vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 05:20:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(providers): rewrite Tencent, Mistral, and Inferrs with code-verified setup

Browse Source 
Tencent (docs/providers/tencent.md): rewrote against
extensions/tencent/openclaw.plugin.json. Removed the duplicate
'# Tencent Cloud TokenHub' H1 (Mintlify renders title from frontmatter;
the in-body H1 produces a brittle anchor). Added a properties summary
with onboarding flag and direct CLI flag. Promoted the Quick Start
auth step into a CodeGroup covering onboarding/direct/env. Added a
tiered-pricing table sourced from the bundled cost.tieredPricing
metadata so cost expectations are visible alongside the catalog.
Replaced trailing bullet list under 'Related documentation' with a
CardGroup pointing at TokenHub product/model-card pages.

Mistral (docs/providers/mistral.md): replaced the 3-bullet provider
header with a properties table that surfaces all four contracts the
plugin registers (chat completions via the model catalog, media
understanding Voxtral batch, voice-call streaming Voxtral Realtime, and
memory embeddings via mistral-embed) plus the onboarding flag and
direct CLI flag. Removed a stray 'Z.AI uses Bearer auth' line that had
leaked into the 'Auth and base URL' accordion from a copy-paste
elsewhere; replaced it with a Mistral-correct base-URL override note.
Verified the seven-row LLM catalog matches plugin manifest model ids.

Inferrs (docs/providers/inferrs.md): added a properties table
explicitly stating that inferrs is NOT a bundled plugin and is
configured under models.providers.inferrs (no onboarding choice flag,
no extension package). Cross-linked SGLang and vLLM as bundled
self-hosted alternatives so readers picking a local backend can
compare.
This commit is contained in:
Vincent Koc
2026-05-05 17:24:29 -07:00
parent d583013b8f
commit 813fe0a3be
3 changed files with 103 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
docs/providers/inferrs.md
View File

@@ -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) |
<Note>
`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).
</Note>
## Getting started

26
docs/providers/mistral.md
View File

@@ -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 <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.
</Accordion>
<Accordion title="Auth and base URL">
- 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.
</Accordion>
</AccordionGroup>

114
docs/providers/tencent.md
View File

@@ -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 <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.
</Step>
<Step title="Run onboarding">
```bash
openclaw onboard --auth-choice tokenhub-api-key
```
<CodeGroup>
```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=...
```
</CodeGroup>
</Step>
<Step title="Verify the model">
```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`.
<Tip>
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.
</Tip>
## 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/<modelId>`.
- 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.
<AccordionGroup>
<Accordion title="Endpoint override">
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
</Accordion>
- [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)
<Accordion title="Environment availability for the daemon">
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.
<Warning>
Keys set only in `~/.profile` are not visible to managed gateway processes. Use the env file or config seam for persistent availability.
</Warning>
</Accordion>
</AccordionGroup>
## Related
<CardGroup cols={2}>
<Card title="Model providers" href="/concepts/model-providers" icon="layers">
Choosing providers, model refs, and failover behavior.
</Card>
<Card title="Configuration reference" href="/gateway/configuration" icon="gear">
Full config schema including provider settings.
</Card>
<Card title="Tencent TokenHub" href="https://cloud.tencent.com/product/tokenhub" icon="arrow-up-right-from-square">
Tencent Cloud's TokenHub product page.
</Card>
<Card title="Hy3 preview model card" href="https://huggingface.co/tencent/Hy3-preview" icon="square-poll-horizontal">
Tencent Hunyuan Hy3 preview details and benchmarks.
</Card>
</CardGroup>