Developer & API · Cost Calculator
What will it cost?
Estimate your monthly API bill across every general-purpose model. Includes long-context surcharges, , discounts, and , with the full calculation on every row.
$31.50/mo on GPT-6 Luna (cheapest)
$2,520/mo on Claude Fable 5.2 (top index)
1,500requests of 150,000 in + 12,000 out
Show the maths
- Input: 150,000 tokens × $0.10/1M = $0.015
- Output: 12,000 tokens × $0.50/1M = $0.006
- One request: $0.021 × 1,500 requests = $31.50 / month
100K-prompt rate applied
Show the maths
- Input: 150,000 tokens × $0.50/1M = $0.075
- Output: 12,000 tokens × $2.50/1M = $0.03
- Adjusted from base $0.10 / $0.50 per 1M
- One request: $0.11 × 1,500 requests = $157.50 / month
Show the maths
- Input: 150,000 tokens × $0.75/1M = $0.11
- Output: 12,000 tokens × $3.75/1M = $0.045
- One request: $0.16 × 1,500 requests = $236.25 / month
Show the maths
- Input: 150,000 tokens × $1.00/1M = $0.15
- Output: 12,000 tokens × $5.00/1M = $0.06
- One request: $0.21 × 1,500 requests = $315.00 / month
Show the maths
- Input: 150,000 tokens × $1.50/1M = $0.23
- Output: 12,000 tokens × $7.50/1M = $0.09
- One request: $0.32 × 1,500 requests = $472.50 / month
Output cap not published
Show the maths
- Input: 150,000 tokens × $2.00/1M = $0.30
- Output: 12,000 tokens × $6.00/1M = $0.072
- One request: $0.37 × 1,500 requests = $558.00 / month
Output cap not published
Show the maths
- Input: 150,000 tokens × $2.00/1M = $0.30
- Output: 12,000 tokens × $8.00/1M = $0.096
- One request: $0.40 × 1,500 requests = $594.00 / month
Show the maths
- Input: 150,000 tokens × $2.00/1M = $0.30
- Output: 12,000 tokens × $10.00/1M = $0.12
- One request: $0.42 × 1,500 requests = $630.00 / month
Show the maths
- Input: 150,000 tokens × $2.00/1M = $0.30
- Output: 12,000 tokens × $10.00/1M = $0.12
- One request: $0.42 × 1,500 requests = $630.00 / month
Show the maths
- Input: 150,000 tokens × $2.00/1M = $0.30
- Output: 12,000 tokens × $10.00/1M = $0.12
- One request: $0.42 × 1,500 requests = $630.00 / month
Show the maths
- Input: 150,000 tokens × $2.00/1M = $0.30
- Output: 12,000 tokens × $10.00/1M = $0.12
- One request: $0.42 × 1,500 requests = $630.00 / month
Show the maths
- Input: 150,000 tokens × $2.00/1M = $0.30
- Output: 12,000 tokens × $10.00/1M = $0.12
- One request: $0.42 × 1,500 requests = $630.00 / month
Show the maths
- Input: 150,000 tokens × $3.00/1M = $0.45
- Output: 12,000 tokens × $15.00/1M = $0.18
- One request: $0.63 × 1,500 requests = $945.00 / month
Show the maths
- Input: 150,000 tokens × $4.00/1M = $0.60
- Output: 12,000 tokens × $20.00/1M = $0.24
- One request: $0.84 × 1,500 requests = $1,260.00 / month
Show the maths
- Input: 150,000 tokens × $8.00/1M = $1.20
- Output: 12,000 tokens × $40.00/1M = $0.48
- One request: $1.68 × 1,500 requests = $2,520.00 / month
Show the maths
- Input: 150,000 tokens × $8.00/1M = $1.20
- Output: 12,000 tokens × $40.00/1M = $0.48
- One request: $1.68 × 1,500 requests = $2,520.00 / month
Show the maths
- Input: 150,000 tokens × $10.00/1M = $1.50
- Output: 12,000 tokens × $50.00/1M = $0.60
- One request: $2.10 × 1,500 requests = $3,150.00 / month
Included: OpenAI’s surcharge above 272K input tokens, Haiku 5.5’s higher rate above 100K prompt tokens, and Grok 4.7’s higher rate from 200K. Cache and batch apply each lab’s published discount when enabled. Excluded: tax, data-residency uplifts, tool fees, retries, and consumer app subscriptions.