Skip to main content
See also: Breaking Down Tasks for AI for practical advice on model selection and structuring your tasks.
Cellm supports hosted models from Anthropic, AWS, Azure, DeepSeek, Google, OpenAI, Mistral, and any OpenAI-compatible cloud provider. These models are more powerful than anything you can run on your own computer.
AI providers use data from free tiers and even some consumer plans to improve their models. Review each provider’s data usage policies before sending sensitive information. For data privacy guarantees, consider local models or Cellm’s subscription plans.

Model sizes

We split hosted models into three tiers based on their size and capabilities, balancing speed, intelligence, and problem-solving skills:
Small ModelMedium ModelLarge Model
Speed
Intelligence
World Knowledge
Recommended modelGemini 2.5 Flash LiteGemini 2.5 FlashClaude Sonnet 4.5

Provider setup

To use hosted models, you need an API key from your chosen provider. Below are setup instructions for the most popular providers. Mistral offers a generous free tier with access to powerful models.
1

Create an account

Go to console.mistral.ai and sign up. Check your inbox and verify your email.
2

Select a plan

Choose between “Experiment” (free tier) or “Scale” (pay-as-you-go). The free Experiment tier offers generous usage limits.
3

Activate billing

Navigate to your Organization settings at admin.mistral.ai and add payment information. This activates your API keys even if you’re using the free tier.
4

Create API key

Under the “Workspace” tab, go to “API Keys” and click “Create new key”. Give your key a name and set an expiration date, then click “Create”.
5

Save your key

Copy the key immediately and store it securely - you won’t be able to see it again.
6

Configure in Cellm

In Excel, open Cellm’s ribbon menu, select the mistral provider, click the provider icon, and paste your API key. Try a model like:
Mistral example
=PROMPTMODEL("mistral/mistral-small-latest", "Summarize customer feedback", A1)
And go nuts.
Mistral’s free tier is excellent for getting started - you get significant usage before incurring costs.

OpenAI

OpenAI provides access to GPT models, including GPT-4o and GPT-4o-mini.
1

Create an account

Go to platform.openai.com and sign up or sign in.
2

Add payment method

OpenAI requires a payment method to use the API. Click “Start building” and add your payment details to purchase API credits.
3

Create API key

Click your profile icon in the top-right, select “View API keys”, then click “Create new secret key”. Copy the key immediately - you won’t be able to see it again.
4

Configure in Cellm

In Excel, open Cellm’s ribbon menu, select the openai provider, click the provider icon, and paste your API key. Try a model like:
OpenAI example
=PROMPTMODEL("openai/gpt-4o-mini", "Classify sentiment as positive, neutral, or negative", A1)
OpenAI no longer provides free trial credits, so you’ll need to add funds before making API calls.

Google Gemini

Google Gemini offers powerful AI models with a generous free tier.
1

Access Google AI Studio

Go to ai.google.dev and sign in with your Google account.
2

Get API key

Click “Get API key” in the left sidebar, then click “Create API key”. Select an existing Google Cloud project or create a new one.
3

Save your key

Copy the generated API key and store it securely.
4

Configure in Cellm

In Excel, open Cellm’s ribbon menu, select the gemini provider, click the provider icon, and paste your API key. Try a model like:
Gemini example
=PROMPTMODEL("gemini/gemini-2.5-flash", "Extract person names from text", A1)
Google Gemini offers 1,500 requests per day on the free tier, making it excellent for testing and development.

Anthropic (Claude)

Anthropic provides Claude models, known for their strong reasoning capabilities.
1

Create an account

Go to console.anthropic.com and sign up. Click “Start Building” to access the console.
2

Set up billing

Add a payment method to purchase credits. Anthropic offers free credits for new accounts.
3

Create API key

Navigate to “API Keys” in the left sidebar and click “Create Key”. Give your key a name and click “Create”.
4

Save immediately

Copy the key immediately - it’s only shown once. Store it in a password manager.
5

Configure in Cellm

In Excel, open Cellm’s ribbon menu, select the anthropic provider, click the provider icon, and paste your API key. Try a model like:
Claude example
=PROMPTMODEL("anthropic/claude-sonnet-4.5", "Analyze customer feedback", A1)

DeepSeek

DeepSeek provides cost-effective AI models with OpenAI-compatible API.
1

Create an account

Go to platform.deepseek.com and sign up.
2

Generate API key

Navigate to the “API Keys” section and click “Create new API key”. Optionally assign a name to your key.
3

Save your key

Copy the key immediately and store it securely - it won’t be displayed again.
4

Configure in Cellm

In Excel, open Cellm’s ribbon menu, select the deepseek provider (or openaicompatible with base address https://api.deepseek.com), click the provider icon, and paste your API key. Try a model like:
DeepSeek example
=PROMPTMODEL("deepseek/deepseek-chat", "Summarize text", A1)

Other OpenAI-compatible providers

You can use any provider compatible with OpenAI’s API format, including OpenRouter or LiteLLM.
Local models running on localhost are free to use. However, a Cellm subscription is required to access online APIs like openrouter.com or cerebras.ai. See Cellm’s subscription plans for details.
1

Choose OpenAI Compatible provider

In Cellm’s ribbon menu, select the OpenAI Compatible provider.
2

Configure endpoint

Click the provider icon to open settings. Enter the API endpoint URL and your API key.
3

Test the connection

Enter a model name and try a test prompt to verify the configuration works.

Best practices

  • Store API keys securely: Use a password manager or environment variables
  • Monitor usage: Check your provider dashboard regularly to track costs
  • Start small: Begin with smaller, cheaper models and scale up as needed
  • Test thoroughly: Verify API setup with a few test prompts before processing large datasets