Quickstart

Go from zero to your first inference call in under 5 minutes.

1. Create Your Account

Sign up at app.tensormesh.ai using Google or GitHub.

---

2. Add a Payment Method

1. Go to Billing

   Navigate to Management → Billing → Payment Methods in the sidebar.

2. Add a Card

   Click Add Payment Method and enter your card details.

---

3. Get Your API Key

Navigate to Management → Account → API Keys tab. Use the Copy icon to grab your key for programmatic access.

Treat your API key like a password. Never share it publicly or commit it to version control.

---

4. Make Your First API Call

The serverless API is OpenAI-compatible. Use the endpoint https://serverless.tensormesh.ai with your Tensormesh API key.

cURL

curl --request POST \
  --url https://serverless.tensormesh.ai/v1/chat/completions \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "MiniMaxAI/MiniMax-M2.5",
  "max_tokens": 16384,
  "temperature": 0.6,
  "messages": [
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ],
  "top_p": 1,
  "top_k": 40,
  "presence_penalty": 0,
  "frequency_penalty": 0
}'

Python

import requests

url = "https://serverless.tensormesh.ai/v1/chat/completions"

payload = {
    "model": "MiniMaxAI/MiniMax-M2.5",
    "max_tokens": 16384,
    "temperature": 0.6,
    "messages": [
        {
            "role": "user",
            "content": "Hello, how are you?"
        }
    ],
    "top_p": 1,
    "top_k": 40,
    "presence_penalty": 0,
    "frequency_penalty": 0
}
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

SDK

Install the Tensormesh Python SDK (pip install tensormesh), then:

from tensormesh import Tensormesh
from tensormesh.types import ChatMessage

with Tensormesh(inference_api_key="YOUR_API_KEY") as client:
    completion = client.inference.serverless.chat.completions.create(
        model="MiniMaxAI/MiniMax-M2.5",
        messages=[
            ChatMessage(role="user", content="Hello, how are you?"),
        ],
    )

print(completion.choices[0].message.content)

For the full model list and per-model pricing, go to Deploy → Serverless in the dashboard.

---

5. Enable External Storage (Optional)

By default, the KV cache only lasts for a single session. External Storage persists your cache across sessions and users — so repeated system prompts and shared context stay warm and cost nothing on return visits.

1. Go to Storage

   Navigate to Operations → Storage in the sidebar.

2. Choose a Plan

   Subscribe to a Bronze, Silver, or Gold plan depending on your cache volume needs. Billing starts immediately and you can upgrade or downgrade at any time.

See External Storage for a full breakdown of plan tiers and how persistent caching affects your costs.

---

Next Steps

Serverless Inference

Full model catalog, per-token pricing, and capability details.

Pricing Overview

How $0 cached tokens work and how to structure prompts to maximize savings.

External Storage

Plan tiers, usage monitoring, and how persistent caching affects your costs.

Account & API Keys

Manage your API keys, notification preferences, and profile settings.