gettokencalculator

Cost per Token

Translate model prices into the cost of one token or one thousand tokens.

Use the input count from your provider or expected workload.

API cost estimate

USD
Estimated monthly cost—
Per request—

Text counts use a reference encoding. Actual API usage and pricing can vary by model and tier.

Model pricing

Uncached text input and output in USD per 1 million tokens. Rates checked November 20, 2026.

ModelInputOutput
GPT-6.2 SolShort-context Standard $2.00$10.00
GPT-6.2 AstraShort-context Standard $8.00$40.00
GPT-6.1 TerraShort-context Standard $1.00$5.00
GPT-6 LunaShort-context Standard $0.10$0.50
Claude Sonnet 5.5 $2.00$10.00
Claude Opus 5.5 $4.00$20.00
Claude Fable 5.2 $8.00$40.00
Claude Haiku 5.5Prompts up to 100K tokens $0.10$0.50
Gemini 3.5 Flash-Lite $0.30$2.50
Grok 4.7Under 200K input tokens $2.00$6.00
DeepSeek V4.1 FlashPeak rates $0.30$1.20
DeepSeek V4 ProPeak rates $1.32$3.96

Presets use base text rates. Long prompts, cache usage, and separate tool fees can change the bill.

How much does one token cost?

Take the published USD price per million tokens and divide it by 1,000,000. A model that charges $2 per million input tokens costs $0.000002 per input token, or $0.002 per 1,000 input tokens. At $10 per million output tokens, a single output token costs $0.00001, or $0.01 per 1,000.

Published rate Per token Per 1,000 tokens
$0.30 per million $0.0000003 $0.0003
$2.00 per million $0.000002 $0.002
$10.00 per million $0.00001 $0.01

Why there are two rates

Providers often publish separate input and output prices. Input covers the instructions, chat history, or documents you send. Output covers the returned tokens and can include billed reasoning tokens. Some APIs also publish distinct rates for cached input, long prompts, and asynchronous batch processing. Convert comparable tiers before deciding which model costs less.

How to price a real workload

Unit prices make rates comparable, but the cheaper unit rate does not always give the cheapest request. A workflow that consumes fewer tokens or produces shorter replies may cost less at a higher rate. Use the AI token calculator to price both sides of one request. Use the token cost calculator for the totals on a usage report.