Supported Models

Pencel connects to three AI providers: Anthropic, Google, and OpenAI. Each model has different strengths, speeds, and costs. You choose which model an agent uses, and you can mix models across agents in the same workspace.

Available Models

These are the models you can pick from directly in the model selector:

Provider	Model	Model ID	Best For	Relative Cost
Anthropic	Claude Opus 5	claude-opus-5	Hardest reasoning, nuanced writing, multi-step analysis	$$$
Anthropic	Claude Sonnet 5	claude-sonnet-5	Balanced quality and speed — a good default for most work	$$
OpenAI	GPT-5.6 Sol	gpt-5.6-sol	Strong general-purpose reasoning, broad knowledge	$$$
OpenAI	GPT-5.6 Terra	gpt-5.6-terra	Balanced general-purpose work at a lower cost than Sol	$$
Google	Gemini 2.5 Flash	gemini-2.5-flash	Fast routine tasks, research, summarization	$
Google	Gemini 2.5 Pro	gemini-2.5-pro	Complex analysis, long context windows, detailed reports	$$

INFO

New agents are created with no preferred model. An agent without one uses the workspace default set in Settings → General, and if that is also unset, Pencel picks a balanced model from the providers you have available. Set Preferred Model on an agent to pin it to a specific model.

Managed vs. BYOK availability

On a Pro Desktop subscription, every model in the table above is available through Pencel-managed credits with no API key required.

On the Free plan, every model is BYOK — add your own provider key in Settings → LLM Providers.

The model picker also offers two managed modes on a subscription: Pencel Auto (cost-optimized — Pencel picks the model) and Pencel Private (zero data retention). See Accounts & sign-in.

Choosing the Right Model

Pick a model based on what the agent needs to do, not on the provider name.

Use Claude Opus 5 when:

• The task requires careful, nuanced writing (executive briefings, customer communications)
• The agent needs to follow complex, multi-layered instructions
• Accuracy is more important than speed
• The output is customer-facing or goes to leadership

Use Claude Sonnet 5 (a good default) when:

• You want the best balance of quality, speed, and cost
• The task is moderately complex (reports, analysis, multi-step workflows)
• You are unsure which model to pick

Use GPT-5.6 Sol or GPT-5.6 Terra when:

• You want strong general-purpose reasoning and broad world knowledge
• Choose Sol for the hardest tasks, and Terra for everyday work at a lower cost

Use Gemini 2.5 Pro when:

• You need to analyze very long documents (up to ~1M tokens of context)
• The task requires deep analysis at a lower input cost than Claude Opus or GPT-5.6 Sol
• You want a balance between quality and price

Use Gemini 2.5 Flash when:

• The task is simple or routine (classification, extraction, formatting, high-volume research)
• You want the lowest possible cost
• Speed matters more than depth

Let Pencel choose for you

If you do not want to pick a model per task, use Pencel Auto (a managed mode on a subscription): Pencel routes each turn to the most cost-effective capable model, and the chat message always shows which one actually ran.

TIP

A common pattern is to use a cheaper model for data gathering steps and a premium model for the final synthesis step. You can assign different agents to different workflow steps, each with their own preferred model.

Setting a Model for an Agent

1. Open the agent you want to configure (or create a new one).
2. Find the Preferred Model field.
3. Select a model from the dropdown.
4. Save the agent.

Every time this agent runs — whether in chat or as part of a workflow — it uses the selected model.

How Model Routing Works

Pencel automatically routes requests to the right provider based on the model you selected. You don't need to think about API endpoints or provider-specific settings. Just pick the model and go.

INFO

Each provider requires its own API key. Set up your keys in Settings before using models from that provider. You only need keys for the providers you actually use.

Circuit Breakers and Provider Health

Pencel monitors the health of each provider in real time. If a provider starts returning errors (network issues, rate limits, outages), the circuit breaker activates:

• Closed (healthy) — Requests flow normally.
• Open (unavailable) — The provider is temporarily disabled. Pencel stops sending requests to avoid cascading failures.
• Half-open (testing) — Pencel periodically tests whether the provider has recovered.

You can see the current status of all providers in the diagnostics view on the Jobs page (/jobs).

WARNING

When a provider's circuit breaker is open, agents using that provider's models cannot run. They will wait for the provider to recover. Pencel does not automatically fall back to a different provider — the agent uses the model you assigned.

Cost Tracking

Every model call is tracked in the Cost & Usage section of Settings. You can see:

• Per-run costs — How much each workflow run consumed
• Per-date costs — Daily spending across all agents
• Input vs. output tokens — Input tokens (what you send) are cheaper than output tokens (what the model generates)

The relative cost column in the table above gives a rough guide:

Symbol	Meaning
$	Low cost — suitable for high-volume use
$$	Moderate cost — good for important tasks
$$$	Premium cost — reserve for high-value outputs

TIP

If your monthly costs are climbing, the Cost & Usage section is the best place to start. Look for agents running expensive models on routine tasks, and consider switching them to a cheaper alternative.

API Key Requirements

Provider	Where to Get a Key
Anthropic	console.anthropic.com
Google	aistudio.google.com
OpenAI	platform.openai.com

Keys are stored securely in your operating system's keychain. They never leave your machine except to authenticate with the respective provider. See Settings for setup instructions.