MODEL SELECTION / API WORKBENCH

AI API Cost Calculator

Know your usage. Choose your model.

One workload, different bills. Scale a single request to a month and compare model cost with task performance.

↗ Pricing sources & check dates included◷ 30 days / month◇ Calculated in your browser

01 / Set your workload

Pick an illustrative scenario, then adjust your usage.

Which task leaderboard?

Input tokens / request

Output tokens / request

Requests / day

Billing days / monthInput cache hit rate0%

Missing cache prices use the standard input rate. Cache writes are extra.

Monthly requests: 3,000
Monthly input tokens: 9,000,000
Monthly output tokens: 12,000,000

How many tokens is that?

Rough heuristic: ~1 token per CJK character, or 4 other characters per token. Use the provider’s tokenizer for exact counts.

Text to estimate (browser only)

≈ 0 Token · 0 characters

CURRENT FILTERS · LOWEST ESTIMATE

$6.10

/ month

GLM-5.3 Flash

Lower cost does not guarantee a better fit. Evaluate with your own tasks.

Same usage × 12 months $73.23

Lowest estimate, broken down

Uncached input: $1.08
Cached input: $0.00
Output: $5.03

02 / Compare models

Current task leaderboard and supplemental models only; not every model on the market.

Currency

CNY per 1 USD

Exchange rate date: 2026-10-16

Search models or providersProviderSort byChina-based providers only

42 models · 32 priced · USD / million tokens

GLM-5.3 Flash
Z.ai · Task rank #45 · Score 23.1
$6.10
/ month
Input $0.12Cached $0.034399Output $0.42
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$1.08
Cached input
$0.00
Output
$5.03
Per request: $0.002034
DeepSeek V4 Pro Preview
DeepSeek · Task rank #43 · Score 24.5
$14.36
/ month
Input $0.44Cached $0.003625Output $0.87
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$3.92
Cached input
$0.00
Output
$10.44
Per request: $0.004785
GPT-5.6 Luna
OpenAI · Task rank #22 · Score 69.3
$16.20
/ month
Input $0.20Cached $0.02Output $1.20
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$1.80
Cached input
$0.00
Output
$14.40
Per request: $0.0054
DeepSeek V4.1 Flash
DeepSeek · Task rank #25 · Score 65.7
$17.10
/ month
Input $0.30Cached $0.006Output $1.20
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$2.70
Cached input
$0.00
Output
$14.40
Per request: $0.0057
DeepSeek V4 Flash 0731
DeepSeek · Task rank #34 · Score 49.6
$20.19
/ month
Input $0.45Cached $0.014956Output $1.35
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$4.04
Cached input
$0.00
Output
$16.15
Per request: $0.00673
Gemini 3.7 Flash
Google · Task rank #15 · Score 77.8
$51.75
/ month
Input $0.75Cached $0.075Output $3.75
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$6.75
Cached input
$0.00
Output
$45.00
Per request: $0.01725
Gemini 3.8 Flash
Google · Task rank #20 · Score 71.0
$51.75
/ month
Input $0.75Cached $0.075Output $3.75
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$6.75
Cached input
$0.00
Output
$45.00
Per request: $0.01725
DeepSeek V4 Pro 0813
DeepSeek · Task rank #19 · Score 71.1
$60.57
/ month
Input $1.35Cached $0.044869Output $4.04
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$12.11
Cached input
$0.00
Output
$48.46
Per request: $0.020191
GLM-5.2
Z.ai · Task rank #41 · Score 29.6
$61.02
/ month
Input $1.20Cached $0.30Output $4.19
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$10.77
Cached input
$0.00
Output
$50.25
Per request: $0.02034
Muse Spark 1.3
Meta · Task rank #14 · Score 79.8
$62.25
/ month
Input $1.25Cached —Output $4.25
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$11.25
Cached input
$0.00
Output
$51.00
Per request: $0.02075
Muse Spark 1.2
Meta · Task rank #18 · Score 72.4
$62.25
/ month
Input $1.25Cached —Output $4.25
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$11.25
Cached input
$0.00
Output
$51.00
Per request: $0.02075
GLM-5.3
Z.ai · Task rank #33 · Score 54.0
$65.40
/ month
Input $1.40Cached $0.26Output $4.40
Price checked 2026-09-26Official pricing ↗
Cost breakdown
Uncached input
$12.60
Cached input
$0.00
Output
$52.80
Per request: $0.0218

Cost vs. performance: the frontier

Cost–performance frontier

Models on the frontier have no alternative with a lower cost and an equal or better score.Adjust your usage to see how the trade-offs change.

GLM-5.3 Flash$6.10 / month · Score 23.1

On the current frontier. Evaluate it with your actual tasks.

Per million tokens: Input $0.12 · Cache $0.034399 · Output $0.42

Task scores are comparative indices, not accuracy or success rates. The cost axis is logarithmic. Only models with complete pricing are compared.

How is the bill calculated?

Monthly cost = [input tokens × (cache miss rate × input price + cache hit rate × cache price) + output tokens × output price] × daily requests × days ÷ 1,000,000.

Text token costs only. Include billed reasoning tokens in output usage. Excludes tools, search, images, audio, cache writes, tax, subscriptions, tiered prices and batch discounts. Missing prices are never treated as zero. Annual figures multiply the same monthly usage by 12.