@picsart/ai-sdk 6.54.0 → 6.55.0

package/README.md

@@ -194,7 +194,7 @@ names or catalog model IDs from an arbitrary vendor request.
 
 ## Text Generation (LLMs)
 
-Claude, GPT, Gemini, Kimi and Grok text models are called with `generateText()`. Single-shot:
+Claude, GPT, Gemini, Kimi, Grok and MiniMax text models are called with `generateText()`. Single-shot:
 pass a prompt and optional image(s)/video, get text back. They surface in the catalog
 as `mode: 'text'`. Each vendor uses its own native workflow, so capabilities aren't lost
 — Gemini accepts video input, Claude uses the Anthropic-native messages API.
@@ -227,9 +227,10 @@ await ai.generateText(Models.Gemini3Pro, {
 catalog.find({ output: 'text' })
 ```
 
-> Thinking level maps per vendor: OpenAI, Kimi and Grok → `reasoning_effort`, Gemini →
-> `thinkingConfig.thinkingLevel` (LOW/HIGH). Kimi K3 and Grok 4.7 always reason, so
-> they have no `off`. Claude’s `claude/v1/messages`
+> Thinking level maps per vendor: OpenAI, Kimi, Grok and MiniMax M3.1 Flash → `reasoning_effort`, Gemini →
+> `thinkingConfig.thinkingLevel` (LOW/HIGH). Kimi K3, Grok 4.7 and MiniMax M3.1 Flash
+> always reason, so they have no `off`. MiniMax M3 reasons adaptively and has no
+> thinking knob. Claude’s `claude/v1/messages`
 > workflow exposes no thinking knob, so Claude models omit `thinking`.
 
 `generateText()` is type-narrowed to text models (`TextModelId`); calling it with an

package/index.d.ts

@@ -1360,6 +1360,15 @@ type ModelInputById = {
         seed?: number;
         enableSafetyChecker?: boolean;
     };
+    "minimax-m3": {
+        prompt: string;
+        imageUrls?: string[];
+    };
+    "minimax-m3.1-flash": {
+        prompt: string;
+        imageUrls?: string[];
+        thinking?: "low" | "medium" | "high";
+    };
     "minimax-music-v2": {
         prompt: string;
         lyricsPrompt?: string;
@@ -2194,7 +2203,7 @@ type ModelInputById = {
 type TypedModelId = keyof ModelInputById;
 type ModelInput<M extends TypedModelId> = ModelInputById[M];
 /** IDs of text-generation (LLM) models — narrows generateText(). */
-type TextModelId = "claude-fable-5" | "claude-fable-5-1" | "claude-haiku-4-5" | "claude-haiku-5-5" | "claude-opus-4-8" | "claude-opus-5" | "claude-sonnet-4-5" | "claude-sonnet-4-6" | "claude-sonnet-5" | "eleven-speech-to-text" | "gemini-2.5-flash" | "gemini-3-pro" | "gemini-3.5-flash-lite" | "gemini-3.6-flash" | "gemini-3.7-flash" | "gemini-3.8-flash" | "gemini-4-argon" | "gpt-4.1-mini" | "gpt-4.1-nano" | "gpt-4o" | "gpt-4o-mini" | "gpt-5" | "gpt-5-mini" | "gpt-5.1" | "gpt-5.2" | "gpt-5.5" | "gpt-5.6-luna" | "gpt-5.6-sol" | "gpt-5.6-terra" | "gpt-6-astra" | "gpt-6-luna" | "gpt-6-sol" | "grok-4.7" | "kimi-k3" | "minimax-h3-context-ir";
+type TextModelId = "claude-fable-5" | "claude-fable-5-1" | "claude-haiku-4-5" | "claude-haiku-5-5" | "claude-opus-4-8" | "claude-opus-5" | "claude-sonnet-4-5" | "claude-sonnet-4-6" | "claude-sonnet-5" | "eleven-speech-to-text" | "gemini-2.5-flash" | "gemini-3-pro" | "gemini-3.5-flash-lite" | "gemini-3.6-flash" | "gemini-3.7-flash" | "gemini-3.8-flash" | "gemini-4-argon" | "gpt-4.1-mini" | "gpt-4.1-nano" | "gpt-4o" | "gpt-4o-mini" | "gpt-5" | "gpt-5-mini" | "gpt-5.1" | "gpt-5.2" | "gpt-5.5" | "gpt-5.6-luna" | "gpt-5.6-sol" | "gpt-5.6-terra" | "gpt-6-astra" | "gpt-6-luna" | "gpt-6-sol" | "grok-4.7" | "kimi-k3" | "minimax-h3-context-ir" | "minimax-m3" | "minimax-m3.1-flash";
 type TextModelInputById = Pick<ModelInputById, TextModelId>;
 /** IDs of structured-output (json-mode) models — narrows run()'s result type. */
 type JsonModelId = "typesafe-evaluate";
@@ -3724,6 +3733,8 @@ declare const Models: {
     readonly MinimaxH3MaxLipSync: "minimax-h3-max-lip-sync";
     readonly MinimaxH3MaxRelight: "minimax-h3-max-relight";
     readonly MinimaxH3MaxTurbo: "minimax-h3-max-turbo";
+    readonly MinimaxM3: "minimax-m3";
+    readonly MinimaxM31Flash: "minimax-m3.1-flash";
     readonly MinimaxMusicV2: "minimax-music-v2";
     readonly MinimaxMusicV3: "minimax-music-v3";
     readonly MireloSfx20TextToAudio: "mirelo-sfx-2.0-text-to-audio";

package/index.js

@@ -11119,7 +11119,41 @@ var h3ContextIrConstraints = [
   { when: { videoUrls: { exists: true } }, then: H3_REFERENCE_EXCLUDES_FRAMES },
   { when: { audioUrls: { exists: true } }, then: H3_REFERENCE_EXCLUDES_FRAMES }
 ];
+var minimaxFlashThinkingParam = () => p.enum("thinking", ["low", "medium", "high"], "high", { label: "Thinking" });
 var { MODELS: MINIMAX_LLM } = defineModels("minimax", [
+  {
+    id: "minimax-m3",
+    name: "MiniMax M3",
+    workflow: "chat-completions",
+    addedAt: "2026-10-26",
+    estimatedTime: 10,
+    mode: "text",
+    inputType: "i2t",
+    badge: ["new"],
+    description: "MiniMax\u2019s flagship model \u2014 adaptive reasoning with a 1M-token context.",
+    features: [feat("Vision", "input"), feat("Thinking", "characteristic")],
+    paramConfig: {
+      ...params.prompt(),
+      ...params.imageInput(8, "Images")
+    }
+  },
+  {
+    id: "minimax-m3.1-flash",
+    name: "MiniMax M3.1 Flash",
+    workflow: "chat-completions",
+    addedAt: "2026-10-26",
+    estimatedTime: 8,
+    mode: "text",
+    inputType: "i2t",
+    badge: ["new"],
+    description: "Fast, low-cost MiniMax model \u2014 always-on reasoning with a 1M-token context.",
+    features: [feat("Vision", "input"), feat("Thinking", "characteristic")],
+    paramConfig: {
+      ...params.prompt(),
+      ...params.imageInput(8, "Images"),
+      ...minimaxFlashThinkingParam()
+    }
+  },
   {
     id: "minimax-h3-context-ir",
     name: "MiniMax H3 Context IR",
@@ -11252,7 +11286,9 @@ registerPayloads(MODELS34, {
   "gemini-3.5-flash-lite": buildOpenAiPayload("gemini-3.5-flash-lite"),
   "gemini-2.5-flash": buildOpenAiPayload("gemini-2.5-flash"),
   "kimi-k3": buildOpenAiPayload("kimi-k3"),
-  "grok-4.7": buildOpenAiPayload("grok-4.7")
+  "grok-4.7": buildOpenAiPayload("grok-4.7"),
+  "minimax-m3": buildOpenAiPayload("minimax-m3"),
+  "minimax-m3.1-flash": buildOpenAiPayload("minimax-m3.1-flash")
 });
 
 // src/vendors/catalog/captionsai.ts
@@ -15490,6 +15526,8 @@ var MinimaxH3MaxExtend = "minimax-h3-max-extend";
 var MinimaxH3MaxLipSync = "minimax-h3-max-lip-sync";
 var MinimaxH3MaxRelight = "minimax-h3-max-relight";
 var MinimaxH3MaxTurbo = "minimax-h3-max-turbo";
+var MinimaxM3 = "minimax-m3";
+var MinimaxM31Flash = "minimax-m3.1-flash";
 var MinimaxMusicV2 = "minimax-music-v2";
 var MinimaxMusicV3 = "minimax-music-v3";
 var MireloSfx20TextToAudio = "mirelo-sfx-2.0-text-to-audio";
@@ -15760,6 +15798,8 @@ var Models = {
   MinimaxH3MaxLipSync,
   MinimaxH3MaxRelight,
   MinimaxH3MaxTurbo,
+  MinimaxM3,
+  MinimaxM31Flash,
   MinimaxMusicV2,
   MinimaxMusicV3,
   MireloSfx20TextToAudio,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@picsart/ai-sdk",
-  "version": "6.54.0",
+  "version": "6.55.0",
   "type": "module",
   "description": "Type-safe SDK for 100+ AI models — image, video, audio, and text generation with Picsart",
   "license": "MIT",