Providers · Getting started

Free Models

Several cloud providers offer free API tiers that work out of the box with Manifest. No credit card required to get started.

Why use free models

Free models are useful for bootstrapping your agent setup, testing routing strategies, and keeping costs low on lightweight tasks. Manifest lets you combine free and paid providers in the same routing config, so you can start for free and scale progressively.

  • Start without a credit card
  • Use as a fallback
  • Test before committing
  • Offload simple tasks

How to connect a free model

1

Get a free API key from the provider

Find the provider you're interested in below and click "Get API key" to go to their website and generate a free API key.

2

Sign in to Manifest

Log in to your Manifest account and set up your agent. Don't have an account yet? Sign up for free . Skip this step if you're already logged in.

3

Click "Connect" and paste your key

Click the "Connect" button on the provider card below. Manifest opens with the provider already configured. Paste your API key, save, and the free models show up in your routing options.

Up to 1,000 calls/month No credit card required
Base URL: https://api.cohere.ai/compatibility/v1
Trial keys cannot be used for production or commercial workloads. Data may be used for training.
Model Name Context Max Output Modality Rate Limit
command-a-03-2025 256K 8K Text 20 req / min
command-a-reasoning-08-2025 256K 32K Text 20 req / min
250K TPM (Tokens/Minute) shared across models No credit card required
Base URL: https://generativelanguage.googleapis.com/v1beta/openai/
Rate limits apply per Google Cloud project, not per API key. On the free tier, prompts and responses may be used to improve Google products.
Model Name Context Max Output Modality Rate Limit
gemini-2.5-pro 1M 64K Text 5 req / min
gemini-2.5-flash 1M 64K Text 10 req / min
gemini-2.5-flash-lite 1M 64K Text 15 req / min
gemini-3-flash-preview 1M 64K Text Preview limits
gemini-3.1-flash-lite-preview 1M 64K Text Preview limits
No credit card required
Base URL: https://api.kilo.ai/api/gateway
Prompts and outputs are logged on free models to improve provider products.
Model Name Context Max Output Modality Rate Limit
qwen/qwen3.6-plus:free 1M 65K Text / Image / Video ~200 req / hr
nvidia/nemotron-3-super-120b-a12b:free 262K 262K Text ~200 req / hr
stepfun/step-3.5-flash:free 256K 256K Text ~200 req / hr
corethink:free 78K 8K Text ~200 req / hr

Start routing for free

Connect a free provider, paste your key, and start routing in under a minute.

Get started