diff --git a/docs/providers/huggingface.md b/docs/providers/huggingface.md index 7b33955f524..13a6c883bf6 100644 --- a/docs/providers/huggingface.md +++ b/docs/providers/huggingface.md @@ -84,12 +84,11 @@ When you configure a Hugging Face API key (via onboarding, `HUGGINGFACE_HUB_TOKE } ``` -- **Provider / policy selection:** Append a suffix to the **model id** to choose how the router picks the backend: - - **`:fastest`** — highest throughput (router picks; provider choice is **locked** — no interactive backend picker). - - **`:cheapest`** — lowest cost per output token (router picks; provider choice is **locked**). - - **`:provider`** — force a specific backend (e.g. `:sambanova`, `:together`). +- **Policy suffixes:** OpenClaw's bundled Hugging Face docs and helpers currently treat these two suffixes as the built-in policy variants: + - **`:fastest`** — highest throughput. + - **`:cheapest`** — lowest cost per output token. - When you select **:cheapest** or **:fastest** (e.g. in the onboarding model dropdown), the provider is locked: the router decides by cost or speed and no optional “prefer specific backend” step is shown. You can add these as separate entries in `models.providers.huggingface.models` or set `model.primary` with the suffix. You can also set your default order in [Inference Provider settings](https://hf.co/settings/inference-providers) (no suffix = use that order). + You can add these as separate entries in `models.providers.huggingface.models` or set `model.primary` with the suffix. You can also set your default provider order in [Inference Provider settings](https://hf.co/settings/inference-providers) (no suffix = use that order). - **Config merge:** Existing entries in `models.providers.huggingface.models` (e.g. in `models.json`) are kept when config is merged. So any custom `name`, `alias`, or model options you set there are preserved. @@ -112,7 +111,7 @@ Model refs use the form `huggingface//` (Hub-style IDs). The list be | GLM 4.7 | `zai-org/GLM-4.7` | | Kimi K2.5 | `moonshotai/Kimi-K2.5` | -You can append `:fastest`, `:cheapest`, or `:provider` (e.g. `:together`, `:sambanova`) to the model id. Set your default order in [Inference Provider settings](https://hf.co/settings/inference-providers); see [Inference Providers](https://huggingface.co/docs/inference-providers) and **GET** `https://router.huggingface.co/v1/models` for the full list. +You can append `:fastest` or `:cheapest` to the model id. Set your default order in [Inference Provider settings](https://hf.co/settings/inference-providers); see [Inference Providers](https://huggingface.co/docs/inference-providers) and **GET** `https://router.huggingface.co/v1/models` for the full list. ### Complete configuration examples @@ -175,21 +174,6 @@ You can append `:fastest`, `:cheapest`, or `:provider` (e.g. `:together`, `:samb } ``` -**Force a specific backend with :provider:** - -```json5 -{ - agents: { - defaults: { - model: { primary: "huggingface/deepseek-ai/DeepSeek-R1:together" }, - models: { - "huggingface/deepseek-ai/DeepSeek-R1:together": { alias: "DeepSeek R1 (Together)" }, - }, - }, - }, -} -``` - **Multiple Qwen and DeepSeek models with policy suffixes:** ```json5 diff --git a/docs/providers/together.md b/docs/providers/together.md index c416755e9c1..edc9676318b 100644 --- a/docs/providers/together.md +++ b/docs/providers/together.md @@ -13,6 +13,7 @@ The [Together AI](https://together.ai) provides access to leading open-source mo - Provider: `together` - Auth: `TOGETHER_API_KEY` - API: OpenAI-compatible +- Base URL: `https://api.together.xyz/v1` ## Quick start @@ -51,16 +52,19 @@ If the Gateway runs as a daemon (launchd/systemd), make sure `TOGETHER_API_KEY` is available to that process (for example, in `~/.openclaw/.env` or via `env.shellEnv`). -## Available models +## Built-in catalog -Together AI provides access to many popular open-source models: +OpenClaw currently ships this bundled Together catalog: -- **GLM 4.7 Fp8** - Default model with 200K context window -- **Llama 3.3 70B Instruct Turbo** - Fast, efficient instruction following -- **Llama 4 Scout** - Vision model with image understanding -- **Llama 4 Maverick** - Advanced vision and reasoning -- **DeepSeek V3.1** - Powerful coding and reasoning model -- **DeepSeek R1** - Advanced reasoning model -- **Kimi K2 Instruct** - High-performance model with 262K context window +| Model ref | Name | Input | Context | Notes | +| ------------------------------------------------------------ | -------------------------------------- | ----------- | ---------- | -------------------------------- | +| `together/moonshotai/Kimi-K2.5` | Kimi K2.5 | text, image | 262,144 | Default model; reasoning enabled | +| `together/zai-org/GLM-4.7` | GLM 4.7 Fp8 | text | 202,752 | General-purpose text model | +| `together/meta-llama/Llama-3.3-70B-Instruct-Turbo` | Llama 3.3 70B Instruct Turbo | text | 131,072 | Fast instruction model | +| `together/meta-llama/Llama-4-Scout-17B-16E-Instruct` | Llama 4 Scout 17B 16E Instruct | text, image | 10,000,000 | Multimodal | +| `together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | Llama 4 Maverick 17B 128E Instruct FP8 | text, image | 20,000,000 | Multimodal | +| `together/deepseek-ai/DeepSeek-V3.1` | DeepSeek V3.1 | text | 131,072 | General text model | +| `together/deepseek-ai/DeepSeek-R1` | DeepSeek R1 | text | 131,072 | Reasoning model | +| `together/moonshotai/Kimi-K2-Instruct-0905` | Kimi K2-Instruct 0905 | text | 262,144 | Secondary Kimi text model | -All models support standard chat completions and are OpenAI API compatible. +The onboarding preset sets `together/moonshotai/Kimi-K2.5` as the default model. diff --git a/docs/providers/volcengine.md b/docs/providers/volcengine.md index 75ad2577dec..f61d2520525 100644 --- a/docs/providers/volcengine.md +++ b/docs/providers/volcengine.md @@ -57,15 +57,30 @@ automatically. ## Available models -- **doubao-seed-1-8** - Doubao Seed 1.8 (general, default) -- **doubao-seed-code-preview** - Doubao coding model -- **ark-code-latest** - Coding plan default -- **Kimi K2.5** - Moonshot AI via Volcano Engine -- **GLM-4.7** - GLM via Volcano Engine -- **DeepSeek V3.2** - DeepSeek via Volcano Engine +General provider (`volcengine`): -Most models support text + image input. Context windows range from 128K to 256K -tokens. +| Model ref | Name | Input | Context | +| -------------------------------------------- | ------------------------------- | ----------- | ------- | +| `volcengine/doubao-seed-1-8-251228` | Doubao Seed 1.8 | text, image | 256,000 | +| `volcengine/doubao-seed-code-preview-251028` | doubao-seed-code-preview-251028 | text, image | 256,000 | +| `volcengine/kimi-k2-5-260127` | Kimi K2.5 | text, image | 256,000 | +| `volcengine/glm-4-7-251222` | GLM 4.7 | text, image | 200,000 | +| `volcengine/deepseek-v3-2-251201` | DeepSeek V3.2 | text, image | 128,000 | + +Coding provider (`volcengine-plan`): + +| Model ref | Name | Input | Context | +| ------------------------------------------------- | ------------------------ | ----- | ------- | +| `volcengine-plan/ark-code-latest` | Ark Coding Plan | text | 256,000 | +| `volcengine-plan/doubao-seed-code` | Doubao Seed Code | text | 256,000 | +| `volcengine-plan/glm-4.7` | GLM 4.7 Coding | text | 200,000 | +| `volcengine-plan/kimi-k2-thinking` | Kimi K2 Thinking | text | 256,000 | +| `volcengine-plan/kimi-k2.5` | Kimi K2.5 Coding | text | 256,000 | +| `volcengine-plan/doubao-seed-code-preview-251028` | Doubao Seed Code Preview | text | 256,000 | + +`openclaw onboard --auth-choice volcengine-api-key` currently sets +`volcengine-plan/ark-code-latest` as the default model while also registering +the general `volcengine` catalog. ## Environment note