diff --git a/docs/providers/inferrs.md b/docs/providers/inferrs.md index 11817c3a65d..982fa9616c1 100644 --- a/docs/providers/inferrs.md +++ b/docs/providers/inferrs.md @@ -7,12 +7,19 @@ read_when: title: "Inferrs" --- -[inferrs](https://github.com/ericcurtin/inferrs) can serve local models behind an -OpenAI-compatible `/v1` API. OpenClaw works with `inferrs` through the generic -`openai-completions` path. +[inferrs](https://github.com/ericcurtin/inferrs) can serve local models behind an OpenAI-compatible `/v1` API. OpenClaw works with `inferrs` through the generic `openai-completions` path. -`inferrs` is currently best treated as a custom self-hosted OpenAI-compatible -backend, not a dedicated OpenClaw provider plugin. +| Property | Value | +| ------------------ | ------------------------------------------------------------------ | +| Provider id | `inferrs` (custom; configure under `models.providers.inferrs`) | +| Plugin | none — `inferrs` is not a bundled OpenClaw provider plugin | +| Auth env var | Optional. Any value works if your inferrs server has no auth | +| API | OpenAI-compatible (`openai-completions`) | +| Suggested base URL | `http://127.0.0.1:8080/v1` (or wherever your inferrs server lives) | + + + `inferrs` is currently best treated as a custom self-hosted OpenAI-compatible backend, not a dedicated OpenClaw provider plugin. You configure it through `models.providers.inferrs` rather than an onboarding choice flag. If you need a true bundled plugin with auto-discovery, see [SGLang](/providers/sglang) or [vLLM](/providers/vllm). + ## Getting started diff --git a/docs/providers/mistral.md b/docs/providers/mistral.md index de0f156b9f9..d73499009d3 100644 --- a/docs/providers/mistral.md +++ b/docs/providers/mistral.md @@ -7,13 +7,21 @@ read_when: title: "Mistral" --- -OpenClaw supports Mistral for both text/image model routing (`mistral/...`) and -audio transcription via Voxtral in media understanding. -Mistral can also be used for memory embeddings (`memorySearch.provider = "mistral"`). +OpenClaw includes a bundled Mistral plugin that registers four contracts: chat completions, media understanding (Voxtral batch transcription), realtime STT for Voice Call (Voxtral Realtime), and memory embeddings (`mistral-embed`). -- Provider: `mistral` -- Auth: `MISTRAL_API_KEY` -- API: Mistral Chat Completions (`https://api.mistral.ai/v1`) +| Property | Value | +| ---------------- | ------------------------------------------- | +| Provider id | `mistral` | +| Plugin | bundled, `enabledByDefault: true` | +| Auth env var | `MISTRAL_API_KEY` | +| Onboarding flag | `--auth-choice mistral-api-key` | +| Direct CLI flag | `--mistral-api-key ` | +| API | OpenAI-compatible (`openai-completions`) | +| Base URL | `https://api.mistral.ai/v1` | +| Default model | `mistral/mistral-large-latest` | +| Embedding model | `mistral-embed` | +| Voxtral batch | `voxtral-mini-latest` (audio transcription) | +| Voxtral realtime | `voxtral-mini-transcribe-realtime-2602` | ## Getting started @@ -157,10 +165,10 @@ matching `sampleRate` only if your upstream stream is already raw PCM. - - Mistral auth uses `MISTRAL_API_KEY`. - - Provider base URL defaults to `https://api.mistral.ai/v1`. + - Mistral auth uses `MISTRAL_API_KEY` (Bearer header). + - Provider base URL defaults to `https://api.mistral.ai/v1` and accepts the standard OpenAI-compatible chat-completions request shape. - Onboarding default model is `mistral/mistral-large-latest`. - - Z.AI uses Bearer auth with your API key. + - Override the base URL under `models.providers.mistral.baseUrl` only when Mistral explicitly publishes a regional endpoint you need. diff --git a/docs/providers/tencent.md b/docs/providers/tencent.md index 6ef772af9f6..ae97e8eed93 100644 --- a/docs/providers/tencent.md +++ b/docs/providers/tencent.md @@ -6,20 +6,19 @@ read_when: - You need the TokenHub API key setup --- -# Tencent Cloud TokenHub +Tencent Cloud ships as a bundled provider plugin in OpenClaw. It gives access to Tencent Hy3 preview through the TokenHub endpoint (`tencent-tokenhub`) using an OpenAI-compatible API. -Tencent Cloud ships as a **bundled provider plugin** in OpenClaw. It gives access to Tencent Hy3 preview through the TokenHub endpoint (`tencent-tokenhub`). - -The provider uses an OpenAI-compatible API. - -| Property | Value | -| ------------- | ------------------------------------------ | -| Provider | `tencent-tokenhub` | -| Default model | `tencent-tokenhub/hy3-preview` | -| Auth | `TOKENHUB_API_KEY` | -| API | OpenAI-compatible chat completions | -| Base URL | `https://tokenhub.tencentmaas.com/v1` | -| Global URL | `https://tokenhub-intl.tencentmaas.com/v1` | +| Property | Value | +| ---------------- | ----------------------------------------------------- | +| Provider id | `tencent-tokenhub` | +| Plugin | bundled, `enabledByDefault: true` | +| Auth env var | `TOKENHUB_API_KEY` | +| Onboarding flag | `--auth-choice tokenhub-api-key` | +| Direct CLI flag | `--tokenhub-api-key ` | +| API | OpenAI-compatible (`openai-completions`) | +| Default base URL | `https://tokenhub.tencentmaas.com/v1` | +| Global base URL | `https://tokenhub-intl.tencentmaas.com/v1` (override) | +| Default model | `tencent-tokenhub/hy3-preview` | ## Quick start @@ -28,9 +27,24 @@ The provider uses an OpenAI-compatible API. Create an API key in Tencent Cloud TokenHub. If you choose a limited access scope for the key, include **Hy3 preview** in the allowed models. - ```bash - openclaw onboard --auth-choice tokenhub-api-key - ``` + + +```bash Onboarding +openclaw onboard --auth-choice tokenhub-api-key +``` + +```bash Direct flag +openclaw onboard --non-interactive \ + --auth-choice tokenhub-api-key \ + --tokenhub-api-key "$TOKENHUB_API_KEY" +``` + +```bash Env only +export TOKENHUB_API_KEY=... +``` + + + ```bash @@ -59,38 +73,58 @@ openclaw onboard --non-interactive \ Hy3 preview is Tencent Hunyuan's large MoE language model for reasoning, long-context instruction following, code, and agent workflows. Tencent's OpenAI-compatible examples use `hy3-preview` as the model id and support standard chat-completions tool calling plus `reasoning_effort`. -The model id is `hy3-preview`. Do not confuse it with Tencent's `HY-3D-*` models, which are 3D generation APIs and are not the OpenClaw chat model configured by this provider. + The model id is `hy3-preview`. Do not confuse it with Tencent's `HY-3D-*` models, which are 3D generation APIs and are not the OpenClaw chat model configured by this provider. -## Endpoint override +## Tiered pricing -OpenClaw defaults to Tencent Cloud's `https://tokenhub.tencentmaas.com/v1` endpoint. Tencent also documents an international TokenHub endpoint: +The bundled catalog ships tiered cost metadata that scales with input window length, so cost estimates are populated without manual overrides. -```bash -openclaw config set models.providers.tencent-tokenhub.baseUrl "https://tokenhub-intl.tencentmaas.com/v1" -``` +| Input tokens range | Input rate | Output rate | Cache read | +| ------------------ | ---------- | ----------- | ---------- | +| 0 - 16,000 | 0.176 | 0.587 | 0.059 | +| 16,000 - 32,000 | 0.235 | 0.939 | 0.088 | +| 32,000+ | 0.293 | 1.173 | 0.117 | -Only override the endpoint when your TokenHub account or region requires it. +Rates are per million tokens in USD as advertised by Tencent. Override pricing under `models.providers.tencent-tokenhub` only when you need a different surface. -## Notes +## Advanced configuration -- TokenHub model refs use `tencent-tokenhub/`. -- The bundled catalog currently includes `hy3-preview`. -- The plugin marks Hy3 preview as reasoning-capable and streaming-usage capable. -- The plugin ships with tiered Hy3 pricing metadata, so cost estimates are populated without manual pricing overrides. -- Override pricing, context, or endpoint metadata in `models.providers` only when needed. + + + OpenClaw defaults to Tencent Cloud's `https://tokenhub.tencentmaas.com/v1` endpoint. Tencent also documents an international TokenHub endpoint: -## Environment note + ```bash + openclaw config set models.providers.tencent-tokenhub.baseUrl "https://tokenhub-intl.tencentmaas.com/v1" + ``` -If the Gateway runs as a daemon (launchd/systemd), make sure `TOKENHUB_API_KEY` -is available to that process (for example, in `~/.openclaw/.env` or via -`env.shellEnv`). + Only override the endpoint when your TokenHub account or region requires it. -## Related documentation + -- [OpenClaw Configuration](/gateway/configuration) -- [Model Providers](/concepts/model-providers) -- [Tencent TokenHub product page](https://cloud.tencent.com/product/tokenhub) -- [Tencent TokenHub text generation](https://cloud.tencent.com/document/product/1823/130079) -- [Tencent TokenHub Cline setup for Hy3 preview](https://cloud.tencent.com/document/product/1823/130932) -- [Tencent Hy3 preview model card](https://huggingface.co/tencent/Hy3-preview) + + If the Gateway runs as a managed service (launchd, systemd, Docker), `TOKENHUB_API_KEY` must be visible to that process. Set it in `~/.openclaw/.env` or via `env.shellEnv` so launchd, systemd, or Docker exec environments can read it. + + + Keys set only in `~/.profile` are not visible to managed gateway processes. Use the env file or config seam for persistent availability. + + + + + +## Related + + + + Choosing providers, model refs, and failover behavior. + + + Full config schema including provider settings. + + + Tencent Cloud's TokenHub product page. + + + Tencent Hunyuan Hy3 preview details and benchmarks. + +