fix(models): default MiniMax to /anthropic
This commit is contained in:
@@ -112,8 +112,8 @@ OpenAI/Anthropic‑compatible proxies.
|
||||
|
||||
MiniMax is configured via `models.providers` because it uses custom endpoints:
|
||||
|
||||
- MiniMax Cloud (OpenAI‑compatible): `--auth-choice minimax-cloud`
|
||||
- MiniMax API (Anthropic‑compatible): `--auth-choice minimax-api`
|
||||
- MiniMax (Anthropic‑compatible): `--auth-choice minimax-cloud`
|
||||
- `--auth-choice minimax-api` is a legacy alias.
|
||||
- Auth: `MINIMAX_API_KEY`
|
||||
|
||||
See [/providers/minimax](/providers/minimax) for setup details, model options, and config snippets.
|
||||
|
||||
@@ -1830,7 +1830,7 @@ Use MiniMax's Anthropic-compatible API directly without LM Studio:
|
||||
```
|
||||
|
||||
Notes:
|
||||
- Set `MINIMAX_API_KEY` environment variable or use `clawdbot onboard --auth-choice minimax-api`
|
||||
- Set `MINIMAX_API_KEY` environment variable or use `clawdbot onboard --auth-choice minimax-cloud`
|
||||
- Available models: `MiniMax-M2.1` (default), `MiniMax-M2.1-lightning` (~100 tps), `MiniMax-M2` (reasoning)
|
||||
- Pricing is a placeholder; MiniMax doesn't publish public rates. Override in `models.json` for accurate cost tracking.
|
||||
|
||||
|
||||
@@ -27,52 +27,15 @@ MiniMax highlights these improvements in M2.1:
|
||||
|
||||
## Choose a setup
|
||||
|
||||
### Option A: MiniMax Cloud (OpenAI-compatible `/v1`)
|
||||
### Option A: MiniMax (Anthropic-compatible `/anthropic`) — recommended
|
||||
|
||||
**Best for:** hosted MiniMax with OpenAI-compatible API.
|
||||
**Best for:** hosted MiniMax with Anthropic-compatible API.
|
||||
|
||||
Configure via CLI:
|
||||
- Run `clawdbot configure`
|
||||
- Select **Model/auth**
|
||||
- Choose **MiniMax M2.1 (minimax.io)**
|
||||
|
||||
```json5
|
||||
{
|
||||
env: { MINIMAX_API_KEY: "sk-..." },
|
||||
agents: { defaults: { model: { primary: "minimax/MiniMax-M2.1" } } },
|
||||
models: {
|
||||
mode: "merge",
|
||||
providers: {
|
||||
minimax: {
|
||||
baseUrl: "https://api.minimax.io/v1",
|
||||
apiKey: "${MINIMAX_API_KEY}",
|
||||
api: "openai-completions",
|
||||
models: [
|
||||
{
|
||||
id: "MiniMax-M2.1",
|
||||
name: "MiniMax M2.1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
||||
contextWindow: 200000,
|
||||
maxTokens: 8192
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Option B: MiniMax API (Anthropic-compatible `/anthropic`)
|
||||
|
||||
**Best for:** MiniMax's Anthropic-compatible API (platform.minimax.io).
|
||||
|
||||
Configure via CLI:
|
||||
- Run `clawdbot configure`
|
||||
- Select **Model/auth**
|
||||
- Choose **MiniMax API (platform.minimax.io)**
|
||||
|
||||
```json5
|
||||
{
|
||||
env: { MINIMAX_API_KEY: "sk-..." },
|
||||
@@ -93,22 +56,36 @@ Configure via CLI:
|
||||
cost: { input: 15, output: 60, cacheRead: 2, cacheWrite: 10 },
|
||||
contextWindow: 200000,
|
||||
maxTokens: 8192
|
||||
},
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Option B: MiniMax OpenAI-compatible `/v1` (manual)
|
||||
|
||||
**Best for:** setups that require OpenAI-compatible payloads.
|
||||
|
||||
```json5
|
||||
{
|
||||
env: { MINIMAX_API_KEY: "sk-..." },
|
||||
agents: { defaults: { model: { primary: "minimax/MiniMax-M2.1" } } },
|
||||
models: {
|
||||
mode: "merge",
|
||||
providers: {
|
||||
minimax: {
|
||||
baseUrl: "https://api.minimax.io/v1",
|
||||
apiKey: "${MINIMAX_API_KEY}",
|
||||
api: "openai-completions",
|
||||
models: [
|
||||
{
|
||||
id: "MiniMax-M2.1-lightning",
|
||||
name: "MiniMax M2.1 Lightning",
|
||||
id: "MiniMax-M2.1",
|
||||
name: "MiniMax M2.1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: { input: 15, output: 60, cacheRead: 2, cacheWrite: 10 },
|
||||
contextWindow: 200000,
|
||||
maxTokens: 8192
|
||||
},
|
||||
{
|
||||
id: "MiniMax-M2",
|
||||
name: "MiniMax M2",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: { input: 15, output: 60, cacheRead: 2, cacheWrite: 10 },
|
||||
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
||||
contextWindow: 200000,
|
||||
maxTokens: 8192
|
||||
}
|
||||
|
||||
@@ -80,8 +80,7 @@ Tip: `--json` does **not** imply non-interactive mode. Use `--non-interactive` (
|
||||
- **OpenAI API key**: uses `OPENAI_API_KEY` if present or prompts for a key, then saves it to `~/.clawdbot/.env` so launchd can read it.
|
||||
- **OpenCode Zen (multi-model proxy)**: prompts for `OPENCODE_API_KEY` (or `OPENCODE_ZEN_API_KEY`, get it at https://opencode.ai/auth).
|
||||
- **API key**: stores the key for you.
|
||||
- **MiniMax M2.1 (minimax.io)**: config is auto‑written for the OpenAI-compatible `/v1` endpoint.
|
||||
- **MiniMax API (platform.minimax.io)**: config is auto‑written for the Anthropic-compatible `/anthropic` endpoint.
|
||||
- **MiniMax M2.1 (minimax.io)**: config is auto‑written for the Anthropic-compatible `/anthropic` endpoint.
|
||||
- **MiniMax M2.1 (LM Studio)**: config is auto‑written for the LM Studio endpoint.
|
||||
- More detail: [MiniMax](/providers/minimax)
|
||||
- **Skip**: no auth configured yet.
|
||||
|
||||
Reference in New Issue
Block a user