What does a support chatbot cost per month with an AI API?

On current list prices, GPT-6 Luna is the cheapest model we track for this workload at $35.00 per month, while the most expensive costs $3,500 — a 100× spread. Every model’s exact figure is in the table above, verified November 7, 2026.

Which AI model is cheapest for a support chatbot?

GPT-6 Luna charges $0.10 input / $0.50 per 1M tokens, which works out to $0.0003 per request and $35.00 per month for this workload. Check the capability column too — the cheapest models can score lower on benchmarks, and a mid-priced model is often the better deal.

How is the monthly cost calculated?

Each request splits the 1,500 input tokens into fresh and cached tokens, multiplies each by the model’s rate, then adds 400 output tokens at the output rate: cost = (fresh input × input rate + cached input × cached rate + output × output rate) ÷ 1,000,000. The per-request cost is then multiplied by 100,000 requests per month.

How accurate is this estimate?

It uses each provider’s standard list prices, verified November 7, 2026, including published cached-input rates and long-context thresholds. It excludes cache-write surcharges, batch discounts, taxes and volume deals — heavy users can usually negotiate below list.

Support chatbot: AI API cost per month

100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each.

Requests

100,000

per month

Tokens per request

2K in / 0K out

190M tokens per month

Cheapest model

$35.00

GPT-6 Luna per month

Priciest model

$3,500

Claude Fable 5.1 per month

What support chatbot costs on every model

Model	Per request	Per month	Capability (ECI)
GPT-6 Luna$0.10 in / $0.50 out per 1M tokens	$0.0003	$35.00	156.3
Claude Haiku 5.5$0.10 in / $0.50 out per 1M tokens	$0.0003	$35.00	159.0
GPT-5.6 Luna$0.20 in / $1.20 out per 1M tokens	$0.0008	$78.00	156.3
DeepSeek V4.1 Flash$0.30 in / $1.20 out per 1M tokens	$0.0009	$93.00	155.6
Gemini 3.5 Flash-Lite$0.30 in / $2.50 out per 1M tokens	$0.0014	$145.00	145.2
Gemini 2.5 Flash$0.30 in / $2.50 out per 1M tokens	$0.0014	$145.00	140.8
Gemini 3.8 Flash$0.75 in / $3.75 out per 1M tokens	$0.0026	$262.50	157.2
Gemini 3.6 Flash$0.75 in / $3.75 out per 1M tokens	$0.0026	$262.50	154.2
Grok 4.3$1.25 in / $2.50 out per 1M tokens	$0.0029	$287.50	—
GPT-6.1 Terra$1.00 in / $5.00 out per 1M tokens	$0.0035	$350.00	—
Claude Haiku 4.5$1.00 in / $5.00 out per 1M tokens	$0.0035	$350.00	142.4
DeepSeek V4 Pro$1.32 in / $3.96 out per 1M tokens	$0.0036	$356.40	155.3
Grok 4.7$2.00 in / $6.00 out per 1M tokens	$0.0054	$540.00	154.4
Grok 4.6$2.00 in / $6.00 out per 1M tokens	$0.0054	$540.00	156.3
Gemini 2.5 Pro$1.25 in / $10.00 out per 1M tokens	$0.0059	$587.50	145.3
GPT-6 Sol$2.00 in / $10.00 out per 1M tokens	$0.0070	$700.00	162.6
GPT-6.1 Sol$2.00 in / $10.00 out per 1M tokens	$0.0070	$700.00	166.3
Claude Sonnet 5.5$2.00 in / $10.00 out per 1M tokens	$0.0070	$700.00	164.4
Claude Sonnet 5$2.00 in / $10.00 out per 1M tokens	$0.0070	$700.00	156.4
Gemini 4 Argon$2.00 in / $10.00 out per 1M tokens	$0.0070	$700.00	164.6
GPT-5.6 Terra$2.00 in / $12.00 out per 1M tokens	$0.0078	$780.00	159.4
Gemini 3.1 Pro$2.00 in / $12.00 out per 1M tokens	$0.0078	$780.00	154.7
GPT-5.6 Sol$4.00 in / $20.00 out per 1M tokens	$0.01	$1,400	161.7
Claude Opus 5.5$4.00 in / $20.00 out per 1M tokens	$0.01	$1,400	166.8
Claude Opus 5$5.00 in / $25.00 out per 1M tokens	$0.02	$1,750	162.6
GPT-6 Astra$10.00 in / $50.00 out per 1M tokens	$0.04	$3,500	166.4
Claude Fable 5.1$10.00 in / $50.00 out per 1M tokens	$0.04	$3,500	164.7

ECI = Epoch Capabilities Index (Epoch AI, CC BY 4.0). A dash means the model is not yet rated. See the full leaderboard.

How this estimate works

The workload above — 100,000 requests a month, 1,500 input tokens and 400 output tokens each— is run through every model’s official price list. Where a provider publishes a long-context threshold and this workload’s prompts exceed it, the higher long-context rate applies automatically.

Run your own numbers in the cost calculator, or see the full methodology. If two models are close in price, compare them directly: GPT-6 Luna vs Claude Haiku 5.5.

Other workload estimates

Frequently asked questions

What does a support chatbot cost per month with an AI API?: On current list prices, GPT-6 Luna is the cheapest model we track for this workload at $35.00 per month, while the most expensive costs $3,500 — a 100× spread. Every model’s exact figure is in the table above, verified November 7, 2026.
Which AI model is cheapest for a support chatbot?: GPT-6 Luna charges $0.10 input / $0.50 per 1M tokens, which works out to $0.0003 per request and $35.00 per month for this workload. Check the capability column too — the cheapest models can score lower on benchmarks, and a mid-priced model is often the better deal.
How is the monthly cost calculated?: Each request splits the 1,500 input tokens into fresh and cached tokens, multiplies each by the model’s rate, then adds 400 output tokens at the output rate: cost = (fresh input × input rate + cached input × cached rate + output × output rate) ÷ 1,000,000. The per-request cost is then multiplied by 100,000 requests per month.
How accurate is this estimate?: It uses each provider’s standard list prices, verified November 7, 2026, including published cached-input rates and long-context thresholds. It excludes cache-write surcharges, batch discounts, taxes and volume deals — heavy users can usually negotiate below list.