AI Agent Cost Calculator

Calculate real operational costs for AI agents. Compare models, estimate API costs, and understand the economics of running AI systems at scale.

Technology

Parameters

User Message Length
30 tokens
10
750
1,500
2,250
3,000
Agent Response Length
100 tokens
10
1,250
2,500
3,750
5,000
System Prompt Length
1,000 tokens
0
2,500
5,000
7,500
10,000
Context Length (RAG)
2,000 tokens
0
5,000
10,000
15,000
20,000
Conversation Length
2 messages
1
25
50
75
100

Cost Breakdown

$0.0009/message
$0.0018/conversation

Cost breakdown (per message)

System Prompt
$0.0003(27%)
Context (RAG)
$0.0005(54%)
User Message
$0.0000(1%)
Agent Response
$0.0002(16%)
Message History
$0.0000(2%)

Model Specifications

Input Cost
$0.25/1M tokens
Output Cost
$1.50/1M tokens
Speed
470 tokens/s
Intelligence Index
30
Context Window
1,000K tokens
TTFT
500ms
Calculated using Gemini 3.1 Flash Lite

Want to know the full cost of your AI agent?

API pricing doesn't cover development, testing, infrastructure, or optimization. Share what you're building and we'll map the complete cost.

Built with♥bySoftcery

Complete LLM Model Comparison

Compare pricing, performance, and capabilities across 29+ LLM models from OpenAI, Anthropic, Google, DeepSeek, Meta, and xAI. Use this comprehensive comparison to choose the best model for your AI agent based on cost, speed, intelligence, and reasoning capabilities.

Model Provider Input Price
(1M tokens)		 Output Price
(1M tokens)		 Speed
(tokens/sec)		 Intelligence
(index)		 Context Window
(tokens)		 TTFT
(ms)		 Reasoning Max Thinking
(tokens)		 Link
GPT-5 OpenAI $1.25 $10.00 84.3
(84.3 thinking)
45
(45 thinking)
400,000 460
(85,850 thinking)
✓ 128,000 Pricing
GPT-5 mini OpenAI $0.25 $2.00 67.6
(67.6 thinking)
41
(41 thinking)
400,000 800
(110,670 thinking)
✓ 128,000 Pricing
GPT-5 nano OpenAI $0.05 $0.40 145.3
(145.3 thinking)
27
(27 thinking)
400,000 900
(100,270 thinking)
✓ 128,000 Pricing
GPT-5.4 OpenAI $2.50 $15.00 85.7
(85.7 thinking)
57
(57 thinking)
1,100,000 1,500
(185,050 thinking)
✓ 128,000 Pricing
GPT-5.4 mini OpenAI $0.75 $4.50 173.9
(173.9 thinking)
49
(49 thinking)
400,000 800
(4,410 thinking)
✓ 128,000 Pricing
GPT-5.4 nano OpenAI $0.20 $1.25 160.2
(160.2 thinking)
44
(44 thinking)
400,000 500
(3,870 thinking)
✓ 128,000 Pricing
GPT-5.5 OpenAI $5.00 $30.00 73.2
(73.2 thinking)
60
(60 thinking)
922,000 2,000
(67,250 thinking)
✓ 128,000 Pricing
GPT-5.5 Pro OpenAI $30.00 $180.00 65
(65 thinking)
62
(62 thinking)
922,000 3,000
(80,000 thinking)
✓ 128,000 Pricing
Claude Haiku 3.5 Anthropic $0.80 $4.00 80 19 200,000 700 — — Pricing
Claude Haiku 4.5 Anthropic $1.00 $5.00 150
(150 thinking)
38
(47 thinking)
200,000 500
(3,500 thinking)
✓ 128,000 Pricing
Claude Opus 4.1 Anthropic $15.00 $75.00 44.3 45 200,000 2,820 — — Pricing
Claude Opus 4.5 Anthropic $5.00 $25.00 45.3
(45.3 thinking)
43
(50 thinking)
200,000 1,030
(14,000 thinking)
✓ 64,000 Pricing
Claude Opus 4.6 Anthropic $5.00 $25.00 38.7
(38.7 thinking)
46
(53 thinking)
1,000,000 1,620
(18,000 thinking)
✓ 64,000 Pricing
Claude Opus 4.7 Anthropic $5.00 $25.00 47.2
(47.2 thinking)
57
(57 thinking)
1,000,000 1,500
(22,040 thinking)
✓ 64,000 Pricing
Claude Sonnet 4.5 Anthropic $3.00 $15.00 50
(50 thinking)
42
(49 thinking)
1,000,000 1,400
(10,000 thinking)
✓ 64,000 Pricing
Claude Sonnet 4.6 Anthropic $3.00 $15.00 45.2
(45.2 thinking)
44
(50 thinking)
1,000,000 1,190
(12,000 thinking)
✓ 64,000 Pricing
Gemini 2.5 Flash Google $0.30 $2.50 206.9
(206.9 thinking)
21
(38 thinking)
1,000,000 660
(6,000 thinking)
✓ 24,576 Pricing
Gemini 2.5 Flash Lite Google $0.10 $0.40 256.4 13 1,000,000 1,570 — — Pricing
Gemini 2.5 Pro Google $1.25 $10.00 117.1
(117.1 thinking)
35
(50 thinking)
1,000,000 4,000
(27,520 thinking)
✓ 24,576 Pricing
Gemini 3 Flash Google $0.50 $3.00 183.9
(183.9 thinking)
35
(50 thinking)
1,000,000 980
(6,000 thinking)
✓ 24,576 Pricing
Gemini 3.1 Flash Lite Google $0.25 $1.50 470 30 1,000,000 500 — — Pricing
Gemini 3.1 Pro Google $2.00 $12.00 80
(80 thinking)
57
(60 thinking)
1,000,000 2,000
(12,000 thinking)
✓ 32,768 Pricing
DeepSeek V4 Flash DeepSeek $0.14 $0.28 79.6
(79.6 thinking)
47
(47 thinking)
1,000,000 1,140
(6,000 thinking)
✓ 64,000 Pricing
DeepSeek V4 Pro DeepSeek $0.43 $0.87 33.9
(33.9 thinking)
52
(52 thinking)
1,000,000 1,860
(1,860 thinking)
✓ 64,000 Pricing
Grok 4 xAI $4.25 $21.25 43.9
(43.9 thinking)
42
(42 thinking)
256,000 1,340
(18,370 thinking)
✓ 128,000 Pricing
Grok 4.1 Fast xAI $0.20 $0.50 104.8 24 2,000,000 610 — — Pricing
Grok 4.3 xAI $1.25 $2.50 104.2
(104.2 thinking)
53
(53 thinking)
1,000,000 1,500
(32,360 thinking)
✓ 128,000 Pricing
Llama 3.3 70B Meta $0.88 $0.88 276 24 128,000 400 — — Pricing
Llama 4 Maverick Meta $0.35 $0.85 111 18 1,000,000 1,030 — — Pricing
Llama 4 Scout Meta $0.17 $0.66 141.6 14 10,000,000 800 — — Pricing
Mistral Large 3 Mistral $0.50 $1.50 50.7 23 256,000 1,080 — — Pricing
Mistral Medium 3.5 Mistral $1.50 $7.50 158.8
(158.8 thinking)
39
(45 thinking)
256,000 1,750
(8,000 thinking)
✓ 32,000 Pricing
Mistral Small 4 Mistral $0.15 $0.60 166.8
(166.8 thinking)
28
(28 thinking)
256,000 760
(5,000 thinking)
✓ 32,000 Pricing

TTFT: Time to First Token (latency before model starts generating)

TTFAT: Time to First Answer Token (latency before model starts answering, after reasoning)

Intelligence Index: Relative capability score based on benchmark performance (higher is better)

Thinking/Reasoning: Models that show their reasoning process before answering (values in parentheses show performance when reasoning is enabled)

All pricing is per million tokens. Performance metrics are approximate and may vary based on query complexity and API load.

Last updated: May 5, 2026