@@ -33,7 +33,9 @@ models including Llama, DeepSeek, Kimi, and more through a unified API.
3333{
3434 agents: {
3535 defaults: {
36- model: { primary: "together/moonshotai/Kimi-K2.5" },
36+ model: {
37+ primary: "together/meta-llama/Llama-3.3-70B-Instruct-Turbo",
38+ },
3739 },
3840 },
3941}
@@ -51,35 +53,32 @@ openclaw onboard --non-interactive \
5153```
52545355<Note>
54-The onboarding preset sets `together/moonshotai/Kimi-K2.5` as the default
55-model.
56+The onboarding preset sets
57+`together/meta-llama/Llama-3.3-70B-Instruct-Turbo` as the default model.
5658</Note>
57595860## Built-in catalog
59616062OpenClaw ships this bundled Together catalog:
616362-| Model ref | Name | Input | Context | Notes |
63-| ------------------------------------------------------------ | -------------------------------------- | ----------- | ---------- | -------------------------------- |
64-| `together/moonshotai/Kimi-K2.5` | Kimi K2.5 | text, image | 262,144 | Default model; reasoning enabled |
65-| `together/zai-org/GLM-4.7` | GLM 4.7 Fp8 | text | 202,752 | General-purpose text model |
66-| `together/meta-llama/Llama-3.3-70B-Instruct-Turbo` | Llama 3.3 70B Instruct Turbo | text | 131,072 | Fast instruction model |
67-| `together/meta-llama/Llama-4-Scout-17B-16E-Instruct` | Llama 4 Scout 17B 16E Instruct | text, image | 10,000,000 | Multimodal |
68-| `together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | Llama 4 Maverick 17B 128E Instruct FP8 | text, image | 20,000,000 | Multimodal |
69-| `together/deepseek-ai/DeepSeek-V3.1` | DeepSeek V3.1 | text | 131,072 | General text model |
70-| `together/deepseek-ai/DeepSeek-R1` | DeepSeek R1 | text | 131,072 | Reasoning model |
71-| `together/moonshotai/Kimi-K2-Instruct-0905` | Kimi K2-Instruct 0905 | text | 262,144 | Secondary Kimi text model |
64+| Model ref | Name | Input | Context | Notes |
65+| -------------------------------------------------- | ---------------------------- | ----------- | ------- | -------------------- |
66+| `together/meta-llama/Llama-3.3-70B-Instruct-Turbo` | Llama 3.3 70B Instruct Turbo | text | 131,072 | Default model |
67+| `together/moonshotai/Kimi-K2.6` | Kimi K2.6 FP4 | text, image | 262,144 | Kimi reasoning model |
68+| `together/deepseek-ai/DeepSeek-V4-Pro` | DeepSeek V4 Pro | text | 512,000 | Reasoning text model |
69+| `together/Qwen/Qwen2.5-7B-Instruct-Turbo` | Qwen2.5 7B Instruct Turbo | text | 32,768 | Fast text model |
70+| `together/zai-org/GLM-5.1` | GLM 5.1 FP4 | text | 202,752 | Reasoning text model |
72717372## Video generation
74737574The bundled `together` plugin also registers video generation through the
7675shared `video_generate` tool.
777678-| Property | Value |
79-| -------------------- | ------------------------------------- |
80-| Default video model | `together/Wan-AI/Wan2.2-T2V-A14B` |
81-| Modes | text-to-video, single-image reference |
82-| Supported parameters | `aspectRatio`, `resolution` |
77+| Property | Value |
78+| -------------------- | ------------------------------------------------------------------------ |
79+| Default video model | `together/Wan-AI/Wan2.2-T2V-A14B` |
80+| Modes | text-to-video; single-image reference only with `Wan-AI/Wan2.2-I2V-A14B` |
81+| Supported parameters | `aspectRatio`, `resolution` |
83828483To use Together as the default video provider:
8584此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。