# Models Reference
Source: https://docs.tensormachine.ai/models

## Available models

Tensor Machine serves a catalogue of frontier models via a single OpenAI-compatible API endpoint. All models run on India-resident infrastructure.

<Callout type="info">
  The examples below are **illustrative** — the live catalogue is larger and changes often, and
  **current pricing lives on the website**, not here. For the up-to-date model list, context
  windows, and per-model INR rates, see [tensormachine.ai/models](https://tensormachine.ai/models)
  and [tensormachine.ai/pricing](https://tensormachine.ai/pricing).
</Callout>

### Example models

A few representative models and the kinds of work they suit (not the full list, and **not**
pricing — check the [live catalogue](https://tensormachine.ai/models) for both):

| Model ID | Provider | Context | Type |
|----------|----------|---------|------|
| `z-ai/glm-5.2` | Z-AI | 1M | Chat, Code |
| `minimax/minimax-m3` | MiniMax | 1M | Chat, Code, Vision |
| `deepseek/deepseek-v4-pro` | DeepSeek | 1M | Chat, Code |
| `deepseek/deepseek-v4-flash` | DeepSeek | 1M | Chat |
| `moonshotai/kimi-k2.6` | MoonshotAI | 256K | Chat |
| `moonshotai/kimi-k2.7-code` | MoonshotAI | 256K | Code |
| `qwen/qwen3-235b-a22b` | Alibaba | 128K | Chat, Code |
| `meta-llama/llama-4-maverick` | Meta | 1M | Chat, Vision |
| `google/gemma-3-27b` | Google | 128K | Chat |

View the full, current library — with filtering and live pricing — at
[tensormachine.ai/models](https://tensormachine.ai/models).

## API endpoint

All models are accessed via:

```
POST https://edge.tensormachine.ai/v1/chat/completions
```

The request format is identical to the OpenAI Chat Completions API.

## Choosing a model

| Scenario | Recommended model |
|----------|------------------|
| High-volume chat at low cost | `deepseek/deepseek-v4-flash` |
| Complex reasoning & coding | `deepseek/deepseek-v4-pro` |
| Long document analysis (1M ctx) | `z-ai/glm-5.2` or `minimax/minimax-m3` |
| Image understanding | `minimax/minimax-m3` or `meta-llama/llama-4-maverick` |
| Code generation | `moonshotai/kimi-k2.7-code` |
| Multilingual (Hindi, etc.) | `moonshotai/kimi-k2.6` |
| Budget-friendly open model | `google/gemma-3-27b` |

## Model parameters

All standard OpenAI parameters are supported:

| Parameter | Description |
|-----------|-------------|
| `model` | Model ID (required) |
| `messages` | Conversation history (required) |
| `max_tokens` | Maximum tokens to generate |
| `temperature` | Sampling temperature (0–2) |
| `top_p` | Nucleus sampling |
| `stream` | Enable streaming (SSE) |
| `stop` | Stop sequences |
| `n` | Number of completions |

## Requesting new models

If you need a model not yet on the platform, request it from the console (Models → Request a model). We pool demand and stand up dedicated deployments on a first-come, first-served basis — see [how model requests work](https://tensormachine.ai/request-a-model).