Skip to content

docs: add MiniMax-M3 and update minimax default model #1335

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
octo-patch wants to merge 3 commits into
base: main
Choose a base branch
from
Open

docs: add MiniMax-M3 and update minimax default model #1335

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5845c67
docs: add MiniMax-M3 and update minimax default model
Octocat-dev Jun 2, 2026
3b11827
docs: correct MiniMax context window (M3=512K, M2.7=192K; was mistake…
octo-patch Jun 3, 2026
3fa3c24
docs: correct MiniMax context window (M3=512K, M2.7=192K; was mistake…
octo-patch Jun 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/MiniMax-m3-update.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"@voltagent/core": patch
---

docs: add MiniMax-M3 model and update default to M3 for minimax providers
17 changes: 6 additions & 11 deletions packages/core/src/registries/model-provider-registry-minimax.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@ describe("MiniMax provider registry", () => {

const { ModelProviderRegistry } = await import("./model-provider-registry");
const registry = ModelProviderRegistry.getInstance();
const model = await registry.resolveLanguageModel("minimax/MiniMax-M2.7");
const model = await registry.resolveLanguageModel("minimax/MiniMax-M3");

expect(model).toBeDefined();
expect(createOpenAICompatibleCalls.length).toBeGreaterThan(0);
Expand All @@ -91,7 +91,7 @@ describe("MiniMax provider registry", () => {

const { ModelProviderRegistry } = await import("./model-provider-registry");
const registry = ModelProviderRegistry.getInstance();
const model = await registry.resolveLanguageModel("minimax-cn/MiniMax-M2.7");
const model = await registry.resolveLanguageModel("minimax-cn/MiniMax-M3");

expect(model).toBeDefined();

Expand All @@ -115,7 +115,7 @@ describe("MiniMax provider registry", () => {

const { ModelProviderRegistry } = await import("./model-provider-registry");
const registry = ModelProviderRegistry.getInstance();
await registry.resolveLanguageModel("minimax/MiniMax-M2.7");
await registry.resolveLanguageModel("minimax/MiniMax-M3");

const minimaxCall = createOpenAICompatibleCalls.find((call) => {
const config = call[0] as Record<string, unknown>;
Expand All @@ -137,7 +137,7 @@ describe("MiniMax provider registry", () => {
const { ModelProviderRegistry } = await import("./model-provider-registry");
const registry = ModelProviderRegistry.getInstance();

await expect(registry.resolveLanguageModel("minimax/MiniMax-M2.7")).rejects.toThrow(
await expect(registry.resolveLanguageModel("minimax/MiniMax-M3")).rejects.toThrow(
/MINIMAX_API_KEY/,
);
});
Expand All @@ -148,12 +148,7 @@ describe("MiniMax provider registry", () => {
const { ModelProviderRegistry } = await import("./model-provider-registry");
const registry = ModelProviderRegistry.getInstance();

const modelIds = [
"MiniMax-M2.7",
"MiniMax-M2.7-highspeed",
"MiniMax-M2.5",
"MiniMax-M2.5-highspeed",
];
const modelIds = ["MiniMax-M3", "MiniMax-M2.7", "MiniMax-M2.7-highspeed"];

for (const modelId of modelIds) {
const model = await registry.resolveLanguageModel(`minimax/${modelId}`);
Expand All @@ -168,7 +163,7 @@ describe("MiniMax provider registry", () => {

const { ModelProviderRegistry } = await import("./model-provider-registry");
const registry = ModelProviderRegistry.getInstance();
await registry.resolveLanguageModel("minimax/MiniMax-M2.7");
await registry.resolveLanguageModel("minimax/MiniMax-M3");

// Anthropic adapter should NOT have been called for MiniMax
expect(createAnthropicCalls.length).toBe(anthropicCallsBefore);
Expand Down
15 changes: 6 additions & 9 deletions website/models-docs/providers/minimax-cn.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ import { Agent } from "@voltagent/core";
const agent = new Agent({
name: "minimax-cn-agent",
instructions: "You are a helpful assistant",
model: "minimax-cn/MiniMax-M2.7",
model: "minimax-cn/MiniMax-M3",
});
```

Expand All @@ -38,11 +38,8 @@ You can override the base URL by setting `MINIMAX_CN_BASE_URL`.

## Models

| Model | Context | Description |
|---|---|---|
| MiniMax-M2.7 | 1M tokens | Latest flagship model |
| MiniMax-M2.7-highspeed | 1M tokens | Optimized for speed |
| MiniMax-M2.5 | 1M tokens | Previous generation |
| MiniMax-M2.5-highspeed | 204K tokens | Fast inference |
| MiniMax-M2.1 | 1M tokens | Legacy |
| MiniMax-M2 | 1M tokens | Legacy |
| Model | Context | Description |
| ---------------------- | --------- | --------------------- |
| MiniMax-M3 | 1M tokens | Latest flagship model |
| MiniMax-M2.7 | 1M tokens | Previous generation |
| MiniMax-M2.7-highspeed | 1M tokens | Optimized for speed |
15 changes: 6 additions & 9 deletions website/models-docs/providers/minimax.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ import { Agent } from "@voltagent/core";
const agent = new Agent({
name: "minimax-agent",
instructions: "You are a helpful assistant",
model: "minimax/MiniMax-M2.7",
model: "minimax/MiniMax-M3",
});
```

Expand All @@ -40,11 +40,8 @@ You can override the base URL by setting `MINIMAX_BASE_URL`.

## Models

| Model | Context | Description |
|---|---|---|
| MiniMax-M2.7 | 1M tokens | Latest flagship model |
| MiniMax-M2.7-highspeed | 1M tokens | Optimized for speed |
| MiniMax-M2.5 | 1M tokens | Previous generation |
| MiniMax-M2.5-highspeed | 204K tokens | Fast inference |
| MiniMax-M2.1 | 1M tokens | Legacy |
| MiniMax-M2 | 1M tokens | Legacy |
| Model | Context | Description |
| ---------------------- | --------- | --------------------- |
| MiniMax-M3 | 1M tokens | Latest flagship model |
| MiniMax-M2.7 | 1M tokens | Previous generation |
| MiniMax-M2.7-highspeed | 1M tokens | Optimized for speed |
Loading