Ayuriel/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Docs: switch MiniMax defaults to M2.7

Browse Source
This commit is contained in:
Gustavo Madeira Santana 2026-03-20 00:04:32 -04:00
parent 80110c550f
commit 1ba70c3707
No known key found for this signature in database
6 changed files with 62 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/gateway/configuration-examples.md
View File

@ -566,7 +566,7 @@ terms before depending on subscription auth.
workspace: "~/.openclaw/workspace", workspace: "~/.openclaw/workspace",
model: { model: {
primary: "anthropic/claude-opus-4-6", primary: "anthropic/claude-opus-4-6",
fallbacks: ["minimax/MiniMax-M2.5"], fallbacks: ["minimax/MiniMax-M2.7"],
}, },
}, },
} }

19
docs/gateway/configuration-reference.md
View File

@ -864,11 +864,11 @@ Time format in system prompt. Default: `auto` (OS preference).
defaults: { defaults: {
models: { models: {
"anthropic/claude-opus-4-6": { alias: "opus" }, "anthropic/claude-opus-4-6": { alias: "opus" },
"minimax/MiniMax-M2.5": { alias: "minimax" }, "minimax/MiniMax-M2.7": { alias: "minimax" },
}, },
model: { model: {
primary: "anthropic/claude-opus-4-6", primary: "anthropic/claude-opus-4-6",
fallbacks: ["minimax/MiniMax-M2.5"], fallbacks: ["minimax/MiniMax-M2.7"],
}, },
imageModel: { imageModel: {
primary: "openrouter/qwen/qwen-2.5-vl-72b-instruct:free", primary: "openrouter/qwen/qwen-2.5-vl-72b-instruct:free",
@ -2058,7 +2058,7 @@ Notes:
agents: { agents: {
defaults: { defaults: {
subagents: { subagents: {
model: "minimax/MiniMax-M2.5", model: "minimax/MiniMax-M2.7",
maxConcurrent: 1, maxConcurrent: 1,
runTimeoutSeconds: 900, runTimeoutSeconds: 900,
archiveAfterMinutes: 60, archiveAfterMinutes: 60,
@ -2311,15 +2311,15 @@ Base URL should omit `/v1` (Anthropic client appends it). Shortcut: `openclaw on
</Accordion> </Accordion>
<Accordion title="MiniMax M2.5 (direct)"> <Accordion title="MiniMax M2.7 (direct)">
```json5 ```json5
{ {
agents: { agents: {
defaults: { defaults: {
model: { primary: "minimax/MiniMax-M2.5" }, model: { primary: "minimax/MiniMax-M2.7" },
models: { models: {
"minimax/MiniMax-M2.5": { alias: "Minimax" }, "minimax/MiniMax-M2.7": { alias: "Minimax" },
}, },
}, },
}, },
@ -2332,11 +2332,11 @@ Base URL should omit `/v1` (Anthropic client appends it). Shortcut: `openclaw on
api: "anthropic-messages", api: "anthropic-messages",
models: [ models: [
{ {
id: "MiniMax-M2.5", id: "MiniMax-M2.7",
name: "MiniMax M2.5", name: "MiniMax M2.7",
reasoning: true, reasoning: true,
input: ["text"], input: ["text"],
cost: { input: 15, output: 60, cacheRead: 2, cacheWrite: 10 }, cost: { input: 0.3, output: 1.2, cacheRead: 0.03, cacheWrite: 0.12 },
contextWindow: 200000, contextWindow: 200000,
maxTokens: 8192, maxTokens: 8192,
}, },
@ -2348,6 +2348,7 @@ Base URL should omit `/v1` (Anthropic client appends it). Shortcut: `openclaw on
``` ```
Set `MINIMAX_API_KEY`. Shortcut: `openclaw onboard --auth-choice minimax-api`. Set `MINIMAX_API_KEY`. Shortcut: `openclaw onboard --auth-choice minimax-api`.
`MiniMax-M2.5` and `MiniMax-M2.5-highspeed` remain available if you prefer the older text models.
</Accordion> </Accordion>

11
docs/help/faq.md
View File

@ -2013,7 +2013,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
**For tool-enabled or untrusted-input agents:** prioritize model strength over cost. **For tool-enabled or untrusted-input agents:** prioritize model strength over cost.
**For routine/low-stakes chat:** use cheaper fallback models and route by agent role. **For routine/low-stakes chat:** use cheaper fallback models and route by agent role.
MiniMax M2.5 has its own docs: [MiniMax](/providers/minimax) and MiniMax has its own docs: [MiniMax](/providers/minimax) and
[Local models](/gateway/local-models). [Local models](/gateway/local-models).
Rule of thumb: use the **best model you can afford** for high-stakes work, and a cheaper Rule of thumb: use the **best model you can afford** for high-stakes work, and a cheaper
@ -2146,7 +2146,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
</Accordion> </Accordion>
<Accordion title='Why do I see "Unknown model: minimax/MiniMax-M2.5"?'> <Accordion title='Why do I see "Unknown model: minimax/MiniMax-M2.7"?'>
This means the **provider isn't configured** (no MiniMax provider config or auth This means the **provider isn't configured** (no MiniMax provider config or auth
profile was found), so the model can't be resolved. A fix for this detection is profile was found), so the model can't be resolved. A fix for this detection is
in **2026.1.12** (unreleased at the time of writing). in **2026.1.12** (unreleased at the time of writing).
@ -2156,7 +2156,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
1. Upgrade to **2026.1.12** (or run from source `main`), then restart the gateway. 1. Upgrade to **2026.1.12** (or run from source `main`), then restart the gateway.
2. Make sure MiniMax is configured (wizard or JSON), or that a MiniMax API key 2. Make sure MiniMax is configured (wizard or JSON), or that a MiniMax API key
exists in env/auth profiles so the provider can be injected. exists in env/auth profiles so the provider can be injected.
3. Use the exact model id (case-sensitive): `minimax/MiniMax-M2.5` or 3. Use the exact model id (case-sensitive): `minimax/MiniMax-M2.7`,
`minimax/MiniMax-M2.7-highspeed`, `minimax/MiniMax-M2.5`, or
`minimax/MiniMax-M2.5-highspeed`. `minimax/MiniMax-M2.5-highspeed`.
4. Run: 4. Run:
@ -2181,9 +2182,9 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
env: { MINIMAX_API_KEY: "sk-...", OPENAI_API_KEY: "sk-..." }, env: { MINIMAX_API_KEY: "sk-...", OPENAI_API_KEY: "sk-..." },
agents: { agents: {
defaults: { defaults: {
model: { primary: "minimax/MiniMax-M2.5" }, model: { primary: "minimax/MiniMax-M2.7" },
models: { models: {
"minimax/MiniMax-M2.5": { alias: "minimax" }, "minimax/MiniMax-M2.7": { alias: "minimax" },
"openai/gpt-5.2": { alias: "gpt" }, "openai/gpt-5.2": { alias: "gpt" },
}, },
}, },

77
docs/providers/minimax.md
View File

@ -1,5 +1,5 @@
--- ---
summary: "Use MiniMax M2.5 in OpenClaw" summary: "Use MiniMax models in OpenClaw"
read_when: read_when:
- You want MiniMax models in OpenClaw - You want MiniMax models in OpenClaw
- You need MiniMax setup guidance - You need MiniMax setup guidance
@ -8,30 +8,16 @@ title: "MiniMax"
# MiniMax # MiniMax
MiniMax is an AI company that builds the **M2/M2.5** model family. The current OpenClaw's MiniMax provider defaults to **MiniMax M2.7** and keeps
coding-focused release is **MiniMax M2.5** (December 23, 2025), built for **MiniMax M2.5** in the catalog for compatibility.
real-world complex tasks.
Source: [MiniMax M2.5 release note](https://www.minimax.io/news/minimax-m25) ## Model lineup
## Model overview (M2.5) - `MiniMax-M2.7`: default hosted text model.
- `MiniMax-M2.7-highspeed`: faster M2.7 text tier.
MiniMax highlights these improvements in M2.5: - `MiniMax-M2.5`: previous text model, still available in the MiniMax catalog.
- `MiniMax-M2.5-highspeed`: faster M2.5 text tier.
- Stronger **multi-language coding** (Rust, Java, Go, C++, Kotlin, Objective-C, TS/JS). - `MiniMax-VL-01`: vision model for text + image inputs.
- Better **web/app development** and aesthetic output quality (including native mobile).
- Improved **composite instruction** handling for office-style workflows, building on
interleaved thinking and integrated constraint execution.
- **More concise responses** with lower token usage and faster iteration loops.
- Stronger **tool/agent framework** compatibility and context management (Claude Code,
Droid/Factory AI, Cline, Kilo Code, Roo Code, BlackBox).
- Higher-quality **dialogue and technical writing** outputs.
## MiniMax M2.5 vs MiniMax M2.5 Highspeed
- **Speed:** `MiniMax-M2.5-highspeed` is the official fast tier in MiniMax docs.
- **Cost:** MiniMax pricing lists the same input cost and a higher output cost for highspeed.
- **Current model IDs:** use `MiniMax-M2.5` or `MiniMax-M2.5-highspeed`.
## Choose a setup ## Choose a setup
@ -54,7 +40,7 @@ You will be prompted to select an endpoint:
See [MiniMax plugin README](https://github.com/openclaw/openclaw/tree/main/extensions/minimax) for details. See [MiniMax plugin README](https://github.com/openclaw/openclaw/tree/main/extensions/minimax) for details.
### MiniMax M2.5 (API key) ### MiniMax M2.7 (API key)
**Best for:** hosted MiniMax with Anthropic-compatible API. **Best for:** hosted MiniMax with Anthropic-compatible API.
@ -62,12 +48,12 @@ Configure via CLI:
- Run `openclaw configure` - Run `openclaw configure`
- Select **Model/auth** - Select **Model/auth**
- Choose **MiniMax M2.5** - Choose a **MiniMax** auth option
```json5 ```json5
{ {
env: { MINIMAX_API_KEY: "sk-..." }, env: { MINIMAX_API_KEY: "sk-..." },
agents: { defaults: { model: { primary: "minimax/MiniMax-M2.5" } } }, agents: { defaults: { model: { primary: "minimax/MiniMax-M2.7" } } },
models: { models: {
mode: "merge", mode: "merge",
providers: { providers: {
@ -76,6 +62,24 @@ Configure via CLI:
apiKey: "${MINIMAX_API_KEY}", apiKey: "${MINIMAX_API_KEY}",
api: "anthropic-messages", api: "anthropic-messages",
models: [ models: [
{
id: "MiniMax-M2.7",
name: "MiniMax M2.7",
reasoning: true,
input: ["text"],
cost: { input: 0.3, output: 1.2, cacheRead: 0.03, cacheWrite: 0.12 },
contextWindow: 200000,
maxTokens: 8192,
},
{
id: "MiniMax-M2.7-highspeed",
name: "MiniMax M2.7 Highspeed",
reasoning: true,
input: ["text"],
cost: { input: 0.3, output: 1.2, cacheRead: 0.03, cacheWrite: 0.12 },
contextWindow: 200000,
maxTokens: 8192,
},
{ {
id: "MiniMax-M2.5", id: "MiniMax-M2.5",
name: "MiniMax M2.5", name: "MiniMax M2.5",
@ -101,9 +105,9 @@ Configure via CLI:
} }
``` ```
### MiniMax M2.5 as fallback (example) ### MiniMax M2.7 as fallback (example)
**Best for:** keep your strongest latest-generation model as primary, fail over to MiniMax M2.5. **Best for:** keep your strongest latest-generation model as primary, fail over to MiniMax M2.7.
Example below uses Opus as a concrete primary; swap to your preferred latest-gen primary model. Example below uses Opus as a concrete primary; swap to your preferred latest-gen primary model.
```json5 ```json5
@ -113,11 +117,11 @@ Example below uses Opus as a concrete primary; swap to your preferred latest-gen
defaults: { defaults: {
models: { models: {
"anthropic/claude-opus-4-6": { alias: "primary" }, "anthropic/claude-opus-4-6": { alias: "primary" },
"minimax/MiniMax-M2.5": { alias: "minimax" }, "minimax/MiniMax-M2.7": { alias: "minimax" },
}, },
model: { model: {
primary: "anthropic/claude-opus-4-6", primary: "anthropic/claude-opus-4-6",
fallbacks: ["minimax/MiniMax-M2.5"], fallbacks: ["minimax/MiniMax-M2.7"],
}, },
}, },
}, },
@ -170,7 +174,7 @@ Use the interactive config wizard to set MiniMax without editing JSON:
1. Run `openclaw configure`. 1. Run `openclaw configure`.
2. Select **Model/auth**. 2. Select **Model/auth**.
3. Choose **MiniMax M2.5**. 3. Choose a **MiniMax** auth option.
4. Pick your default model when prompted. 4. Pick your default model when prompted.
## Configuration options ## Configuration options
@ -185,28 +189,31 @@ Use the interactive config wizard to set MiniMax without editing JSON:
## Notes ## Notes
- Model refs are `minimax/<model>`. - Model refs are `minimax/<model>`.
- Recommended model IDs: `MiniMax-M2.5` and `MiniMax-M2.5-highspeed`. - Default text model: `MiniMax-M2.7`.
- Alternate text models: `MiniMax-M2.7-highspeed`, `MiniMax-M2.5`, `MiniMax-M2.5-highspeed`.
- Coding Plan usage API: `https://api.minimaxi.com/v1/api/openplatform/coding_plan/remains` (requires a coding plan key). - Coding Plan usage API: `https://api.minimaxi.com/v1/api/openplatform/coding_plan/remains` (requires a coding plan key).
- Update pricing values in `models.json` if you need exact cost tracking. - Update pricing values in `models.json` if you need exact cost tracking.
- Referral link for MiniMax Coding Plan (10% off): [https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link](https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link) - Referral link for MiniMax Coding Plan (10% off): [https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link](https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link)
- See [/concepts/model-providers](/concepts/model-providers) for provider rules. - See [/concepts/model-providers](/concepts/model-providers) for provider rules.
- Use `openclaw models list` and `openclaw models set minimax/MiniMax-M2.5` to switch. - Use `openclaw models list` and `openclaw models set minimax/MiniMax-M2.7` to switch.
## Troubleshooting ## Troubleshooting
### "Unknown model: minimax/MiniMax-M2.5" ### "Unknown model: minimax/MiniMax-M2.7"
This usually means the **MiniMax provider isn’t configured** (no provider entry This usually means the **MiniMax provider isn’t configured** (no provider entry
and no MiniMax auth profile/env key found). A fix for this detection is in and no MiniMax auth profile/env key found). A fix for this detection is in
**2026.1.12** (unreleased at the time of writing). Fix by: **2026.1.12** (unreleased at the time of writing). Fix by:
- Upgrading to **2026.1.12** (or run from source `main`), then restarting the gateway. - Upgrading to **2026.1.12** (or run from source `main`), then restarting the gateway.
- Running `openclaw configure` and selecting **MiniMax M2.5**, or - Running `openclaw configure` and selecting a **MiniMax** auth option, or
- Adding the `models.providers.minimax` block manually, or - Adding the `models.providers.minimax` block manually, or
- Setting `MINIMAX_API_KEY` (or a MiniMax auth profile) so the provider can be injected. - Setting `MINIMAX_API_KEY` (or a MiniMax auth profile) so the provider can be injected.
Make sure the model id is **case‑sensitive**: Make sure the model id is **case‑sensitive**:
- `minimax/MiniMax-M2.7`
- `minimax/MiniMax-M2.7-highspeed`
- `minimax/MiniMax-M2.5` - `minimax/MiniMax-M2.5`
- `minimax/MiniMax-M2.5-highspeed` - `minimax/MiniMax-M2.5-highspeed`

2
docs/reference/wizard.md
View File

@ -46,7 +46,7 @@ For a high-level overview, see [Onboarding (CLI)](/start/wizard).
- More detail: [Vercel AI Gateway](/providers/vercel-ai-gateway) - More detail: [Vercel AI Gateway](/providers/vercel-ai-gateway)
- **Cloudflare AI Gateway**: prompts for Account ID, Gateway ID, and `CLOUDFLARE_AI_GATEWAY_API_KEY`. - **Cloudflare AI Gateway**: prompts for Account ID, Gateway ID, and `CLOUDFLARE_AI_GATEWAY_API_KEY`.
- More detail: [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway) - More detail: [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway)
- **MiniMax M2.5**: config is auto-written. - **MiniMax**: config is auto-written; hosted default is `MiniMax-M2.7` and `MiniMax-M2.5` stays available.
- More detail: [MiniMax](/providers/minimax) - More detail: [MiniMax](/providers/minimax)
- **Synthetic (Anthropic-compatible)**: prompts for `SYNTHETIC_API_KEY`. - **Synthetic (Anthropic-compatible)**: prompts for `SYNTHETIC_API_KEY`.
- More detail: [Synthetic](/providers/synthetic) - More detail: [Synthetic](/providers/synthetic)

4
docs/start/wizard-cli-reference.md
View File

@ -170,8 +170,8 @@ What you set:
Prompts for account ID, gateway ID, and `CLOUDFLARE_AI_GATEWAY_API_KEY`. Prompts for account ID, gateway ID, and `CLOUDFLARE_AI_GATEWAY_API_KEY`.
More detail: [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway). More detail: [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway).
</Accordion> </Accordion>
<Accordion title="MiniMax M2.5"> <Accordion title="MiniMax">
Config is auto-written. Config is auto-written. Hosted default is `MiniMax-M2.7`; `MiniMax-M2.5` stays available.
More detail: [MiniMax](/providers/minimax). More detail: [MiniMax](/providers/minimax).
</Accordion> </Accordion>
<Accordion title="Synthetic (Anthropic-compatible)"> <Accordion title="Synthetic (Anthropic-compatible)">