,144 | 8,192 | Default model | -| `xiaomi/mimo-v2-pro` | text | 1,048,576 | 32,000 | Reasoning-enabled | -| `xiaomi/mimo-v2-omni` | text, image | 262,144 | 32,000 | Reasoning-enabled multimodal | + + + Create an API key in the [Xiaomi MiMo console](https://platform.xiaomimimo.com/#/console/api-keys). + + + ```bash + openclaw onboard --auth-choice xiaomi-api-key + ``` -## CLI setup + Or pass the key directly: -```bash -openclaw onboard --auth-choice xiaomi-api-key -# or non-interactive -openclaw onboard --auth-choice xiaomi-api-key --xiaomi-api-key "$XIAOMI_API_KEY" -``` + ```bash + openclaw onboard --auth-choice xiaomi-api-key --xiaomi-api-key "$XIAOMI_API_KEY" + ``` -## Config snippet + + + ```bash + openclaw models list --provider xiaomi + ``` + + + +## Available models + +| Model ref | Input | Context | Max output | Reasoning | Notes | +| ---------------------- | ----------- | --------- | ---------- | --------- | ------------- | +| `xiaomi/mimo-v2-flash` | text | 262,144 | 8,192 | No | Default model | +| `xiaomi/mimo-v2-pro` | text | 1,048,576 | 32,000 | Yes | Large context | +| `xiaomi/mimo-v2-omni` | text, image | 262,144 | 32,000 | Yes | Multimodal | + + +The default model ref is `xiaomi/mimo-v2-flash`. The provider is injected automatically when `XIAOMI_API_KEY` is set or an auth profile exists. + + +## Config example ```json5 { @@ -81,9 +103,43 @@ openclaw onboard --auth-choice xiaomi-api-key --xiaomi-api-key "$XIAOMI_API_KEY" } ``` -## Notes + + + The `xiaomi` provider is injected automatically when `XIAOMI_API_KEY` is set in your environment or an auth profile exists. You do not need to manually configure the provider unless you want to override model metadata or the base URL. + -- Default model ref: `xiaomi/mimo-v2-flash`. -- Additional built-in models: `xiaomi/mimo-v2-pro`, `xiaomi/mimo-v2-omni`. -- The provider is injected automatically when `XIAOMI_API_KEY` is set (or an auth profile exists). -- See [/concepts/model-providers](/concepts/model-providers) for provider rules. + + - **mimo-v2-flash** — lightweight and fast, ideal for general-purpose text tasks. No reasoning support. + - **mimo-v2-pro** — supports reasoning with a 1M token context window for long-document workloads. + - **mimo-v2-omni** — reasoning-enabled multimodal model that accepts both text and image inputs. + + + All models use the `xiaomi/` prefix (for example `xiaomi/mimo-v2-pro`). + + + + + + - If models do not appear, confirm `XIAOMI_API_KEY` is set and valid. + - When the Gateway runs as a daemon, ensure the key is available to that process (for example in `~/.openclaw/.env` or via `env.shellEnv`). + + + Keys set only in your interactive shell are not visible to daemon-managed gateway processes. Use `~/.openclaw/.env` or `env.shellEnv` config for persistent availability. + + + + + +## Related + + + + Choosing providers, model refs, and failover behavior. + + + Full OpenClaw configuration reference. + + + Xiaomi MiMo dashboard and API key management. + +