Skip to content

feat(llm_minimax): add MiniMax M3 model profile #1046

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

Merged
dsapandora merged 3 commits into from
Jun 2, 2026
+160 −70
Merged

feat(llm_minimax): add MiniMax M3 model profile #1046

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
90581fd
feat(llm_minimax): add MiniMax M3 model profile
Jun 1, 2026
1b8ef80
Merge branch 'rocketride-org:develop' into feat/RR-1045-add-minimax-m…
mithileshgau Jun 2, 2026
6f67be7
fix(sync_models): protect MiniMax local profiles from pass-2 deprecation
Jun 2, 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
3 changes: 2 additions & 1 deletion nodes/src/nodes/llm_minimax/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@ The MiniMax API is OpenAI-compatible, so this node uses the OpenAI SDK / `langch

| Profile | Model | Context |
| ---------------------- | ------------------------- | ----------- |
| MiniMax M3 | `MiniMax-M3` | 1M tokens |
| MiniMax M2 _(default)_ | `MiniMax-M2` | 200K tokens |
| MiniMax M2.1 | `MiniMax-M2.1` | 200K tokens |
| MiniMax M2.1 Highspeed | `MiniMax-M2.1-highspeed` | 200K tokens |
Expand All @@ -43,7 +44,7 @@ The MiniMax API is OpenAI-compatible, so this node uses the OpenAI SDK / `langch
| MiniMax M2.7 Highspeed | `MiniMax-M2.7-highspeed` | 200K tokens |
| Custom Model | User-defined | User-defined |

The cloud catalogue above is what `models.list()` returns as of 2026-05-21. The `-highspeed` variants are MiniMax's faster/cheaper tier of the same generation.
The cloud catalogue above is what `models.list()` returns as of 2026-05-29. The `-highspeed` variants are MiniMax's faster/cheaper tier of the same generation. **MiniMax M3** is MiniMax's frontier multimodal coding model — 5× the M2-family context (1M tokens) and a 128K-token recommended output limit (max 512K). M3 is multimodal at the API level (text + image + video), though the `llm_minimax` node only exposes the text path.

**Local deploy**

Expand Down
193 changes: 129 additions & 64 deletions nodes/src/nodes/llm_minimax/services.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,103 +91,98 @@
"minimax-m2": {
"title": "MiniMax M2",
"model": "MiniMax-M2",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelSource": "provider",
"modelTotalTokens": 204800, // sync_models.config.json
"modelOutputTokens": 65536, // sync_models.config.json
"serverbase": "https://api.minimax.io/v1",
"apikey": ""
},
"minimax-m2-1": {
"title": "MiniMax M2.1",
"model": "MiniMax-M2.1",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelSource": "provider",
"modelTotalTokens": 204800, // sync_models.config.json
"modelOutputTokens": 65536, // sync_models.config.json
"serverbase": "https://api.minimax.io/v1",
"apikey": ""
},
"minimax-m2-1-highspeed": {
"title": "MiniMax M2.1 Highspeed",
"model": "MiniMax-M2.1-highspeed",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelSource": "provider",
"modelTotalTokens": 204800, // sync_models.config.json
"modelOutputTokens": 65536, // sync_models.config.json
"serverbase": "https://api.minimax.io/v1",
"apikey": ""
},
"minimax-m2-5": {
"title": "MiniMax M2.5",
"model": "MiniMax-M2.5",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelSource": "provider",
"modelTotalTokens": 204800, // sync_models.config.json
"modelOutputTokens": 65536, // sync_models.config.json
"serverbase": "https://api.minimax.io/v1",
"apikey": ""
},
"minimax-m2-5-highspeed": {
"title": "MiniMax M2.5 Highspeed",
"model": "MiniMax-M2.5-highspeed",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelSource": "provider",
"modelTotalTokens": 204800, // sync_models.config.json
"modelOutputTokens": 65536, // sync_models.config.json
"serverbase": "https://api.minimax.io/v1",
"apikey": ""
},
"minimax-m2-7": {
"title": "MiniMax M2.7",
"model": "MiniMax-M2.7",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelSource": "provider",
"modelTotalTokens": 204800, // sync_models.config.json
"modelOutputTokens": 65536, // sync_models.config.json
"serverbase": "https://api.minimax.io/v1",
"apikey": ""
},
"minimax-m2-7-highspeed": {
"title": "MiniMax M2.7 Highspeed",
"model": "MiniMax-M2.7-highspeed",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelSource": "provider",
"modelTotalTokens": 204800, // sync_models.config.json
"modelOutputTokens": 65536, // sync_models.config.json
"serverbase": "https://api.minimax.io/v1",
"apikey": ""
},
// Local-deploy profiles. Defaults target vLLM / SGLang on port 8000 with the
// HuggingFace model path (MiniMaxAI/MiniMax-M2.X) — that's the path MiniMax
// itself documents at platform.minimax.io/docs/guides/local-deploy.
//
// MiniMax open-weight models are MIT-licensed but very large (M2 = 230B MoE /
// 10B active; M2.5 / M2.7 likewise) and need ≥96 GB unified memory or a
// multi-GPU server. M2.7 is the only variant whose local-deploy steps are
// formally documented today; M2 / M2.5 entries here are scaffolded against
// the same HF naming so they work as soon as their guides land.
//
// To use Ollama instead: edit serverbase to http://localhost:11434/v1 and set
// `model` to the Ollama tag you pulled. To use MLX on Apple Silicon: set
// serverbase to http://localhost:8080/v1 and model to e.g.
// mlx-community/MiniMax-M2.7-4bit.
"minimax-m2-local": {
"title": "MiniMax M2 (Local)",
"model": "MiniMaxAI/MiniMax-M2",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelTotalTokens": 204800, // manual
"modelOutputTokens": 8192, // manual
"serverbase": "http://localhost:8000/v1"
},
"minimax-m2-5-local": {
"title": "MiniMax M2.5 (Local)",
"model": "MiniMaxAI/MiniMax-M2.5",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelTotalTokens": 204800, // manual
"modelOutputTokens": 8192, // manual
"serverbase": "http://localhost:8000/v1"
},
"minimax-m2-7-local": {
"title": "MiniMax M2.7 (Local)",
"model": "MiniMaxAI/MiniMax-M2.7",
"modelSource": "manual",
"modelTotalTokens": 204800,
"modelOutputTokens": 8192,
"modelTotalTokens": 204800, // manual
"modelOutputTokens": 8192, // manual
"serverbase": "http://localhost:8000/v1"
},
"minimax-m3": {
"title": "MiniMax M3",
"model": "MiniMax-M3",
"modelSource": "provider",
"modelTotalTokens": 1000000, // sync_models.config.json
"modelOutputTokens": 131072, // sync_models.config.json
"serverbase": "https://api.minimax.io/v1",
"apikey": ""
}
}
},
Expand Down Expand Up @@ -216,100 +211,170 @@
},
"minimax.custom": {
"object": "custom",
"properties": ["model", "modelTotalTokens", "minimax.serverbase", "llm.cloud.apikey", "llm.cloud.modelSource"]
"properties": [
"model",
"modelTotalTokens",
"minimax.serverbase",
"llm.cloud.apikey",
"llm.cloud.modelSource"
]
},
"minimax.minimax-m2": {
"object": "minimax-m2",
"properties": ["llm.cloud.apikey", "llm.cloud.modelSource"]
"properties": [
"llm.cloud.apikey",
"llm.cloud.modelSource"
]
},
"minimax.minimax-m2-1": {
"object": "minimax-m2-1",
"properties": ["llm.cloud.apikey", "llm.cloud.modelSource"]
"properties": [
"llm.cloud.apikey",
"llm.cloud.modelSource"
]
},
"minimax.minimax-m2-1-highspeed": {
"object": "minimax-m2-1-highspeed",
"properties": ["llm.cloud.apikey", "llm.cloud.modelSource"]
"properties": [
"llm.cloud.apikey",
"llm.cloud.modelSource"
]
},
"minimax.minimax-m2-5": {
"object": "minimax-m2-5",
"properties": ["llm.cloud.apikey", "llm.cloud.modelSource"]
"properties": [
"llm.cloud.apikey",
"llm.cloud.modelSource"
]
},
"minimax.minimax-m2-5-highspeed": {
"object": "minimax-m2-5-highspeed",
"properties": ["llm.cloud.apikey", "llm.cloud.modelSource"]
"properties": [
"llm.cloud.apikey",
"llm.cloud.modelSource"
]
},
"minimax.minimax-m2-7": {
"object": "minimax-m2-7",
"properties": ["llm.cloud.apikey", "llm.cloud.modelSource"]
"properties": [
"llm.cloud.apikey",
"llm.cloud.modelSource"
]
},
"minimax.minimax-m2-7-highspeed": {
"object": "minimax-m2-7-highspeed",
"properties": ["llm.cloud.apikey", "llm.cloud.modelSource"]
"properties": [
"llm.cloud.apikey",
"llm.cloud.modelSource"
]
},
"minimax.minimax-m2-local": {
"object": "minimax-m2-local",
"properties": ["llm.local.serverbase"]
"properties": [
"llm.local.serverbase"
]
},
"minimax.minimax-m2-5-local": {
"object": "minimax-m2-5-local",
"properties": ["llm.local.serverbase"]
"properties": [
"llm.local.serverbase"
]
},
"minimax.minimax-m2-7-local": {
"object": "minimax-m2-7-local",
"properties": ["llm.local.serverbase"]
"properties": [
"llm.local.serverbase"
]
},
"minimax.profile": {
"title": "Model",
"description": "MiniMax LLM model",
"type": "string",
"default": "minimax-m2",
"enum": ["*>preconfig.profiles.*.title"],
"enum": [
"*>preconfig.profiles.*.title"
],
"conditional": [
{
"value": "custom",
"properties": ["minimax.custom"]
"properties": [
"minimax.custom"
]
},
{
"value": "minimax-m2",
"properties": ["minimax.minimax-m2"]
"properties": [
"minimax.minimax-m2"
]
},
{
"value": "minimax-m2-1",
"properties": ["minimax.minimax-m2-1"]
"properties": [
"minimax.minimax-m2-1"
]
},
{
"value": "minimax-m2-1-highspeed",
"properties": ["minimax.minimax-m2-1-highspeed"]
"properties": [
"minimax.minimax-m2-1-highspeed"
]
},
{
"value": "minimax-m2-5",
"properties": ["minimax.minimax-m2-5"]
"properties": [
"minimax.minimax-m2-5"
]
},
{
"value": "minimax-m2-5-highspeed",
"properties": ["minimax.minimax-m2-5-highspeed"]
"properties": [
"minimax.minimax-m2-5-highspeed"
]
},
{
"value": "minimax-m2-7",
"properties": ["minimax.minimax-m2-7"]
"properties": [
"minimax.minimax-m2-7"
]
},
{
"value": "minimax-m2-7-highspeed",
"properties": ["minimax.minimax-m2-7-highspeed"]
"properties": [
"minimax.minimax-m2-7-highspeed"
]
},
{
"value": "minimax-m2-local",
"properties": ["minimax.minimax-m2-local"]
"properties": [
"minimax.minimax-m2-local"
]
},
{
"value": "minimax-m2-5-local",
"properties": ["minimax.minimax-m2-5-local"]
"properties": [
"minimax.minimax-m2-5-local"
]
},
{
"value": "minimax-m2-7-local",
"properties": ["minimax.minimax-m2-7-local"]
"properties": [
"minimax.minimax-m2-7-local"
]
},
{
"value": "minimax-m3",
"properties": [
"minimax.minimax-m3"
]
}
]
},
"minimax.minimax-m3": {
"object": "minimax-m3",
"properties": [
"llm.cloud.apikey",
"llm.cloud.modelSource"
]
}
},
//
Expand Down
Loading
Loading