Pricing

Use a BlockRun API key for account billing: account setup guide. Register at user.blockrun.ai, create a key and add credits. Account mode needs no payment wallet; wallet billing supports Solana first, then Base.

Pay-Per-Action

Pay for model and tool usage with account credits or wallet USDC through x402 on Solana or Base. Check the model catalog and account dashboard for current prices and limits.

In account mode, local cost totals and max-spend limits use estimates. The account dashboard is authoritative for billed usage and remaining credits.

Free Tier

Franklin always includes a free tier with unlimited usage — seven models, no wallet:

• Nemotron 3 Nano 30B (NVIDIA — the fastest free model)
• Nemotron 3.5 Lightning (NVIDIA, 1M context)
• Nemotron 3 Nano Omni (NVIDIA, vision)
• Nemotron 3 Ultra 550B (NVIDIA, 1M context)
• Llama 3.2 11B Vision (NVIDIA)
• Cohere North Mini Code (256K context, coding)
• Poolside Laguna XS 2.1 (coding)

Smart Router Cost Optimization

The Smart Router automatically optimizes cost by selecting the cheapest model capable of handling the current task. For simple tasks (file reads, shell commands), it routes to free or low-cost models. For complex reasoning, it routes to premium models.

You can override this by pinning a specific model:

# Use a specific model
franklin -m claude-sonnet-4-20250514

# See all available models and their cost tiers
franklin models

Cost Tracking

Franklin tracks every cent spent. Use these tools to monitor your usage:

In-session

# Inside a Franklin session
/cost

Shows the running cost of the current session, broken down by model.

From the command line

franklin insights

Displays aggregated spending analytics: total cost, cost per model, cost per session, and trends over time.

Web panel

franklin panel

Opens a web dashboard with charts showing spending history, model usage breakdown, and cost projections.

What $1 Gets You

Concrete token budgets for $1 in USDC:

• GPT-5.4 — ~400K input tokens
• DeepSeek V4 Flash — ~5M input tokens
• Gemini 2.5 Flash Lite — ~10M input tokens
• GPT Image 1 — ~50 images
• Exa neural search — ~40 queries
• NVIDIA free models — Unlimited (FREE)

Example Session Costs

Approximate costs for common operations (varies by model and context size):

• Simple question — $0.001 – $0.005
• File edit with tool calls — $0.005 – $0.02
• Complex multi-step task — $0.02 – $0.10
• Full coding session (30 min) — $0.10 – $0.50