AI chatbot cost calculator
Work out what an AI chatbot costs to run each month on each model, and roughly what it costs to build.
Free, runs in your browser, no sign-up. Updated 2026-10-25.
Result
5,000 conversations a month: from $5.78 a month on Claude Haiku 5.5 to $578 on gpt-6-astra. Build estimate $10,200 – $29,600 at OceanLab's default rates.
- Tokens / conversation
- 14,040
- Tokens / month
- 70.2M
- Build estimate
- $10,200 – $29,600
- Build time
- 3–7 weeks
| Model | Per conversation | Per month | Price checked |
|---|---|---|---|
| Claude Haiku 5.5Anthropic | $0.0012 | $5.78 | 2026-10-23 |
| gpt-6-lunaOpenAI | $0.0012 | $5.78 | 2026-10-23 |
| MiniMax M3.1-FlashMiniMax | $0.0016 | $7.76 | 2026-10-23 |
| gpt-5.6-lunaOpenAI | $0.0026 | $12.75 | 2026-10-23 |
| deepseek-flashDeepSeek | $0.0029 | $14.55 | 2026-10-23 |
| MiniMax M3MiniMax | $0.0033 | $16.74 | 2026-10-23 |
| Gemini 2.5 FlashGoogle | $0.0047 | $23.33 | 2026-10-23 |
| Gemini 3.8 FlashGoogle | $0.0087 | $43.31 | 2026-10-23 |
| gpt-5.4-miniOpenAI | $0.0096 | $47.81 | 2026-10-23 |
| deepseek-v4-proDeepSeek | $0.011 | $56.83 | 2026-10-23 |
| Claude Haiku 4.5Anthropic | $0.012 | $57.75 | 2026-10-23 |
| Gemini 2.5 ProGoogle | $0.019 | $94.69 | 2026-10-23 |
| Claude Sonnet 5.5Anthropic | $0.022 | $111 | 2026-10-23 |
| gpt-6.1-solOpenAI | $0.022 | $111 | 2026-10-23 |
| Gemini 4 ArgonGoogle | $0.022 | $111 | 2026-10-23 |
| Claude Sonnet 5Anthropic | $0.023 | $116 | 2026-10-23 |
| gpt-5.6-terraOpenAI | $0.026 | $127 | 2026-10-23 |
| Gemini 3.1 Pro PreviewGoogle | $0.026 | $127 | 2026-10-23 |
| Claude Opus 5.5Anthropic | $0.045 | $223 | 2026-10-23 |
| gpt-5.6-solOpenAI | $0.046 | $231 | 2026-10-23 |
| Claude Opus 5Anthropic | $0.058 | $289 | 2026-10-23 |
| Claude Fable 5.1Anthropic | $0.11 | $547 | 2026-10-23 |
| gpt-6-astraOpenAI | $0.12 | $578 | 2026-10-23 |
Assumptions
Every number the result depends on, and where it comes from. Change any value and the result updates.
| Assumption | Value | Source |
|---|---|---|
| Conversations per month | conversations | OceanLab planning assumption. Use your own traffic.Reviewed 2026-10-25 |
| User turns per conversation | turns | OceanLab planning assumption. Check your chat logs.Reviewed 2026-10-25 |
| System prompt + knowledge snippets (tokens) | tokens | OceanLab planning assumption. Paste your prompt into the token counter.Reviewed 2026-10-25 |
| User message (tokens) | tokens | OceanLab planning assumption: one or two sentences.Reviewed 2026-10-25 |
| Bot reply (tokens) | tokens | OceanLab planning assumption: a short paragraph.Reviewed 2026-10-25 |
| Share of system prompt served from cache | % | OceanLab planning assumption: the system prompt repeats on every turn. Set 0 if you do not use caching.Reviewed 2026-10-25 |
Send this estimate to OceanLab
Opens an email to OceanLab with this result and a link to your inputs. Nothing is sent until you press send, and there is no sign-up.
How this is calculated
Each user turn re-sends the system prompt and the conversation so far, so later turns carry more input than early ones. The system prompt is the part a prompt cache can serve.
Tokens per conversation are priced on every model at its published rates, then multiplied by conversations per month.
The optional build estimate uses the software development cost engine with login, the AI feature, an admin panel and one integration, at OceanLab's default rates.
Sources
- Anthropic API pricing · checked 2026-10-23
- OpenAI API pricing · checked 2026-10-23
- Google API pricing · checked 2026-10-23
- DeepSeek API pricing · checked 2026-10-23
- MiniMax API pricing · checked 2026-10-23
Questions about this tool
Why do long conversations cost more?
Each reply re-sends the conversation so far, so later turns carry more input tokens than early ones.
What does the build estimate include?
Login, the AI feature, an admin panel and one integration, using the same editable hour ranges and rates as the software development cost calculator.
Which model should I use?
The table ranks models by cost for your traffic. Test the cheaper ones on real conversations before deciding; the model picker can help you shortlist.
Is anything I enter sent anywhere?
No. The tool runs in your browser and there is no sign-up. Nothing leaves the page unless you choose to email your result to OceanLab.
Other free tools
OceanLab product builds like this
Products OceanLab designed and built. Each case study covers the screens, the scope and the rules it was built for.
Pahana - Trilingual AI Support Agent with Safe Human Handoff
Designed and built the staff console for a trilingual AI support agent at a Colombo telecom operator: a dashboard of containment and satisfaction, every conversation with its tool calls and guardrail events, a live monitor where team leads take over a chat, and a handoff queue that makes sure no customer passed to a person is lost.
Nakhuda - Bilingual AI Shopping Assistant Grounded in the Product Catalogue
Designed and built a clickable console for an Arabic and English AI shopping assistant at a Kuwait City electronics retailer: every product claim cited to a catalogue field, compatibility decided by fixed rules, nothing added to a cart without the shopper's tap, and a review queue for every suspected invented fact.
Brújula - AI Policy Assistant That Cites the Clause and Escalates the Risky Questions
Designed and built a clickable internal policy assistant for a Guayaquil shrimp farmer, processor and exporter: staff ask in Spanish or English and get answers built only from company policies, each statement linked to its clause and version, while gift approvals, conflicts and possible breaches go to Compliance, HR or the confidential Speak Up channel instead of being answered.
Riffle - AI Ticket Triage Layer That Catches Product Safety Reports
Designed and built a clickable AI triage layer for a Taipei consumer electronics brand: it classifies every new Zendesk and Freshdesk ticket, masks personal data, routes it to the right queue, sends low-confidence tickets to a review queue and pushes possible battery, heat and fire reports to an on-call product safety team.
