💰 AI Agent Cost Calculator

How the math works

Two billing models drive every total below:

• Per-token billing (API + OpenClaw): messages × tokens × per-token rate. Costs scale linearly with usage; cheap at low volume, can run high at heavy usage.
• Subscription (Cowork, ChatGPT, Claude Code Pro/Max): flat per-seat fee with usage caps. Cheap above a usage threshold; potentially wasted money below it.

Published rates (USD per 1M tokens):

• Anthropic (verified 2026-09-06) — Haiku 4.5 $1/$5 · Sonnet 5 $2/$10 · Sonnet 4.6 $3/$15 · Opus 4.6 / 4.7 / 4.8 / 5 $5/$25 · Opus 5.5 $4/$20 · Fable 5.1 / Mythos 5.1 / Fable 5 $10/$50 (most capable). Opus 5.5 is the current flagship — 1M-token context as both default and maximum, 128k max output, thinking on by default, at the same $4/$20 as Opus 4.8. Opus 4.7, Opus 4.8, Opus 5.5, Opus 5, Fable 5.1, Mythos 5.1, Fable 5 scale output by the effort multiplier (low 1× → max 7×).
• OpenAI (verified 2026-08-22) — GPT-5.6 Sol $4/$20 · Terra $2.50/$15 · Luna $1/$6 · GPT-5.5 $4/$20 · GPT-5.4 $2.50/$10 · GPT-5.4 mini $0.30/$1.20 · GPT-5.4-Cyber $12/$60 · o4-mini $1.50/$8. GPT-5.6 Sol dropped from $5/$30 to $4/$20 on August 21, 2026 — 20% off input, 33% off output. That is the same price as GPT-5.5, so GPT-5.5 is now strictly dominated: identical rates, older model. The Ultrafast tier for Sol has no published pricing and is not modelled here.
• Google — Gemini 3.1 Flash $0.30/$1.20 · Gemini 3.1 Pro $3.50/$15 (newest, Apr 2026) · Gemini 2.5 Flash $0.20/$0.80 · Gemini 2.5 Pro $2.50/$12 · Gemma 2 9B local-only (Ollama)
• Open weights via API — Kimi K3 $3/$15 (Moonshot 2.8T flagship, Jul 2026 — premium open-weight, priced like Sonnet 4.6 and above Sonnet 5's $2/$10, not a budget tier) · Kimi K2 $0.60/$1.80 · Qwen 3.5 72B $0.40/$1.20 (typical OpenRouter / Together pricing)
• Open weights local (Ollama + GPU) — Qwen 3.6 35B MoE, Gemma 2 9B: $0/token, ~$8–18/mo electricity for typical home GPU usage. No data ever leaves your network.
• Subscriptions — Cowork Pro ~$20/user · Business ~$30/user · ChatGPT Plus $20 · Pro $200 · Team $30/seat · OpenClaw self-hosted $0–5/mo

Effort level multiplier (Opus 4.7, Opus 4.8, Opus 5.5, Opus 5, Fable 5.1, Mythos 5.1, Fable 5, GPT-6 Sol, GPT-6 Luna, GPT-6 Astra, Gemini 3.8 Flash): low 1× · medium 1.3× · high 2× · xhigh 3.5× · max 7×. Multiplier applies to output tokens (where the extra reasoning work shows up).

What this calculator does not include

• Prompt-cache discounts — can cut input cost 50–90% for stable system prompts (see our cost optimization guide)
• Batch API discounts — Anthropic offers 50% off for batch jobs
• Enterprise volume discounts — negotiate above ~$50K/year spend
• Tool-call costs (web search, file uploads) — usually small but vary by platform
• Local GPU electricity if running NemoClaw/Ollama (~$5–20/mo for typical home use)

For most users, real-world spend lands within ±25% of the estimate. The calculator's main job is to spot order-of-magnitude differences between platforms.

Common scenarios