feat(minimax): add m3 model support (#88860)

2026-06-06 05:51:15 +08:00 · 2026-05-31 21:47:47 -04:00
parent 9919e4601f
commit 0369672691
25 changed files with 279 additions and 115 deletions
--- a/.github/workflows/openclaw-live-and-e2e-checks-reusable.yml
+++ b/.github/workflows/openclaw-live-and-e2e-checks-reusable.yml
@@ -1953,7 +1953,7 @@ jobs:
            profiles: stable full
          - suite_id: native-live-src-gateway-profiles-minimax
            label: Native live gateway profiles MiniMax
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=minimax,minimax-portal OPENCLAW_LIVE_GATEWAY_MODELS=minimax/MiniMax-M2.7,minimax-portal/MiniMax-M2.7 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=minimax,minimax-portal OPENCLAW_LIVE_GATEWAY_MODELS=minimax/MiniMax-M3,minimax-portal/MiniMax-M3 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
            timeout_minutes: 60
            profile_env_only: false
            profiles: stable full
@@ -2252,7 +2252,7 @@ jobs:
            profiles: stable full
          - suite_id: live-gateway-minimax-docker
            label: Docker live gateway MiniMax
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=minimax,minimax-portal OPENCLAW_LIVE_GATEWAY_MODELS=minimax/MiniMax-M2.7,minimax-portal/MiniMax-M2.7 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=1 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=180000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=minimax,minimax-portal OPENCLAW_LIVE_GATEWAY_MODELS=minimax/MiniMax-M3,minimax-portal/MiniMax-M3 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=1 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=180000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
            timeout_minutes: 40
            profile_env_only: false
            profiles: stable full
--- a/docs/concepts/model-providers.md
+++ b/docs/concepts/model-providers.md
@@ -303,7 +303,7 @@ See [/providers/kilocode](/providers/kilocode) for setup details.
 | Hugging Face Inference                  | `huggingface`                    | `HUGGINGFACE_HUB_TOKEN` or `HF_TOKEN`                        | `huggingface/deepseek-ai/DeepSeek-R1`                      |
 | Kilo Gateway                            | `kilocode`                       | `KILOCODE_API_KEY`                                           | `kilocode/kilo/auto`                                       |
 | Kimi Coding                             | `kimi`                           | `KIMI_API_KEY` or `KIMICODE_API_KEY`                         | `kimi/kimi-for-coding`                                     |
-| MiniMax                                 | `minimax` / `minimax-portal`     | `MINIMAX_API_KEY` / `MINIMAX_OAUTH_TOKEN`                    | `minimax/MiniMax-M2.7`                                     |
+| MiniMax                                 | `minimax` / `minimax-portal`     | `MINIMAX_API_KEY` / `MINIMAX_OAUTH_TOKEN`                    | `minimax/MiniMax-M3`                                       |
 | Mistral                                 | `mistral`                        | `MISTRAL_API_KEY`                                            | `mistral/mistral-large-latest`                             |
 | Moonshot                                | `moonshot`                       | `MOONSHOT_API_KEY`                                           | `moonshot/kimi-k2.6`                                       |
 | NVIDIA                                  | `nvidia`                         | `NVIDIA_API_KEY`                                             | `nvidia/nvidia/nemotron-3-super-120b-a12b`                 |
@@ -331,7 +331,7 @@ See [/providers/kilocode](/providers/kilocode) for setup details.
    Gemini-backed refs follow the same proxy-Gemini sanitation path; `kilocode/kilo/auto` and other proxy-reasoning-unsupported refs skip proxy reasoning injection.
  </Accordion>
  <Accordion title="MiniMax">
-    API-key onboarding writes explicit text-only M2.7 chat model definitions; image understanding stays on the plugin-owned `MiniMax-VL-01` media provider.
+    API-key onboarding writes explicit M3 and M2.7 chat model definitions; image understanding stays on the plugin-owned `MiniMax-VL-01` media provider.
  </Accordion>
  <Accordion title="NVIDIA">
    Model ids use a `nvidia/<vendor>/<model>` namespace (for example `nvidia/nvidia/nemotron-...` alongside `nvidia/moonshotai/kimi-k2.5`); pickers preserve the literal `<provider>/<model-id>` composition while the canonical key sent to the API stays single-prefixed.
@@ -537,7 +537,7 @@ On MiniMax's Anthropic-compatible streaming path, OpenClaw disables thinking by

 Plugin-owned capability split:

- Text/chat defaults stay on `minimax/MiniMax-M2.7`
+- Text/chat defaults stay on `minimax/MiniMax-M3`
 - Image generation is `minimax/image-01` or `minimax-portal/image-01`
 - Image understanding is plugin-owned `MiniMax-VL-01` on both MiniMax auth paths
 - Web search stays on provider id `minimax`
--- a/docs/gateway/config-tools.md
+++ b/docs/gateway/config-tools.md
@@ -645,14 +645,14 @@ Interactive custom-provider onboarding infers image input for common vision mode
  <Accordion title="Local models (LM Studio)">
    See [Local Models](/gateway/local-models). TL;DR: run a large local model via LM Studio Responses API on serious hardware; keep hosted models merged for fallback.
  </Accordion>
-  <Accordion title="MiniMax M2.7 (direct)">
+  <Accordion title="MiniMax M3 (direct)">
    ```json5
    {
      agents: {
        defaults: {
-          model: { primary: "minimax/MiniMax-M2.7" },
+          model: { primary: "minimax/MiniMax-M3" },
          models: {
-            "minimax/MiniMax-M2.7": { alias: "Minimax" },
+            "minimax/MiniMax-M3": { alias: "Minimax" },
          },
        },
      },
@@ -665,12 +665,12 @@ Interactive custom-provider onboarding infers image input for common vision mode
            api: "anthropic-messages",
            models: [
              {
-                id: "MiniMax-M2.7",
-                name: "MiniMax M2.7",
+                id: "MiniMax-M3",
+                name: "MiniMax M3",
                reasoning: true,
-                input: ["text"],
-                cost: { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0.375 },
-                contextWindow: 204800,
+                input: ["text", "image"],
+                cost: { input: 0.6, output: 2.4, cacheRead: 0.12, cacheWrite: 0 },
+                contextWindow: 1000000,
                maxTokens: 131072,
              },
            ],
@@ -680,7 +680,7 @@ Interactive custom-provider onboarding infers image input for common vision mode
    }
    ```

-    Set `MINIMAX_API_KEY`. Shortcuts: `openclaw onboard --auth-choice minimax-global-api` or `openclaw onboard --auth-choice minimax-cn-api`. The model catalog defaults to M2.7 only. On the Anthropic-compatible streaming path, OpenClaw disables MiniMax thinking by default unless you explicitly set `thinking` yourself. `/fast on` or `params.fastMode: true` rewrites `MiniMax-M2.7` to `MiniMax-M2.7-highspeed`.
+    Set `MINIMAX_API_KEY`. Shortcuts: `openclaw onboard --auth-choice minimax-global-api` or `openclaw onboard --auth-choice minimax-cn-api`. The model catalog defaults to M3 and also includes the M2.7 variants. On the Anthropic-compatible streaming path, OpenClaw disables MiniMax thinking by default unless you explicitly set `thinking` yourself. `/fast on` or `params.fastMode: true` rewrites `MiniMax-M2.7` to `MiniMax-M2.7-highspeed`.

  </Accordion>
  <Accordion title="Moonshot AI (Kimi)">
--- a/docs/help/faq-models.md
+++ b/docs/help/faq-models.md
@@ -215,7 +215,7 @@ troubleshooting, see the main [FAQ](/help/faq).

  </Accordion>

-  <Accordion title='Why do I see "Unknown model: minimax/MiniMax-M2.7"?'>
+  <Accordion title='Why do I see "Unknown model: minimax/MiniMax-M3"?'>
    This means the **provider isn't configured** (no MiniMax provider config or auth
    profile was found), so the model can't be resolved.

@@ -227,8 +227,9 @@ troubleshooting, see the main [FAQ](/help/faq).
       (`MINIMAX_API_KEY` for `minimax`, `MINIMAX_OAUTH_TOKEN` or stored MiniMax
       OAuth for `minimax-portal`).
    3. Use the exact model id (case-sensitive) for your auth path:
-       `minimax/MiniMax-M2.7` or `minimax/MiniMax-M2.7-highspeed` for API-key
-       setup, or `minimax-portal/MiniMax-M2.7` /
+       `minimax/MiniMax-M3`, `minimax/MiniMax-M2.7`, or
+       `minimax/MiniMax-M2.7-highspeed` for API-key setup, or
+       `minimax-portal/MiniMax-M3`, `minimax-portal/MiniMax-M2.7`, or
       `minimax-portal/MiniMax-M2.7-highspeed` for OAuth setup.
    4. Run:

@@ -253,9 +254,9 @@ troubleshooting, see the main [FAQ](/help/faq).
      env: { MINIMAX_API_KEY: "sk-...", OPENAI_API_KEY: "sk-..." },
      agents: {
        defaults: {
-          model: { primary: "minimax/MiniMax-M2.7" },
+          model: { primary: "minimax/MiniMax-M3" },
          models: {
-            "minimax/MiniMax-M2.7": { alias: "minimax" },
+            "minimax/MiniMax-M3": { alias: "minimax" },
            "openai/gpt-5.5": { alias: "gpt" },
          },
        },
--- a/docs/help/testing-live.md
+++ b/docs/help/testing-live.md
@@ -73,7 +73,7 @@ Live tests are split into two layers so we can isolate failures:
  - `pnpm test:live` (or `OPENCLAW_LIVE_TEST=1` if invoking Vitest directly)
 - Set `OPENCLAW_LIVE_MODELS=modern`, `small`, or `all` (alias for modern) to actually run this suite; otherwise it skips to keep `pnpm test:live` focused on gateway smoke
 - How to select models:
-  - `OPENCLAW_LIVE_MODELS=modern` to run the modern allowlist (Opus/Sonnet 4.6+, GPT-5.2 + Codex, Gemini 3, DeepSeek V4, GLM 4.7, MiniMax M2.7, Grok 4.3)
+  - `OPENCLAW_LIVE_MODELS=modern` to run the modern allowlist (Opus/Sonnet 4.6+, GPT-5.2 + Codex, Gemini 3, DeepSeek V4, GLM 4.7, MiniMax M3, Grok 4.3)
  - `OPENCLAW_LIVE_MODELS=small` to run the constrained small-model allowlist (Qwen 8B/9B local-compatible routes, Ollama Gemma, OpenRouter Qwen/GLM, and Z.AI GLM)
  - `OPENCLAW_LIVE_MODELS=all` is an alias for the modern allowlist
  - or `OPENCLAW_LIVE_MODELS="openai/gpt-5.5,anthropic/claude-opus-4-6,..."` (comma allowlist)
@@ -109,7 +109,7 @@ Live tests are split into two layers so we can isolate failures:
 - How to enable:
  - `pnpm test:live` (or `OPENCLAW_LIVE_TEST=1` if invoking Vitest directly)
 - How to select models:
-  - Default: modern allowlist (Opus/Sonnet 4.6+, GPT-5.2 + Codex, Gemini 3, DeepSeek V4, GLM 4.7, MiniMax M2.7, Grok 4.3)
+  - Default: modern allowlist (Opus/Sonnet 4.6+, GPT-5.2 + Codex, Gemini 3, DeepSeek V4, GLM 4.7, MiniMax M3, Grok 4.3)
  - `OPENCLAW_LIVE_GATEWAY_MODELS=all` is an alias for the modern allowlist
  - Or set `OPENCLAW_LIVE_GATEWAY_MODELS="provider/model"` (or comma list) to narrow
  - Modern/all gateway sweeps default to a curated high-signal cap; set `OPENCLAW_LIVE_GATEWAY_MAX_MODELS=0` for an exhaustive modern sweep or a positive number for a smaller cap.
@@ -351,7 +351,7 @@ Narrow, explicit allowlists are fastest and least flaky:
  - `OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`

 - Tool calling across several providers:
-  - `OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5,anthropic/claude-opus-4-6,google/gemini-3-flash-preview,deepseek/deepseek-v4-flash,zai/glm-5.1,minimax/MiniMax-M2.7" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
+  - `OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5,anthropic/claude-opus-4-6,google/gemini-3-flash-preview,deepseek/deepseek-v4-flash,zai/glm-5.1,minimax/MiniMax-M3" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`

 - Google focus (Gemini API key + Antigravity):
  - Gemini (API key): `OPENCLAW_LIVE_GATEWAY_MODELS="google/gemini-3-flash-preview" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
@@ -385,10 +385,10 @@ This is the "common models" run we expect to keep working:
 - Google (Antigravity): `google-antigravity/claude-opus-4-6-thinking` and `google-antigravity/gemini-3-flash`
 - DeepSeek: `deepseek/deepseek-v4-flash` and `deepseek/deepseek-v4-pro`
 - Z.AI (GLM): `zai/glm-5.1`
- MiniMax: `minimax/MiniMax-M2.7`
+- MiniMax: `minimax/MiniMax-M3`

 Run gateway smoke with tools + image:
-`OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5,anthropic/claude-opus-4-6,google/gemini-3.1-pro-preview,google/gemini-3-flash-preview,google-antigravity/claude-opus-4-6-thinking,google-antigravity/gemini-3-flash,deepseek/deepseek-v4-flash,zai/glm-5.1,minimax/MiniMax-M2.7" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
+`OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.5,anthropic/claude-opus-4-6,google/gemini-3.1-pro-preview,google/gemini-3-flash-preview,google-antigravity/claude-opus-4-6-thinking,google-antigravity/gemini-3-flash,deepseek/deepseek-v4-flash,zai/glm-5.1,minimax/MiniMax-M3" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`

 ### Baseline: tool calling (Read + optional Exec)

@@ -399,7 +399,7 @@ Pick at least one per provider family:
 - Google: `google/gemini-3-flash-preview` (or `google/gemini-3.1-pro-preview`)
 - DeepSeek: `deepseek/deepseek-v4-flash`
 - Z.AI (GLM): `zai/glm-5.1`
- MiniMax: `minimax/MiniMax-M2.7`
+- MiniMax: `minimax/MiniMax-M3`

 Optional additional coverage (nice to have):

--- a/docs/providers/minimax.md
+++ b/docs/providers/minimax.md
@@ -6,7 +6,7 @@ read_when:
 title: "MiniMax"
 ---

-OpenClaw's MiniMax provider defaults to **MiniMax M2.7**.
+OpenClaw's MiniMax provider defaults to **MiniMax M3**.

 MiniMax also provides:

@@ -26,7 +26,8 @@ Provider split:

 | Model                    | Type             | Description                              |
 | ------------------------ | ---------------- | ---------------------------------------- |
-| `MiniMax-M2.7`           | Chat (reasoning) | Default hosted reasoning model           |
+| `MiniMax-M3`             | Chat (reasoning) | Default hosted reasoning model           |
+| `MiniMax-M2.7`           | Chat (reasoning) | Previous hosted reasoning model          |
 | `MiniMax-M2.7-highspeed` | Chat (reasoning) | Faster M2.7 reasoning tier               |
 | `MiniMax-VL-01`          | Vision           | Image understanding model                |
 | `image-01`               | Image generation | Text-to-image and image-to-image editing |
@@ -79,7 +80,7 @@ Choose your preferred auth method and follow the setup steps.
    </Tabs>

    <Note>
-    OAuth setups use the `minimax-portal` provider id. Model refs follow the form `minimax-portal/MiniMax-M2.7`.
+    OAuth setups use the `minimax-portal` provider id. Model refs follow the form `minimax-portal/MiniMax-M3`.
    </Note>

    <Tip>
@@ -131,7 +132,7 @@ Choose your preferred auth method and follow the setup steps.
    ```json5
    {
      env: { MINIMAX_API_KEY: "sk-..." },
-      agents: { defaults: { model: { primary: "minimax/MiniMax-M2.7" } } },
+      agents: { defaults: { model: { primary: "minimax/MiniMax-M3" } } },
      models: {
        mode: "merge",
        providers: {
@@ -140,6 +141,15 @@ Choose your preferred auth method and follow the setup steps.
            apiKey: "${MINIMAX_API_KEY}",
            api: "anthropic-messages",
            models: [
+              {
+                id: "MiniMax-M3",
+                name: "MiniMax M3",
+                reasoning: true,
+                input: ["text", "image"],
+                cost: { input: 0.6, output: 2.4, cacheRead: 0.12, cacheWrite: 0 },
+                contextWindow: 1000000,
+                maxTokens: 131072,
+              },
              {
                id: "MiniMax-M2.7",
                name: "MiniMax M2.7",
@@ -170,7 +180,7 @@ Choose your preferred auth method and follow the setup steps.
    </Warning>

    <Note>
-    API-key setups use the `minimax` provider id. Model refs follow the form `minimax/MiniMax-M2.7`.
+    API-key setups use the `minimax` provider id. Model refs follow the form `minimax/MiniMax-M3`.
    </Note>

  </Tab>
@@ -243,9 +253,10 @@ through the CN endpoint; the default global endpoint is
 `https://api.minimax.io`.

 When onboarding or API-key setup writes explicit `models.providers.minimax`
-entries, OpenClaw materializes `MiniMax-M2.7` and
-`MiniMax-M2.7-highspeed` as text-only chat models. Image understanding is
-exposed separately through the plugin-owned `MiniMax-VL-01` media provider.
+entries, OpenClaw materializes `MiniMax-M3`, `MiniMax-M2.7`, and
+`MiniMax-M2.7-highspeed` as chat models. M3 advertises text and image input;
+image understanding remains exposed separately through the plugin-owned
+`MiniMax-VL-01` media provider.

 <Note>
 See [Image Generation](/tools/image-generation) for shared tool parameters, provider selection, and failover behavior.
@@ -353,7 +364,7 @@ catalog:
 | `minimax-portal` | `MiniMax-VL-01`     |

 That is why automatic media routing can use MiniMax image understanding even
-when the bundled text-provider catalog still shows text-only M2.7 chat refs.
+when the bundled text-provider catalog also includes M3 image-capable chat refs.

 ### Web search

@@ -437,12 +448,12 @@ See [MiniMax Search](/tools/minimax-search) for full web search configuration an
 - Model refs follow the auth path:
  - API-key setup: `minimax/<model>`
  - OAuth setup: `minimax-portal/<model>`
- Default chat model: `MiniMax-M2.7`
- Alternate chat model: `MiniMax-M2.7-highspeed`
- Onboarding and direct API-key setup write text-only model definitions for both M2.7 variants
+- Default chat model: `MiniMax-M3`
+- Alternate chat models: `MiniMax-M2.7`, `MiniMax-M2.7-highspeed`
+- Onboarding and direct API-key setup write model definitions for M3 and both M2.7 variants
 - Image understanding uses the plugin-owned `MiniMax-VL-01` media provider
 - Update pricing values in `models.json` if you need exact cost tracking
- Use `openclaw models list` to confirm the current provider id, then switch with `openclaw models set minimax/MiniMax-M2.7` or `openclaw models set minimax-portal/MiniMax-M2.7`
+- Use `openclaw models list` to confirm the current provider id, then switch with `openclaw models set minimax/MiniMax-M3` or `openclaw models set minimax-portal/MiniMax-M3`

 <Tip>
 Referral link for MiniMax Coding Plan (10% off): [MiniMax Coding Plan](https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link)
@@ -455,7 +466,7 @@ See [Model providers](/concepts/model-providers) for provider rules.
 ## Troubleshooting

 <AccordionGroup>
-  <Accordion title='"Unknown model: minimax/MiniMax-M2.7"'>
+  <Accordion title='"Unknown model: minimax/MiniMax-M3"'>
    This usually means the **MiniMax provider is not configured** (no matching provider entry and no MiniMax auth profile/env key found). A fix for this detection is in **2026.1.12**. Fix by:

    - Upgrading to **2026.1.12** (or run from source `main`), then restarting the gateway.
@@ -465,8 +476,8 @@ See [Model providers](/concepts/model-providers) for provider rules.

    Make sure the model id is **case-sensitive**:

-    - API-key path: `minimax/MiniMax-M2.7` or `minimax/MiniMax-M2.7-highspeed`
-    - OAuth path: `minimax-portal/MiniMax-M2.7` or `minimax-portal/MiniMax-M2.7-highspeed`
+    - API-key path: `minimax/MiniMax-M3`, `minimax/MiniMax-M2.7`, or `minimax/MiniMax-M2.7-highspeed`
+    - OAuth path: `minimax-portal/MiniMax-M3`, `minimax-portal/MiniMax-M2.7`, or `minimax-portal/MiniMax-M2.7-highspeed`

    Then recheck with:

--- a/docs/reference/wizard.md
+++ b/docs/reference/wizard.md
@@ -47,7 +47,7 @@ For a high-level overview, see [Onboarding (CLI)](/start/wizard).
    - More detail: [Vercel AI Gateway](/providers/vercel-ai-gateway)
    - **Cloudflare AI Gateway**: prompts for Account ID, Gateway ID, and `CLOUDFLARE_AI_GATEWAY_API_KEY`.
    - More detail: [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway)
-    - **MiniMax**: config is auto-written; hosted default is `MiniMax-M2.7`.
+    - **MiniMax**: config is auto-written; hosted default is `MiniMax-M3`.
      API-key setup uses `minimax/...`, and OAuth setup uses
      `minimax-portal/...`.
    - More detail: [MiniMax](/providers/minimax)
--- a/docs/start/wizard-cli-reference.md
+++ b/docs/start/wizard-cli-reference.md
@@ -182,7 +182,7 @@ What you set:
    More detail: [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway).
  </Accordion>
  <Accordion title="MiniMax">
-    Config is auto-written. Hosted default is `MiniMax-M2.7`; API-key setup uses
+    Config is auto-written. Hosted default is `MiniMax-M3`; API-key setup uses
    `minimax/...`, and OAuth setup uses `minimax-portal/...`.
    More detail: [MiniMax](/providers/minimax).
  </Accordion>
--- a/extensions/minimax/index.test.ts
+++ b/extensions/minimax/index.test.ts
@@ -6,7 +6,7 @@ import {
  registerProviderPlugin,
  requireRegisteredProvider,
 } from "openclaw/plugin-sdk/plugin-test-runtime";
-import { describe, expect, it, vi } from "vitest";
+import { afterEach, describe, expect, it, vi } from "vitest";
 import { registerMinimaxProviders } from "./provider-registration.js";
 import { createMiniMaxWebSearchProvider } from "./src/minimax-web-search-provider.js";

@@ -26,6 +26,10 @@ const minimaxProviderPlugin = {
  },
 };

+afterEach(() => {
+  vi.unstubAllEnvs();
+});
+
 describe("minimax provider hooks", () => {
  it("declares CN provider auth aliases in the manifest", () => {
    const pluginJson = JSON.parse(
@@ -91,7 +95,7 @@ describe("minimax provider hooks", () => {
        hint: "Global endpoint - api.minimax.io",
        choiceId: "minimax-global-api",
        groupId: "minimax",
-        groupHint: "M2.7 (recommended)",
+        groupHint: "M3 (recommended)",
      },
      {
        id: "api-cn",
@@ -99,7 +103,7 @@ describe("minimax provider hooks", () => {
        hint: "CN endpoint - api.minimaxi.com",
        choiceId: "minimax-cn-api",
        groupId: "minimax",
-        groupHint: "M2.7 (recommended)",
+        groupHint: "M3 (recommended)",
      },
    ]);

@@ -119,7 +123,7 @@ describe("minimax provider hooks", () => {
        hint: "Global endpoint - api.minimax.io",
        choiceId: "minimax-global-oauth",
        groupId: "minimax",
-        groupHint: "M2.7 (recommended)",
+        groupHint: "M3 (recommended)",
      },
      {
        id: "oauth-cn",
@@ -127,7 +131,7 @@ describe("minimax provider hooks", () => {
        hint: "CN endpoint - api.minimaxi.com",
        choiceId: "minimax-cn-oauth",
        groupId: "minimax",
-        groupHint: "M2.7 (recommended)",
+        groupHint: "M3 (recommended)",
      },
    ]);
  });
@@ -173,7 +177,7 @@ describe("minimax provider hooks", () => {
    });
  });

-  it("keeps M2.7 on the Anthropic Messages route used by the empty-history guard", async () => {
+  it("lists M3 on the Anthropic Messages route used by the empty-history guard", async () => {
    const { providers } = await registerProviderPlugin({
      plugin: minimaxProviderPlugin,
      id: "minimax",
@@ -193,13 +197,55 @@ describe("minimax provider hooks", () => {
    expect(provider?.api).toBe("anthropic-messages");
    expect(provider?.authHeader).toBe(true);
    expect(provider?.baseUrl).toBe("https://api.minimax.io/anthropic");
-    const model = provider?.models.find((entry: { id?: string }) => entry.id === "MiniMax-M2.7");
-    expect(model?.id).toBe("MiniMax-M2.7");
-    expect(model?.input).toEqual(["text"]);
-    expect(model?.name).toBe("MiniMax M2.7");
+    const model = provider?.models.find((entry: { id?: string }) => entry.id === "MiniMax-M3");
+    expect(model?.id).toBe("MiniMax-M3");
+    expect(model?.input).toEqual(["text", "image"]);
+    expect(model?.name).toBe("MiniMax M3");
    expect(model?.reasoning).toBe(true);
  });

+  it("resolves M3 through the dynamic model hook before agent discovery", async () => {
+    const { providers } = await registerProviderPlugin({
+      plugin: minimaxProviderPlugin,
+      id: "minimax",
+      name: "MiniMax Provider",
+    });
+    const apiProvider = requireRegisteredProvider(providers, "minimax");
+
+    const model = apiProvider.resolveDynamicModel?.({
+      provider: "minimax",
+      modelId: "MiniMax-M3",
+      providerConfig: {},
+    } as never);
+
+    expect(model).toMatchObject({
+      provider: "minimax",
+      id: "MiniMax-M3",
+      api: "anthropic-messages",
+      baseUrl: "https://api.minimax.io/anthropic",
+      input: ["text", "image"],
+      contextWindow: 1_000_000,
+    });
+  });
+
+  it("keeps MINIMAX_API_HOST endpoint overrides on dynamic M3 resolution", async () => {
+    vi.stubEnv("MINIMAX_API_HOST", "https://api.minimaxi.com");
+    const { providers } = await registerProviderPlugin({
+      plugin: minimaxProviderPlugin,
+      id: "minimax",
+      name: "MiniMax Provider",
+    });
+    const apiProvider = requireRegisteredProvider(providers, "minimax");
+
+    const model = apiProvider.resolveDynamicModel?.({
+      provider: "minimax",
+      modelId: "MiniMax-M3",
+      providerConfig: {},
+    } as never);
+
+    expect(model?.baseUrl).toBe("https://api.minimaxi.com/anthropic");
+  });
+
  it("owns fast-mode stream wrapping for MiniMax transports", async () => {
    const { providers } = await registerProviderPlugin({
      plugin: minimaxProviderPlugin,
--- a/extensions/minimax/model-definitions.test.ts
+++ b/extensions/minimax/model-definitions.test.ts
@@ -7,40 +7,43 @@ import {
  MINIMAX_API_COST,
  MINIMAX_API_HIGHSPEED_COST,
  MINIMAX_HOSTED_MODEL_ID,
+  MINIMAX_M27_API_COST,
  MINIMAX_M25_API_COST,
  MINIMAX_M25_API_HIGHSPEED_COST,
+  MINIMAX_M3_CONTEXT_WINDOW,
 } from "./model-definitions.js";

 describe("minimax model definitions", () => {
-  it("uses M2.7 as default hosted model", () => {
-    expect(MINIMAX_HOSTED_MODEL_ID).toBe("MiniMax-M2.7");
+  it("uses M3 as default hosted model", () => {
+    expect(MINIMAX_HOSTED_MODEL_ID).toBe("MiniMax-M3");
  });

-  it("uses the higher upstream MiniMax context and token defaults", () => {
+  it("uses the current upstream MiniMax context, token, and pricing defaults", () => {
+    expect(MINIMAX_M3_CONTEXT_WINDOW).toBe(1_000_000);
    expect(DEFAULT_MINIMAX_CONTEXT_WINDOW).toBe(204800);
    expect(DEFAULT_MINIMAX_MAX_TOKENS).toBe(131072);
    expect(MINIMAX_API_COST).toEqual({
-      input: 0.3,
-      output: 1.2,
-      cacheRead: 0.06,
-      cacheWrite: 0.375,
+      input: 0.6,
+      output: 2.4,
+      cacheRead: 0.12,
+      cacheWrite: 0,
    });
  });

-  it("builds catalog model with name and reasoning from catalog for M2.7", () => {
+  it("builds catalog model with M3 metadata from the catalog", () => {
    const model = buildMinimaxModelDefinition({
-      id: "MiniMax-M2.7",
+      id: "MiniMax-M3",
      cost: MINIMAX_API_COST,
-      contextWindow: DEFAULT_MINIMAX_CONTEXT_WINDOW,
+      contextWindow: MINIMAX_M3_CONTEXT_WINDOW,
      maxTokens: DEFAULT_MINIMAX_MAX_TOKENS,
    });
    expect(model).toEqual({
-      contextWindow: DEFAULT_MINIMAX_CONTEXT_WINDOW,
+      contextWindow: MINIMAX_M3_CONTEXT_WINDOW,
      cost: MINIMAX_API_COST,
-      id: "MiniMax-M2.7",
-      input: ["text"],
+      id: "MiniMax-M3",
+      input: ["text", "image"],
      maxTokens: DEFAULT_MINIMAX_MAX_TOKENS,
-      name: "MiniMax M2.7",
+      name: "MiniMax M3",
      reasoning: true,
    });
  });
@@ -63,12 +66,12 @@ describe("minimax model definitions", () => {
    });
  });

-  it("builds API model definition with standard cost for M2.7", () => {
-    const model = buildMinimaxApiModelDefinition("MiniMax-M2.7");
+  it("builds API model definition with standard cost for M3", () => {
+    const model = buildMinimaxApiModelDefinition("MiniMax-M3");
    expect(model.cost).toEqual(MINIMAX_API_COST);
-    expect(model.contextWindow).toBe(DEFAULT_MINIMAX_CONTEXT_WINDOW);
+    expect(model.contextWindow).toBe(MINIMAX_M3_CONTEXT_WINDOW);
    expect(model.maxTokens).toBe(DEFAULT_MINIMAX_MAX_TOKENS);
-    expect(model.input).toEqual(["text"]);
+    expect(model.input).toEqual(["text", "image"]);
  });

  it("falls back to generated name for unknown model id", () => {
@@ -77,6 +80,13 @@ describe("minimax model definitions", () => {
    expect(model.reasoning).toBe(false);
  });

+  it("keeps M2.7 on its existing price and text-only metadata", () => {
+    const model = buildMinimaxApiModelDefinition("MiniMax-M2.7");
+    expect(model.input).toEqual(["text"]);
+    expect(model.cost).toEqual(MINIMAX_M27_API_COST);
+    expect(model.contextWindow).toBe(DEFAULT_MINIMAX_CONTEXT_WINDOW);
+  });
+
  it("keeps M2.7 text-only on the Anthropic-compatible chat path", () => {
    const model = buildMinimaxApiModelDefinition("MiniMax-M2.7");
    expect(model.input).toEqual(["text"]);
--- a/extensions/minimax/model-definitions.ts
+++ b/extensions/minimax/model-definitions.ts
@@ -7,9 +7,16 @@ export const MINIMAX_CN_API_BASE_URL = "https://api.minimaxi.com/anthropic";
 export const MINIMAX_HOSTED_MODEL_ID = MINIMAX_DEFAULT_MODEL_ID;
 export const MINIMAX_HOSTED_MODEL_REF = `minimax/${MINIMAX_HOSTED_MODEL_ID}`;
 export const DEFAULT_MINIMAX_CONTEXT_WINDOW = 204800;
+export const MINIMAX_M3_CONTEXT_WINDOW = 1_000_000;
 export const DEFAULT_MINIMAX_MAX_TOKENS = 131072;

 export const MINIMAX_API_COST = {
+  input: 0.6,
+  output: 2.4,
+  cacheRead: 0.12,
+  cacheWrite: 0,
+};
+export const MINIMAX_M27_API_COST = {
  input: 0.3,
  output: 1.2,
  cacheRead: 0.06,
@@ -49,6 +56,9 @@ export const MINIMAX_LM_STUDIO_COST = {
 type MinimaxCatalogId = keyof typeof MINIMAX_TEXT_MODEL_CATALOG;

 export function resolveMinimaxApiCost(modelId: string): ModelDefinitionConfig["cost"] {
+  if (modelId === "MiniMax-M2.7") {
+    return MINIMAX_M27_API_COST;
+  }
  if (modelId === "MiniMax-M2.5-highspeed") {
    return MINIMAX_M25_API_HIGHSPEED_COST;
  }
@@ -74,7 +84,7 @@ export function buildMinimaxModelDefinition(params: {
    id: params.id,
    name: params.name ?? catalog?.name ?? `MiniMax ${params.id}`,
    reasoning: params.reasoning ?? catalog?.reasoning ?? false,
-    input: ["text"],
+    input: [...(catalog?.input ?? ["text"])],
    cost: params.cost,
    contextWindow: params.contextWindow,
    maxTokens: params.maxTokens,
@@ -85,7 +95,9 @@ export function buildMinimaxApiModelDefinition(modelId: string): ModelDefinition
  return buildMinimaxModelDefinition({
    id: modelId,
    cost: resolveMinimaxApiCost(modelId),
-    contextWindow: DEFAULT_MINIMAX_CONTEXT_WINDOW,
+    contextWindow:
+      MINIMAX_TEXT_MODEL_CATALOG[modelId as MinimaxCatalogId]?.contextWindow ??
+      DEFAULT_MINIMAX_CONTEXT_WINDOW,
    maxTokens: DEFAULT_MINIMAX_MAX_TOKENS,
  });
 }
--- a/extensions/minimax/onboard.test.ts
+++ b/extensions/minimax/onboard.test.ts
@@ -14,16 +14,16 @@ describe("minimax onboard", () => {
      baseUrl: "https://api.minimax.io/anthropic",
      api: "anthropic-messages",
      authHeader: true,
-      models: [buildMinimaxApiModelDefinition("MiniMax-M2.7")],
+      models: [buildMinimaxApiModelDefinition("MiniMax-M3")],
    });
-    expect(cfg.agents?.defaults?.models?.["minimax/MiniMax-M2.7"]).toEqual({
+    expect(cfg.agents?.defaults?.models?.["minimax/MiniMax-M3"]).toEqual({
      alias: "Minimax",
    });
-    expect(cfg.agents?.defaults?.model).toEqual({ primary: "minimax/MiniMax-M2.7" });
+    expect(cfg.agents?.defaults?.model).toEqual({ primary: "minimax/MiniMax-M3" });
  });

-  it("keeps reasoning enabled for MiniMax-M2.7", () => {
-    const cfg = applyMinimaxApiConfig({}, "MiniMax-M2.7");
+  it("keeps reasoning enabled for MiniMax-M3", () => {
+    const cfg = applyMinimaxApiConfig({}, "MiniMax-M3");
    expect(cfg.models?.providers?.minimax?.models[0]?.reasoning).toBe(true);
  });

@@ -73,7 +73,7 @@ describe("minimax onboard", () => {
      legacyApi: "openai-completions",
    });
    expect(provider?.authHeader).toBe(true);
-    expect(provider?.models.map((m) => m.id)).toEqual(["old-model", "MiniMax-M2.7"]);
+    expect(provider?.models.map((m) => m.id)).toEqual(["old-model", "MiniMax-M3"]);
  });

  it("preserves other providers when adding minimax", () => {
--- a/extensions/minimax/onboard.ts
+++ b/extensions/minimax/onboard.ts
@@ -9,6 +9,7 @@ import {
  MINIMAX_API_BASE_URL,
  MINIMAX_CN_API_BASE_URL,
 } from "./model-definitions.js";
+import { MINIMAX_DEFAULT_MODEL_ID } from "./provider-models.js";

 type MinimaxApiProviderConfigParams = {
  providerId: string;
@@ -61,7 +62,7 @@ function applyMinimaxApiConfigWithBaseUrl(

 export function applyMinimaxApiProviderConfig(
  cfg: OpenClawConfig,
-  modelId = "MiniMax-M2.7",
+  modelId = MINIMAX_DEFAULT_MODEL_ID,
 ): OpenClawConfig {
  return applyMinimaxApiProviderConfigWithBaseUrl(cfg, {
    providerId: "minimax",
@@ -72,7 +73,7 @@ export function applyMinimaxApiProviderConfig(

 export function applyMinimaxApiConfig(
  cfg: OpenClawConfig,
-  modelId = "MiniMax-M2.7",
+  modelId = MINIMAX_DEFAULT_MODEL_ID,
 ): OpenClawConfig {
  return applyMinimaxApiConfigWithBaseUrl(cfg, {
    providerId: "minimax",
@@ -83,7 +84,7 @@ export function applyMinimaxApiConfig(

 export function applyMinimaxApiProviderConfigCn(
  cfg: OpenClawConfig,
-  modelId = "MiniMax-M2.7",
+  modelId = MINIMAX_DEFAULT_MODEL_ID,
 ): OpenClawConfig {
  return applyMinimaxApiProviderConfigWithBaseUrl(cfg, {
    providerId: "minimax",
@@ -94,7 +95,7 @@ export function applyMinimaxApiProviderConfigCn(

 export function applyMinimaxApiConfigCn(
  cfg: OpenClawConfig,
-  modelId = "MiniMax-M2.7",
+  modelId = MINIMAX_DEFAULT_MODEL_ID,
 ): OpenClawConfig {
  return applyMinimaxApiConfigWithBaseUrl(cfg, {
    providerId: "minimax",
--- a/extensions/minimax/openclaw.plugin.json
+++ b/extensions/minimax/openclaw.plugin.json
@@ -34,7 +34,7 @@
      "choiceHint": "Global endpoint - api.minimax.io",
      "groupId": "minimax",
      "groupLabel": "MiniMax",
-      "groupHint": "M2.7 (recommended)"
+      "groupHint": "M3 (recommended)"
    },
    {
      "provider": "minimax",
@@ -45,7 +45,7 @@
      "choiceHint": "Global endpoint - api.minimax.io",
      "groupId": "minimax",
      "groupLabel": "MiniMax",
-      "groupHint": "M2.7 (recommended)",
+      "groupHint": "M3 (recommended)",
      "optionKey": "minimaxApiKey",
      "cliFlag": "--minimax-api-key",
      "cliOption": "--minimax-api-key <key>",
@@ -59,7 +59,7 @@
      "choiceHint": "CN endpoint - api.minimaxi.com",
      "groupId": "minimax",
      "groupLabel": "MiniMax",
-      "groupHint": "M2.7 (recommended)"
+      "groupHint": "M3 (recommended)"
    },
    {
      "provider": "minimax",
@@ -70,7 +70,7 @@
      "choiceHint": "CN endpoint - api.minimaxi.com",
      "groupId": "minimax",
      "groupLabel": "MiniMax",
-      "groupHint": "M2.7 (recommended)",
+      "groupHint": "M3 (recommended)",
      "optionKey": "minimaxApiKey",
      "cliFlag": "--minimax-api-key",
      "cliOption": "--minimax-api-key <key>",
--- a/extensions/minimax/provider-catalog.ts
+++ b/extensions/minimax/provider-catalog.ts
@@ -3,14 +3,13 @@ import type {
  ModelProviderConfig,
 } from "openclaw/plugin-sdk/provider-model-shared";
 import {
-  DEFAULT_MINIMAX_CONTEXT_WINDOW,
  DEFAULT_MINIMAX_MAX_TOKENS,
  MINIMAX_API_BASE_URL,
  resolveMinimaxApiCost,
 } from "./model-definitions.js";
 import { MINIMAX_TEXT_MODEL_CATALOG, MINIMAX_TEXT_MODEL_ORDER } from "./provider-models.js";

-function resolveMinimaxCatalogBaseUrl(env: NodeJS.ProcessEnv = process.env): string {
+export function resolveMinimaxCatalogBaseUrl(env: NodeJS.ProcessEnv = process.env): string {
  const rawHost = env.MINIMAX_API_HOST?.trim();
  if (!rawHost) {
    return MINIMAX_API_BASE_URL;
@@ -34,6 +33,7 @@ function buildMinimaxModel(params: {
  reasoning: boolean;
  input: ModelDefinitionConfig["input"];
  cost: ModelDefinitionConfig["cost"];
+  contextWindow: number;
 }): ModelDefinitionConfig {
  return {
    id: params.id,
@@ -41,7 +41,7 @@ function buildMinimaxModel(params: {
    reasoning: params.reasoning,
    input: params.input,
    cost: params.cost,
-    contextWindow: DEFAULT_MINIMAX_CONTEXT_WINDOW,
+    contextWindow: params.contextWindow,
    maxTokens: DEFAULT_MINIMAX_MAX_TOKENS,
  };
 }
@@ -50,9 +50,11 @@ function buildMinimaxTextModel(params: {
  id: string;
  name: string;
  reasoning: boolean;
+  input: ModelDefinitionConfig["input"];
  cost: ModelDefinitionConfig["cost"];
+  contextWindow: number;
 }): ModelDefinitionConfig {
-  return buildMinimaxModel({ ...params, input: ["text"] });
+  return buildMinimaxModel(params);
 }

 function buildMinimaxCatalog(): ModelDefinitionConfig[] {
@@ -62,7 +64,9 @@ function buildMinimaxCatalog(): ModelDefinitionConfig[] {
      id,
      name: model.name,
      reasoning: model.reasoning,
+      input: [...model.input],
      cost: resolveMinimaxApiCost(id),
+      contextWindow: model.contextWindow,
    });
  });
 }
--- a/extensions/minimax/provider-contract-api.ts
+++ b/extensions/minimax/provider-contract-api.ts
@@ -4,7 +4,7 @@ const noopAuth = async () => ({ profiles: [] });
 const wizardGroup = {
  groupId: "minimax",
  groupLabel: "MiniMax",
-  groupHint: "M2.7 (recommended)",
+  groupHint: "M3 (recommended)",
 } as const;

 export function createMinimaxProvider(): ProviderPlugin {
--- a/extensions/minimax/provider-models.ts
+++ b/extensions/minimax/provider-models.ts
@@ -1,20 +1,40 @@
 import { matchesExactOrPrefix } from "openclaw/plugin-sdk/provider-model-shared";

-export const MINIMAX_DEFAULT_MODEL_ID = "MiniMax-M2.7";
+export const MINIMAX_DEFAULT_MODEL_ID = "MiniMax-M3";
 export const MINIMAX_DEFAULT_MODEL_REF = `minimax/${MINIMAX_DEFAULT_MODEL_ID}`;

-export const MINIMAX_TEXT_MODEL_ORDER = ["MiniMax-M2.7", "MiniMax-M2.7-highspeed"] as const;
+export const MINIMAX_TEXT_MODEL_ORDER = [
+  "MiniMax-M3",
+  "MiniMax-M2.7",
+  "MiniMax-M2.7-highspeed",
+] as const;

 export const MINIMAX_TEXT_MODEL_CATALOG = {
-  "MiniMax-M2.7": { name: "MiniMax M2.7", reasoning: true },
-  "MiniMax-M2.7-highspeed": { name: "MiniMax M2.7 Highspeed", reasoning: true },
+  "MiniMax-M3": {
+    name: "MiniMax M3",
+    reasoning: true,
+    input: ["text", "image"],
+    contextWindow: 1_000_000,
+  },
+  "MiniMax-M2.7": {
+    name: "MiniMax M2.7",
+    reasoning: true,
+    input: ["text"],
+    contextWindow: 204800,
+  },
+  "MiniMax-M2.7-highspeed": {
+    name: "MiniMax M2.7 Highspeed",
+    reasoning: true,
+    input: ["text"],
+    contextWindow: 204800,
+  },
 } as const;

 export const MINIMAX_TEXT_MODEL_REFS = MINIMAX_TEXT_MODEL_ORDER.map(
  (modelId) => `minimax/${modelId}`,
 );

-const MINIMAX_MODERN_MODEL_MATCHERS = ["minimax-m2.7"] as const;
+const MINIMAX_MODERN_MODEL_MATCHERS = ["minimax-m3", "minimax-m2.7"] as const;

 export function isMiniMaxModernModelId(modelId: string): boolean {
  return matchesExactOrPrefix(modelId, MINIMAX_MODERN_MODEL_MATCHERS);
--- a/extensions/minimax/provider-registration.ts
+++ b/extensions/minimax/provider-registration.ts
@@ -5,6 +5,8 @@ import type {
  ProviderAuthContext,
  ProviderAuthResult,
  ProviderCatalogContext,
+  ProviderResolveDynamicModelContext,
+  ProviderRuntimeModel,
 } from "openclaw/plugin-sdk/plugin-entry";
 import {
  MINIMAX_OAUTH_MARKER,
@@ -14,14 +16,27 @@ import {
 import { buildOauthProviderAuthResult } from "openclaw/plugin-sdk/provider-auth";
 import { createProviderApiKeyAuthMethod } from "openclaw/plugin-sdk/provider-auth-api-key";
 import type { ProviderPlugin } from "openclaw/plugin-sdk/provider-model-shared";
-import { buildProviderReplayFamilyHooks } from "openclaw/plugin-sdk/provider-model-shared";
+import {
+  buildProviderReplayFamilyHooks,
+  normalizeModelCompat,
+} from "openclaw/plugin-sdk/provider-model-shared";
 import { MINIMAX_FAST_MODE_STREAM_HOOKS } from "openclaw/plugin-sdk/provider-stream-family";
 import { fetchMinimaxUsage } from "openclaw/plugin-sdk/provider-usage";
 import { normalizeOptionalString } from "openclaw/plugin-sdk/string-coerce-runtime";
-import { isMiniMaxModernModelId, MINIMAX_DEFAULT_MODEL_ID } from "./api.js";
+import {
+  isMiniMaxModernModelId,
+  MINIMAX_DEFAULT_MODEL_ID,
+  MINIMAX_TEXT_MODEL_CATALOG,
+  MINIMAX_TEXT_MODEL_ORDER,
+} from "./api.js";
+import { DEFAULT_MINIMAX_MAX_TOKENS, resolveMinimaxApiCost } from "./model-definitions.js";
 import type { MiniMaxRegion } from "./oauth.js";
 import { applyMinimaxApiConfig, applyMinimaxApiConfigCn } from "./onboard.js";
-import { buildMinimaxPortalProvider, buildMinimaxProvider } from "./provider-catalog.js";
+import {
+  buildMinimaxPortalProvider,
+  buildMinimaxProvider,
+  resolveMinimaxCatalogBaseUrl,
+} from "./provider-catalog.js";

 const API_PROVIDER_ID = "minimax";
 const PORTAL_PROVIDER_ID = "minimax-portal";
@@ -38,7 +53,7 @@ const MINIMAX_USAGE_ENV_VAR_KEYS = [
 const MINIMAX_WIZARD_GROUP = {
  groupId: "minimax",
  groupLabel: "MiniMax",
-  groupHint: "M2.7 (recommended)",
+  groupHint: "M3 (recommended)",
 } as const;
 const HYBRID_ANTHROPIC_OPENAI_REPLAY_HOOKS = buildProviderReplayFamilyHooks({
  family: "hybrid-anthropic-openai",
@@ -86,6 +101,35 @@ function buildPortalProviderCatalog(params: { baseUrl: string; apiKey: string })
  };
 }

+function findMinimaxCatalogModel(modelId: string) {
+  const normalizedModelId = modelId.trim().toLowerCase();
+  const catalogId = MINIMAX_TEXT_MODEL_ORDER.find((id) => id.toLowerCase() === normalizedModelId);
+  return catalogId ? { id: catalogId, model: MINIMAX_TEXT_MODEL_CATALOG[catalogId] } : undefined;
+}
+
+function resolveMinimaxDynamicModel(params: {
+  providerId: string;
+  ctx: ProviderResolveDynamicModelContext;
+}): ProviderRuntimeModel | undefined {
+  const catalogModel = findMinimaxCatalogModel(params.ctx.modelId);
+  if (!catalogModel) {
+    return undefined;
+  }
+  return normalizeModelCompat({
+    id: catalogModel.id,
+    name: catalogModel.model.name,
+    provider: params.providerId,
+    api: "anthropic-messages",
+    baseUrl:
+      normalizeOptionalString(params.ctx.providerConfig?.baseUrl) ?? resolveMinimaxCatalogBaseUrl(),
+    reasoning: catalogModel.model.reasoning,
+    input: [...catalogModel.model.input],
+    cost: resolveMinimaxApiCost(catalogModel.id),
+    contextWindow: catalogModel.model.contextWindow,
+    maxTokens: DEFAULT_MINIMAX_MAX_TOKENS,
+  });
+}
+
 function resolveApiCatalog(ctx: ProviderCatalogContext) {
  const apiKey = ctx.resolveProviderApiKey(API_PROVIDER_ID).apiKey;
  if (!apiKey) {
@@ -165,6 +209,7 @@ function createOAuthHandler(region: MiniMaxRegion) {
          agents: {
            defaults: {
              models: {
+                [portalModelRef("MiniMax-M3")]: { alias: "minimax-m3" },
                [portalModelRef("MiniMax-M2.7")]: { alias: "minimax-m2.7" },
                [portalModelRef("MiniMax-M2.7-highspeed")]: {
                  alias: "minimax-m2.7-highspeed",
@@ -267,6 +312,7 @@ export function buildMinimaxApiProviderPlugin(): ProviderPlugin {
      return apiKey ? { token: apiKey } : null;
    },
    ...MINIMAX_PROVIDER_HOOKS,
+    resolveDynamicModel: (ctx) => resolveMinimaxDynamicModel({ providerId: API_PROVIDER_ID, ctx }),
    isModernModelRef: ({ modelId }) => isMiniMaxModernModelId(modelId),
    fetchUsageSnapshot: async (ctx) =>
      await fetchMinimaxUsage(ctx.token, ctx.timeoutMs, ctx.fetchFn, {
@@ -292,6 +338,8 @@ export function buildMinimaxPortalProviderPlugin(): ProviderPlugin {
    },
    auth: [createMinimaxOAuthMethod("global"), createMinimaxOAuthMethod("cn")],
    ...MINIMAX_PROVIDER_HOOKS,
+    resolveDynamicModel: (ctx) =>
+      resolveMinimaxDynamicModel({ providerId: PORTAL_PROVIDER_ID, ctx }),
    isModernModelRef: ({ modelId }) => isMiniMaxModernModelId(modelId),
  };
 }
--- a/src/agents/live-model-filter.ts
+++ b/src/agents/live-model-filter.ts
@@ -19,7 +19,7 @@ const HIGH_SIGNAL_LIVE_MODEL_PRIORITY = [
  "anthropic/claude-opus-4-6",
  "deepseek/deepseek-v4-flash",
  "deepseek/deepseek-v4-pro",
-  "minimax/minimax-m2.7",
+  "minimax/minimax-m3",
  "openai/gpt-5.5",
  "openrouter/openai/gpt-5.2-chat",
  "openrouter/minimax/minimax-m2.7",
@@ -28,7 +28,7 @@ const HIGH_SIGNAL_LIVE_MODEL_PRIORITY = [
  "xai/grok-4.3",
  "zai/glm-5.1",
  "fireworks/accounts/fireworks/models/glm-5p1",
-  "minimax-portal/minimax-m2.7",
+  "minimax-portal/minimax-m3",
 ] as const;

 const SMALL_LIVE_MODEL_PRIORITY = [
--- a/src/agents/minimax-docs.test.ts
+++ b/src/agents/minimax-docs.test.ts
@@ -13,7 +13,7 @@ const minimaxDoc = fs.readFileSync(path.join(repoRoot, "docs/providers/minimax.m

 describe("MiniMax docs sync", () => {
  it("keeps the live-testing guide on the current MiniMax default", () => {
-    expect(testingLiveDoc).toContain("MiniMax M2.7");
+    expect(testingLiveDoc).toContain("MiniMax M3");
    expect(testingLiveDoc).toContain(MINIMAX_DEFAULT_MODEL_REF);
  });

--- a/src/agents/minimax.live.test.ts
+++ b/src/agents/minimax.live.test.ts
@@ -8,7 +8,7 @@ import {

 const MINIMAX_KEY = process.env.MINIMAX_API_KEY ?? "";
 const MINIMAX_BASE_URL = process.env.MINIMAX_BASE_URL?.trim() || "https://api.minimax.io/anthropic";
-const MINIMAX_MODEL = process.env.MINIMAX_MODEL?.trim() || "MiniMax-M2.7";
+const MINIMAX_MODEL = process.env.MINIMAX_MODEL?.trim() || "MiniMax-M3";
 const LIVE = isLiveTestEnabled(["MINIMAX_LIVE_TEST"]);

 const describeLive = LIVE && MINIMAX_KEY ? describe : describe.skip;
@@ -36,10 +36,10 @@ describeLive("minimax live", () => {
      provider: "minimax",
      baseUrl: MINIMAX_BASE_URL,
      reasoning: false,
-      input: ["text"],
+      input: ["text", "image"],
      // Pricing: placeholder values (per 1M tokens, multiplied by 1000 for display)
      cost: { input: 15, output: 60, cacheRead: 2, cacheWrite: 10 },
-      contextWindow: 200000,
+      contextWindow: 1_000_000,
      maxTokens: 8192,
    };
    const probeResult = await runMinimaxTextProbe(model, 128);
--- a/src/agents/model-compat.test.ts
+++ b/src/agents/model-compat.test.ts
@@ -524,6 +524,7 @@ describe("isHighSignalLiveModelRef", () => {
    expect(
      isHighSignalLiveModelRef({ provider: "openrouter", id: "minimax/minimax-m2.1:free" }),
    ).toBe(false);
+    expect(isHighSignalLiveModelRef({ provider: "minimax", id: "MiniMax-M3" })).toBe(true);
    expect(isHighSignalLiveModelRef({ provider: "minimax", id: "MiniMax-M2.7" })).toBe(true);
    expect(isHighSignalLiveModelRef({ provider: "openrouter", id: "minimax/minimax-m2.7" })).toBe(
      true,
@@ -656,7 +657,7 @@ describe("isPrioritizedHighSignalLiveModelRef", () => {
      { provider: "anthropic", id: "claude-opus-4-6" },
      { provider: "deepseek", id: "deepseek-v4-flash" },
      { provider: "deepseek", id: "deepseek-v4-pro" },
-      { provider: "minimax", id: "minimax-m2.7" },
+      { provider: "minimax", id: "minimax-m3" },
      { provider: "openai", id: "gpt-5.5" },
      { provider: "openrouter", id: "openai/gpt-5.2-chat" },
      { provider: "openrouter", id: "minimax/minimax-m2.7" },
@@ -665,7 +666,7 @@ describe("isPrioritizedHighSignalLiveModelRef", () => {
      { provider: "xai", id: "grok-4.3" },
      { provider: "zai", id: "glm-5.1" },
      { provider: "fireworks", id: "accounts/fireworks/models/glm-5p1" },
-      { provider: "minimax-portal", id: "minimax-m2.7" },
+      { provider: "minimax-portal", id: "minimax-m3" },
    ]);
  });
 });
@@ -733,7 +734,7 @@ describe("selectHighSignalLiveItems", () => {
      { provider: "openai", id: "gpt-5.5" },
      { provider: "deepseek", id: "deepseek-v4-flash" },
      { provider: "deepseek", id: "deepseek-v4-pro" },
-      { provider: "minimax", id: "minimax-m2.7" },
+      { provider: "minimax", id: "minimax-m3" },
    ];

    expect(
@@ -746,7 +747,7 @@ describe("selectHighSignalLiveItems", () => {
    ).toEqual([
      { provider: "deepseek", id: "deepseek-v4-flash" },
      { provider: "deepseek", id: "deepseek-v4-pro" },
-      { provider: "minimax", id: "minimax-m2.7" },
+      { provider: "minimax", id: "minimax-m3" },
    ]);
  });

--- a/src/agents/models-config.providers.minimax.test.ts
+++ b/src/agents/models-config.providers.minimax.test.ts
@@ -2,6 +2,15 @@ import { describe, expect, it } from "vitest";

 function buildMinimaxCatalog() {
  return [
+    {
+      id: "MiniMax-M3",
+      cost: {
+        input: 0.6,
+        output: 2.4,
+        cacheRead: 0.12,
+        cacheWrite: 0,
+      },
+    },
    {
      id: "MiniMax-M2.7",
      cost: {
@@ -30,10 +39,12 @@ describe("minimax provider catalog", () => {
      "minimax-portal": { models: buildMinimaxCatalog() },
    };
    expect(providers?.minimax?.models?.map((model) => model.id)).toEqual([
+      "MiniMax-M3",
      "MiniMax-M2.7",
      "MiniMax-M2.7-highspeed",
    ]);
    expect(providers?.["minimax-portal"]?.models?.map((model) => model.id)).toEqual([
+      "MiniMax-M3",
      "MiniMax-M2.7",
      "MiniMax-M2.7-highspeed",
    ]);
--- a/src/plugin-sdk/test-helpers/provider-discovery-contract.ts
+++ b/src/plugin-sdk/test-helpers/provider-discovery-contract.ts
@@ -717,6 +717,7 @@ export function describeMinimaxProviderDiscoveryContract(
        apiKey: "minimax-key",
      });
      const ids = providerModelIds(provider);
+      expect(ids).toContain("MiniMax-M3");
      expect(ids).toContain("MiniMax-M2.7");
      expect(ids).toContain("MiniMax-M2.7-highspeed");
    });
--- a/test/scripts/package-acceptance-workflow.test.ts
+++ b/test/scripts/package-acceptance-workflow.test.ts
@@ -255,9 +255,7 @@ describe("package acceptance workflow", () => {
    expect(crabboxConfig.jobs?.changed?.command).toContain(
      "commit -q --no-gpg-sign -m remote-check-tree",
    );
-    expect(crabboxConfig.jobs?.changed?.command).toContain(
-      "env CI=1 corepack pnpm check --timed",
-    );
+    expect(crabboxConfig.jobs?.changed?.command).toContain("env CI=1 corepack pnpm check --timed");
    expect(crabboxConfig.ssh?.user).toBe("crabbox");
    expect(crabboxConfig.ssh?.port).toBe("22");
  });
@@ -655,7 +653,7 @@ describe("package artifact reuse", () => {
      "OPENCLAW_LIVE_GATEWAY_MODELS=google/gemini-3.1-pro-preview node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles",
    );
    expect(workflow).toContain(
-      "OPENCLAW_LIVE_GATEWAY_MODELS=minimax/MiniMax-M2.7,minimax-portal/MiniMax-M2.7 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2",
+      "OPENCLAW_LIVE_GATEWAY_MODELS=minimax/MiniMax-M3,minimax-portal/MiniMax-M3 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2",
    );
    expect(workflow).toMatch(
      /suite_id: native-live-src-gateway-profiles-fireworks[\s\S]*?timeout_minutes: 30[\s\S]*?advisory: true/u,