Free · Open · Verified daily

Calculate AI API costs in seconds.

Compare pricing across 34+ models from OpenAI, Anthropic, Google, DeepSeek, xAI and Mistral — including cached input and Batch API discounts.

  • Exact tokenization for OpenAI models, transparent estimates for others
  • Side-by-side caching & batch savings
  • Monthly cost forecasts for high-volume workloads
Updated 2026-09-05·USD / CNY / EUR / GBP / INR
✓ Exact tokenizer·$4.00 in·$20.00 out (per 1M)
Quick start with a use case
Total cost per call$0.0140
Input$0.004000
Output$0.0100
Cost comparison
Standard
$0.0140
With Caching
$0.0122
Save 13% ↓
With Batch
$0.0100
Save 29% ↓
Cutting costs? Open models start at $0.28/1M

DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Side by side

All 34 models, ranked by cost

Plug in your token usage. Sort, filter, hide. The cheapest pick for your workload is at the top.

All models compared

Sorted by cost for your token usage. Click column headers to re-sort.

Filter by provider
DeepSeek V3.2
DeepSeek · balanced
$0.2800$0.4000$0.000480
GPT-5.6 Luna
OpenAI · small
$0.2000$1.2000$0.000800
Gemini 3.1 Flash Lite
Google · small
$0.2500$1.5000$0.001000
DeepSeek V4-Flash
DeepSeek · small
$0.4400$1.3200$0.001100
GPT-5 mini
OpenAI · small
$0.2500$2.0000$0.001250
Mistral Large 3
Mistral · balanced
$0.5000$1.5000$0.001250
Gemini 3.5 Flash Lite
Google · small
$0.3000$2.5000$0.001550
Gemini 3 Flash
Google · balanced
$0.5000$3.0000$0.002000
Grok 4.3
xAI · balanced
$1.2500$2.5000$0.002500
Gemini 3.6 Flash
Google · balanced
$0.7500$3.7500$0.002625
Gemini 3.7 Flash
Google · small
$0.7500$3.7500$0.002625
Gemini 3.8 Flash
Google · small
$0.7500$3.7500$0.002625
o4-mini
OpenAI · reasoning
$1.1000$4.4000$0.003300
DeepSeek V4-Pro
DeepSeek · flagship
$1.3200$3.9600$0.003300
Claude Haiku 4.5
Anthropic · small
$1.0000$5.0000$0.003500
Grok 4.5
xAI · flagship
$2.0000$6.0000$0.005000
Grok 4.6
xAI · flagship
$2.0000$6.0000$0.005000
Gemini 3.5 Flash
Google · balanced
$1.5000$9.0000$0.006000
Claude Sonnet 5
Anthropic · balanced
$2.0000$10.0000$0.007000
GPT-5.6 Terra
OpenAI · balanced
$2.0000$12.0000$0.008000
Gemini 3.1 Pro
Google · flagship
$2.0000$12.0000$0.008000
Grok 4
xAI · flagship
$3.0000$15.0000$0.0105
GPT-5.6
OpenAI · flagship
$4.0000$20.0000$0.0140
GPT-5.6 Sol
OpenAI · flagship
$4.0000$20.0000$0.0140
Claude Opus 5
Anthropic · flagship
$5.0000$25.0000$0.0175
Claude Opus 4.8
Anthropic · flagship
$5.0000$25.0000$0.0175
Claude Opus 4.7
Anthropic · flagship
$5.0000$25.0000$0.0175
GPT-5.5
OpenAI · flagship
$5.0000$30.0000$0.0200
Claude Fable 5
Anthropic · flagship
$10.0000$50.0000$0.0350
Claude Mythos 5
Anthropic · flagship
$10.0000$50.0000$0.0350
Claude Fable 5.1
Anthropic · flagship
$10.0000$50.0000$0.0350
GPT-6 Astra
OpenAI · flagship
$10.0000$50.0000$0.0350
GPT-5.6 Cyber
OpenAI · flagship
$12.5000$75.0000$0.0500
GPT-5.5 Pro
OpenAI · flagship
$30.0000$180.00$0.1200
Plan ahead

Forecast your monthly bill

Enter your daily call volume and average tokens. See the monthly damage across up to 5 models with savings highlighted.

Monthly cost forecast

Estimate your monthly bill across up to 5 models.

3/5 selected
3.6 FlashGooglecheapest
$45.0000/mo
per call: $0.001500year: $547.50
GPT-5.6OpenAI
$240.00/mo
per call: $0.008000year: $2920.00
Opus 5Anthropic
$300.00/mo
per call: $0.0100year: $3650.00
Choosing 3.6 Flash over Opus 5 saves $255.00/month ($3060.00/year).
Last verified 2026-09-05Schema v2.0Verified daily against the LiteLLM registryOpen source on GitHub