For agent builders · Free
How much does your AI agent cost per month?
AI agents make thousands of small paid calls — chat completions, tool invocations, embeddings. Estimate the monthly bill for the workload you actually run, and see which model would make the same agent cheaper without breaking it.
Estimate your AI bill, model by model.
Agents make thousands of small paid calls. Estimate your monthly bill, and see which model would let the same agent run for less.
| Model | $ / M input | $ / M output | Monthly | vs. current |
|---|---|---|---|---|
| GPT-5 nanoOpenAI | $0.05 | $0.40 | $65 | −99% |
| Mistral Small 3.1Mistral | $0.10 | $0.30 | $80 | −98% |
| Gemini 2.5 Flash-LiteGoogle | $0.10 | $0.40 | $90 | −98% |
| Qwen 2.5 72BAlibaba · OpenRouter | $0.40 | $0.40 | $240 | −95% |
| DeepSeek V3DeepSeek | $0.27 | $1.10 | $245 | −95% |
| GPT-5 miniOpenAI | $0.25 | $2.00 | $325 | −94% |
| Gemini 2.5 FlashGoogle | $0.30 | $2.50 | $400 | −92% |
| Llama 3.1 70BMeta · Together | $0.88 | $0.88 | $528 | −89% |
| Claude Haiku 4.5Anthropic | $1.00 | $5.00 | $1,000 | −80% |
| Mistral Large 3Mistral | $2.00 | $6.00 | $1,600 | −68% |
| GPT-5OpenAI | $1.25 | $10.00 | $1,625 | −68% |
| Gemini 2.5 ProGoogle | $1.25 | $10.00 | $1,625 | −68% |
| GPT-4.1OpenAI | $2.00 | $8.00 | $1,800 | −64% |
| Claude Sonnet 5Anthropic | $2.00 | $10.00 | $2,000 | −60% |
| Claude Sonnet 4.5Anthropic | $3.00 | $15.00 | $3,000 | −40% |
| Claude Opus 4.8Anthropic | $5.00 | $25.00 | $5,000 | +0% |
Prices reflect typical 2026 list pricing and may change. Verify with each provider before you commit to a budget.
Price alone doesn't tell you if a cheaper model can safely replace yours.
Read the agent budget guide →How the estimate is calculated
monthly cost = calls × input tokens × ($input / 1M) + calls × output tokens × ($output / 1M)
Worked example. At the default reference workload of 100,000 calls per month (5,000 input / 1,000 output tokens), Claude Sonnet 4.5 costs$3,000 per month at list price. The calculator applies the same formula to every model in the registry and ranks the results cheapest first.
Limitations
- The estimate is a planning estimate, not a bill: prompt caching, batching, free tiers, image token multipliers and negotiated enterprise rates are not modeled.
- Prices are published list prices in USD per 1M tokens; DeepSeek peak/off-peak differences are shown at the off-peak rate with a caveat.
- A cheaper model is not a better deal if it fails more tasks — compare cost per successful task via the cost-per-successful-task methodology.
- The calculator runs entirely in your browser; no workload is sent to or logged by Harpd.
Pricing source & data
List prices come from each provider's official pricing page and were last verified 2026-08-18. The same registry powers the LLM pricing table, themachine-readable dataset (/data/llm-pricing.json) and theHarpd evidence register. How the prices are collected and kept current:model pricing methodology.
AI agent cost, answered
How much does an AI agent cost per month?
A typical mid-volume agent (50k–500k paid calls per month, 5k input + 1k output tokens) costs $250–$6,000 on Claude Sonnet 4 — and roughly 1/10 of that on DeepSeek V3 or Llama 70B. Use the calculator above with your real numbers.
Why is the AI agent cost calculator different from the LLM one?
It is the same engine, but the default workload assumes more calls per month and a higher average token count — the shape of an agentic loop, not a single chat. You can override everything in the form.
How do I control agent spend, not just estimate it?
Estimation is the first step. In production, use per-agent budgets, allowlists, pre-settlement approval rules, and independent reconciliation. Read the x402 spending limits page for the protocol-level version.
What is the cheapest LLM for an agent in 2026?
For routing cheap calls (intent classification, extraction, RAG rerank), Llama 3.1 8B, Qwen 2.5 72B and GPT-4o mini are the safest cheap defaults. For planning and tool use, you usually need Sonnet 4 or GPT-4.1. Validate cost and quality on your real agent traces before switching.
Does prompt caching change the math?
Yes — Claude caches prompts at 90% off the input price, and OpenAI has its own caching tier. The calculator ignores caching to keep one clean list price; in production, caching can cut your bill by half on long-system-prompt agents.