mirror of https://github.com/openclaw/openclaw.git
docs(qwen): refresh provider and endpoint guides
This commit is contained in:
Peter Steinberger
parent
df7693027c
commit
889ddb5edf
|
|
@ -506,6 +506,7 @@ Options:
|
|||
`minimax-global-oauth`, `minimax-global-api`, `minimax-cn-oauth`, `minimax-cn-api`,
|
||||
`opencode-zen`, `opencode-go`, `github-copilot`, `copilot-proxy`, `xai-api-key`,
|
||||
`mistral-api-key`, `volcengine-api-key`, `byteplus-api-key`, `qianfan-api-key`,
|
||||
`qwen-standard-api-key-cn`, `qwen-standard-api-key`, `qwen-api-key-cn`, `qwen-api-key`,
|
||||
`modelstudio-standard-api-key-cn`, `modelstudio-standard-api-key`,
|
||||
`modelstudio-api-key-cn`, `modelstudio-api-key`, `custom-api-key`, `skip`
|
||||
- `--secret-input-mode <plaintext|ref>` (default `plaintext`; use `ref` to store provider default env refs instead of plaintext keys)
|
||||
|
|
|
|||
|
|
@ -136,7 +136,7 @@ Current bundled examples:
|
|||
- `opencode` and `opencode-go`: plugin-owned capability metadata plus
|
||||
proxy-Gemini thought-signature sanitation
|
||||
- `byteplus`, `cloudflare-ai-gateway`, `huggingface`, `kimi`,
|
||||
`modelstudio`, `nvidia`, `qianfan`, `stepfun`, `synthetic`, `together`, `venice`,
|
||||
`qwen`, `nvidia`, `qianfan`, `stepfun`, `synthetic`, `together`, `venice`,
|
||||
`vercel-ai-gateway`, and `volcengine`: plugin-owned catalogs only
|
||||
- `minimax`: plugin-owned catalogs, hybrid Anthropic/OpenAI replay-policy
|
||||
selection, and usage auth/snapshot logic
|
||||
|
|
@ -251,7 +251,7 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
|
|||
|
||||
### Other subscription-style hosted options
|
||||
|
||||
- [Qwen / Model Studio](/providers/qwen_modelstudio): Alibaba Cloud Standard pay-as-you-go and Coding Plan subscription endpoints
|
||||
- [Qwen Cloud](/providers/qwen): Qwen Cloud provider surface plus Alibaba DashScope and Coding Plan endpoint mapping
|
||||
- [MiniMax](/providers/minimax): MiniMax Coding Plan OAuth or API key access
|
||||
- [GLM Models](/providers/glm): Z.AI Coding Plan or general API endpoints
|
||||
|
||||
|
|
@ -360,8 +360,8 @@ See [/providers/kilocode](/providers/kilocode) for setup details.
|
|||
- Example model: `kimi/kimi-code`
|
||||
- Qianfan: `qianfan` (`QIANFAN_API_KEY`)
|
||||
- Example model: `qianfan/deepseek-v3.2`
|
||||
- Model Studio: `modelstudio` (`MODELSTUDIO_API_KEY`)
|
||||
- Example model: `modelstudio/qwen3.5-plus`
|
||||
- Qwen Cloud: `qwen` (`QWEN_API_KEY`, `MODELSTUDIO_API_KEY`, or `DASHSCOPE_API_KEY`)
|
||||
- Example model: `qwen/qwen3.5-plus`
|
||||
- NVIDIA: `nvidia` (`NVIDIA_API_KEY`)
|
||||
- Example model: `nvidia/nvidia/llama-3.1-nemotron-70b-instruct`
|
||||
- StepFun: `stepfun` / `stepfun-plan` (`STEPFUN_API_KEY`)
|
||||
|
|
|
|||
|
|
@ -75,8 +75,8 @@ Usage** (pay-as-you-go billed separately from the subscription) for that
|
|||
traffic.
|
||||
|
||||
If you want other subscription-style options in OpenClaw, see [OpenAI
|
||||
Codex](/providers/openai), [Alibaba Cloud Model Studio Coding
|
||||
Plan](/providers/qwen_modelstudio), [MiniMax Coding Plan](/providers/minimax),
|
||||
Codex](/providers/openai), [Qwen Cloud Coding
|
||||
Plan](/providers/qwen), [MiniMax Coding Plan](/providers/minimax),
|
||||
and [Z.AI / GLM Coding Plan](/providers/glm).
|
||||
</Warning>
|
||||
|
||||
|
|
|
|||
|
|
@ -54,7 +54,7 @@
|
|||
"redirects": [
|
||||
{
|
||||
"source": "/providers/modelstudio",
|
||||
"destination": "/providers/qwen_modelstudio"
|
||||
"destination": "/providers/qwen"
|
||||
},
|
||||
{
|
||||
"source": "/platforms/oracle",
|
||||
|
|
|
|||
|
|
@ -576,7 +576,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
|
|||
**Z.AI / GLM Coding Plan**.
|
||||
|
||||
Docs: [Anthropic](/providers/anthropic), [OpenAI](/providers/openai),
|
||||
[Qwen / Model Studio](/providers/qwen_modelstudio),
|
||||
[Qwen Cloud](/providers/qwen),
|
||||
[MiniMax](/providers/minimax), [GLM Models](/providers/glm),
|
||||
[Local models](/gateway/local-models), [Models](/concepts/models).
|
||||
|
||||
|
|
@ -607,7 +607,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
|
|||
For production or multi-user workloads, Anthropic API key auth is the
|
||||
safer, recommended choice. If you want other subscription-style hosted
|
||||
options in OpenClaw, see [OpenAI](/providers/openai), [Qwen / Model
|
||||
Studio](/providers/qwen_modelstudio), [MiniMax](/providers/minimax), and
|
||||
Cloud](/providers/qwen), [MiniMax](/providers/minimax), and
|
||||
[GLM Models](/providers/glm).
|
||||
|
||||
</Accordion>
|
||||
|
|
|
|||
|
|
@ -817,7 +817,7 @@ api.registerProvider({
|
|||
- Mistral, OpenCode Zen, and OpenCode Go use `capabilities` only to keep
|
||||
transcript/tooling quirks out of core.
|
||||
- Catalog-only bundled providers such as `byteplus`, `cloudflare-ai-gateway`,
|
||||
`huggingface`, `kimi-coding`, `modelstudio`, `nvidia`, `qianfan`,
|
||||
`huggingface`, `kimi-coding`, `qwen`, `nvidia`, `qianfan`,
|
||||
`synthetic`, `together`, `venice`, `vercel-ai-gateway`, and `volcengine` use
|
||||
`catalog` only.
|
||||
- MiniMax and Xiaomi use `catalog` plus usage hooks because their `/usage`
|
||||
|
|
@ -1535,7 +1535,7 @@ api.registerVideoGenerationProvider({
|
|||
});
|
||||
|
||||
// shared runtime helper for feature/channel plugins
|
||||
const clip = await api.runtime.videoGeneration.generateFile({
|
||||
const clip = await api.runtime.videoGeneration.generate({
|
||||
prompt: "Show the robot walking through the lab.",
|
||||
cfg,
|
||||
});
|
||||
|
|
|
|||
|
|
@ -23,7 +23,7 @@ can still run in OpenClaw, but Anthropic now requires **Extra Usage**
|
|||
If you want a clearer billing path, use an Anthropic API key instead. OpenClaw
|
||||
also supports other subscription-style options, including [OpenAI
|
||||
Codex](/providers/openai), [Alibaba Cloud Model Studio Coding
|
||||
Plan](/providers/qwen_modelstudio), [MiniMax Coding Plan](/providers/minimax),
|
||||
Plan](/providers/qwen), [MiniMax Coding Plan](/providers/minimax),
|
||||
and [Z.AI / GLM Coding Plan](/providers/glm).
|
||||
</Warning>
|
||||
|
||||
|
|
|
|||
|
|
@ -50,8 +50,8 @@ Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugi
|
|||
- [OpenRouter](/providers/openrouter)
|
||||
- [Perplexity (web search)](/providers/perplexity-provider)
|
||||
- [Qianfan](/providers/qianfan)
|
||||
- [Qwen](/providers/qwen)
|
||||
- [Qwen / Model Studio (Alibaba Cloud)](/providers/qwen_modelstudio)
|
||||
- [Qwen Cloud](/providers/qwen)
|
||||
- [Qwen / Model Studio (endpoint detail)](/providers/qwen_modelstudio)
|
||||
- [SGLang (local models)](/providers/sglang)
|
||||
- [StepFun](/providers/stepfun)
|
||||
- [Synthetic](/providers/synthetic)
|
||||
|
|
|
|||
|
|
@ -1,9 +1,10 @@
|
|||
---
|
||||
summary: "Use Qwen models via Alibaba Cloud Model Studio"
|
||||
summary: "Use Qwen Cloud via OpenClaw's bundled qwen provider"
|
||||
read_when:
|
||||
- You want to use Qwen with OpenClaw
|
||||
- You previously used Qwen OAuth
|
||||
title: "Qwen"
|
||||
|
||||
- You want to use Qwen with OpenClaw
|
||||
- You previously used Qwen OAuth
|
||||
title: "Qwen"
|
||||
|
||||
---
|
||||
|
||||
# Qwen
|
||||
|
|
@ -17,27 +18,87 @@ background.
|
|||
|
||||
</Warning>
|
||||
|
||||
## Recommended: Model Studio (Alibaba Cloud)
|
||||
## Recommended: Qwen Cloud
|
||||
|
||||
Use [Model Studio](/providers/qwen_modelstudio) for officially supported access to
|
||||
Qwen models (Qwen 3.6 Plus, Qwen 3.5 Plus, GLM-5, Kimi K2.5, and more).
|
||||
OpenClaw now treats Qwen as a first-class bundled provider with canonical id
|
||||
`qwen`. The bundled provider targets the Qwen Cloud / Alibaba DashScope and
|
||||
Coding Plan endpoints and keeps legacy `modelstudio` ids working as a
|
||||
compatibility alias.
|
||||
|
||||
If you want `qwen3.6-plus` directly from Alibaba Cloud, prefer the **Standard
|
||||
(pay-as-you-go)** Model Studio endpoint. Coding Plan support can lag behind the
|
||||
public Model Studio catalog.
|
||||
- Provider: `qwen`
|
||||
- Preferred env var: `QWEN_API_KEY`
|
||||
- Also accepted for compatibility: `MODELSTUDIO_API_KEY`, `DASHSCOPE_API_KEY`
|
||||
- API style: OpenAI-compatible
|
||||
|
||||
If you want `qwen3.6-plus`, prefer the **Standard (pay-as-you-go)** endpoint.
|
||||
Coding Plan support can lag behind the public catalog.
|
||||
|
||||
```bash
|
||||
# Global Coding Plan endpoint
|
||||
openclaw onboard --auth-choice modelstudio-api-key
|
||||
openclaw onboard --auth-choice qwen-api-key
|
||||
|
||||
# China Coding Plan endpoint
|
||||
openclaw onboard --auth-choice modelstudio-api-key-cn
|
||||
openclaw onboard --auth-choice qwen-api-key-cn
|
||||
|
||||
# Global Standard (pay-as-you-go) endpoint
|
||||
openclaw onboard --auth-choice modelstudio-standard-api-key
|
||||
openclaw onboard --auth-choice qwen-standard-api-key
|
||||
|
||||
# China Standard (pay-as-you-go) endpoint
|
||||
openclaw onboard --auth-choice modelstudio-standard-api-key-cn
|
||||
openclaw onboard --auth-choice qwen-standard-api-key-cn
|
||||
```
|
||||
|
||||
See [Model Studio](/providers/qwen_modelstudio) for full setup details.
|
||||
Legacy `modelstudio-*` auth-choice ids and `modelstudio/...` model refs still
|
||||
work.
|
||||
|
||||
After onboarding, set a default model:
|
||||
|
||||
```json5
|
||||
{
|
||||
agents: {
|
||||
defaults: {
|
||||
model: { primary: "qwen/qwen3.5-plus" },
|
||||
},
|
||||
},
|
||||
}
|
||||
```
|
||||
|
||||
## Capability plan
|
||||
|
||||
The `qwen` extension is being positioned as the vendor home for the full Qwen
|
||||
Cloud surface, not just coding/text models.
|
||||
|
||||
- Text/chat models: bundled now
|
||||
- Tool calling, structured output, thinking: inherited from the OpenAI-compatible transport
|
||||
- Image generation: planned at the provider-plugin layer
|
||||
- Image/video understanding: bundled now on the Standard endpoint
|
||||
- Speech/audio: planned at the provider-plugin layer
|
||||
- Memory embeddings/reranking: planned through the embedding adapter surface
|
||||
- Video generation: bundled now through the shared video-generation capability
|
||||
|
||||
## Multimodal add-ons
|
||||
|
||||
The `qwen` extension now also exposes:
|
||||
|
||||
- Video understanding via `qwen-vl-max-latest`
|
||||
- Wan video generation via models such as `wan2.6-t2v`, `wan2.6-i2v`, and `wan2.6-r2v`
|
||||
|
||||
These multimodal surfaces use the **Standard** DashScope endpoints, not the
|
||||
Coding Plan endpoints.
|
||||
|
||||
- Global/Intl Standard base URL: `https://dashscope-intl.aliyuncs.com/compatible-mode/v1`
|
||||
- China Standard base URL: `https://dashscope.aliyuncs.com/compatible-mode/v1`
|
||||
|
||||
For video generation, set a default model explicitly:
|
||||
|
||||
```json5
|
||||
{
|
||||
agents: {
|
||||
defaults: {
|
||||
videoGenerationModel: { primary: "qwen/wan2.6-t2v" },
|
||||
},
|
||||
},
|
||||
}
|
||||
```
|
||||
|
||||
See [Qwen / Model Studio](/providers/qwen_modelstudio) for endpoint-level detail
|
||||
and compatibility notes.
|
||||
|
|
|
|||
|
|
@ -1,17 +1,19 @@
|
|||
---
|
||||
title: "Qwen / Model Studio"
|
||||
summary: "Alibaba Cloud Model Studio setup (Standard pay-as-you-go and Coding Plan, dual region endpoints)"
|
||||
summary: "Endpoint detail for the bundled qwen provider and its legacy modelstudio compatibility surface"
|
||||
read_when:
|
||||
- You want to use Qwen (Alibaba Cloud Model Studio) with OpenClaw
|
||||
- You need the API key env var for Model Studio
|
||||
- You want to use the Standard (pay-as-you-go) or Coding Plan endpoint
|
||||
|
||||
- You want endpoint-level detail for Qwen Cloud / Alibaba DashScope
|
||||
- You need the env var compatibility story for the qwen provider
|
||||
- You want to use the Standard (pay-as-you-go) or Coding Plan endpoint
|
||||
|
||||
---
|
||||
|
||||
# Qwen / Model Studio (Alibaba Cloud)
|
||||
|
||||
The Model Studio provider gives access to Alibaba Cloud models including Qwen
|
||||
and third-party models hosted on the platform. Two billing plans are supported:
|
||||
**Standard** (pay-as-you-go) and **Coding Plan** (subscription).
|
||||
This page documents the endpoint mapping behind OpenClaw's bundled `qwen`
|
||||
provider. The provider keeps `modelstudio` provider ids, auth-choice ids, and
|
||||
model refs working as compatibility aliases while `qwen` becomes the canonical
|
||||
surface.
|
||||
|
||||
<Info>
|
||||
|
||||
|
|
@ -22,8 +24,9 @@ model list.
|
|||
|
||||
</Info>
|
||||
|
||||
- Provider: `modelstudio`
|
||||
- Auth: `MODELSTUDIO_API_KEY`
|
||||
- Provider: `qwen` (legacy alias: `modelstudio`)
|
||||
- Auth: `QWEN_API_KEY`
|
||||
- Also accepted: `MODELSTUDIO_API_KEY`, `DASHSCOPE_API_KEY`
|
||||
- API: OpenAI-compatible
|
||||
|
||||
## Quick start
|
||||
|
|
@ -32,29 +35,31 @@ model list.
|
|||
|
||||
```bash
|
||||
# China endpoint
|
||||
openclaw onboard --auth-choice modelstudio-standard-api-key-cn
|
||||
openclaw onboard --auth-choice qwen-standard-api-key-cn
|
||||
|
||||
# Global/Intl endpoint
|
||||
openclaw onboard --auth-choice modelstudio-standard-api-key
|
||||
openclaw onboard --auth-choice qwen-standard-api-key
|
||||
```
|
||||
|
||||
### Coding Plan (subscription)
|
||||
|
||||
```bash
|
||||
# China endpoint
|
||||
openclaw onboard --auth-choice modelstudio-api-key-cn
|
||||
openclaw onboard --auth-choice qwen-api-key-cn
|
||||
|
||||
# Global/Intl endpoint
|
||||
openclaw onboard --auth-choice modelstudio-api-key
|
||||
openclaw onboard --auth-choice qwen-api-key
|
||||
```
|
||||
|
||||
Legacy `modelstudio-*` auth-choice ids still work.
|
||||
|
||||
After onboarding, set a default model:
|
||||
|
||||
```json5
|
||||
{
|
||||
agents: {
|
||||
defaults: {
|
||||
model: { primary: "modelstudio/qwen3.5-plus" },
|
||||
model: { primary: "qwen/qwen3.5-plus" },
|
||||
},
|
||||
},
|
||||
}
|
||||
|
|
@ -62,12 +67,12 @@ After onboarding, set a default model:
|
|||
|
||||
## Plan types and endpoints
|
||||
|
||||
| Plan | Region | Auth choice | Endpoint |
|
||||
| -------------------------- | ------ | --------------------------------- | ------------------------------------------------ |
|
||||
| Standard (pay-as-you-go) | China | `modelstudio-standard-api-key-cn` | `dashscope.aliyuncs.com/compatible-mode/v1` |
|
||||
| Standard (pay-as-you-go) | Global | `modelstudio-standard-api-key` | `dashscope-intl.aliyuncs.com/compatible-mode/v1` |
|
||||
| Coding Plan (subscription) | China | `modelstudio-api-key-cn` | `coding.dashscope.aliyuncs.com/v1` |
|
||||
| Coding Plan (subscription) | Global | `modelstudio-api-key` | `coding-intl.dashscope.aliyuncs.com/v1` |
|
||||
| Plan | Region | Auth choice | Endpoint |
|
||||
| -------------------------- | ------ | -------------------------- | ------------------------------------------------ |
|
||||
| Standard (pay-as-you-go) | China | `qwen-standard-api-key-cn` | `dashscope.aliyuncs.com/compatible-mode/v1` |
|
||||
| Standard (pay-as-you-go) | Global | `qwen-standard-api-key` | `dashscope-intl.aliyuncs.com/compatible-mode/v1` |
|
||||
| Coding Plan (subscription) | China | `qwen-api-key-cn` | `coding.dashscope.aliyuncs.com/v1` |
|
||||
| Coding Plan (subscription) | Global | `qwen-api-key` | `coding-intl.dashscope.aliyuncs.com/v1` |
|
||||
|
||||
The provider auto-selects the endpoint based on your auth choice. You can
|
||||
override with a custom `baseUrl` in config.
|
||||
|
|
@ -76,28 +81,28 @@ Native Model Studio endpoints advertise streaming usage compatibility on the
|
|||
shared `openai-completions` transport. OpenClaw keys that off endpoint
|
||||
capabilities now, so DashScope-compatible custom provider ids targeting the
|
||||
same native hosts inherit the same streaming-usage behavior instead of
|
||||
requiring the built-in `modelstudio` provider id specifically.
|
||||
requiring the built-in `qwen` provider id specifically.
|
||||
|
||||
## Get your API key
|
||||
|
||||
- **China**: [bailian.console.aliyun.com](https://bailian.console.aliyun.com/)
|
||||
- **Global/Intl**: [modelstudio.console.alibabacloud.com](https://modelstudio.console.alibabacloud.com/)
|
||||
- **Manage keys**: [home.qwencloud.com/api-keys](https://home.qwencloud.com/api-keys)
|
||||
- **Docs**: [docs.qwencloud.com](https://docs.qwencloud.com/developer-guides/getting-started/introduction)
|
||||
|
||||
## Built-in catalog
|
||||
|
||||
OpenClaw currently ships this bundled Model Studio catalog:
|
||||
OpenClaw currently ships this bundled Qwen catalog:
|
||||
|
||||
| Model ref | Input | Context | Notes |
|
||||
| ---------------------------------- | ----------- | --------- | -------------------------------------------------- |
|
||||
| `modelstudio/qwen3.5-plus` | text, image | 1,000,000 | Default model |
|
||||
| `modelstudio/qwen3.6-plus` | text, image | 1,000,000 | Prefer Standard endpoints when you need this model |
|
||||
| `modelstudio/qwen3-max-2026-01-23` | text | 262,144 | Qwen Max line |
|
||||
| `modelstudio/qwen3-coder-next` | text | 262,144 | Coding |
|
||||
| `modelstudio/qwen3-coder-plus` | text | 1,000,000 | Coding |
|
||||
| `modelstudio/MiniMax-M2.5` | text | 1,000,000 | Reasoning enabled |
|
||||
| `modelstudio/glm-5` | text | 202,752 | GLM |
|
||||
| `modelstudio/glm-4.7` | text | 202,752 | GLM |
|
||||
| `modelstudio/kimi-k2.5` | text, image | 262,144 | Moonshot AI via Alibaba |
|
||||
| Model ref | Input | Context | Notes |
|
||||
| --------------------------- | ----------- | --------- | -------------------------------------------------- |
|
||||
| `qwen/qwen3.5-plus` | text, image | 1,000,000 | Default model |
|
||||
| `qwen/qwen3.6-plus` | text, image | 1,000,000 | Prefer Standard endpoints when you need this model |
|
||||
| `qwen/qwen3-max-2026-01-23` | text | 262,144 | Qwen Max line |
|
||||
| `qwen/qwen3-coder-next` | text | 262,144 | Coding |
|
||||
| `qwen/qwen3-coder-plus` | text | 1,000,000 | Coding |
|
||||
| `qwen/MiniMax-M2.5` | text | 1,000,000 | Reasoning enabled |
|
||||
| `qwen/glm-5` | text | 202,752 | GLM |
|
||||
| `qwen/glm-4.7` | text | 202,752 | GLM |
|
||||
| `qwen/kimi-k2.5` | text, image | 262,144 | Moonshot AI via Alibaba |
|
||||
|
||||
Availability can still vary by endpoint and billing plan even when a model is
|
||||
present in the bundled catalog.
|
||||
|
|
@ -125,5 +130,5 @@ endpoint/key pair.
|
|||
## Environment note
|
||||
|
||||
If the Gateway runs as a daemon (launchd/systemd), make sure
|
||||
`MODELSTUDIO_API_KEY` is available to that process (for example, in
|
||||
`QWEN_API_KEY` is available to that process (for example, in
|
||||
`~/.openclaw/.env` or via `env.shellEnv`).
|
||||
|
|
|
|||
|
|
@ -93,7 +93,7 @@ and the [Plugin SDK Overview](/plugins/sdk-overview).
|
|||
<AccordionGroup>
|
||||
<Accordion title="Model providers (enabled by default)">
|
||||
`anthropic`, `byteplus`, `cloudflare-ai-gateway`, `github-copilot`, `google`,
|
||||
`huggingface`, `kilocode`, `kimi-coding`, `minimax`, `mistral`, `modelstudio`,
|
||||
`huggingface`, `kilocode`, `kimi-coding`, `minimax`, `mistral`, `qwen`,
|
||||
`moonshot`, `nvidia`, `openai`, `opencode`, `opencode-go`, `openrouter`,
|
||||
`qianfan`, `synthetic`, `together`, `venice`,
|
||||
`vercel-ai-gateway`, `volcengine`, `xiaomi`, `zai`
|
||||
|
|
|
|||
Loading…
Reference in New Issue