Token Cost Calculator

ChatGPT API Pricing

GPT-6 and GPT-5 per-token rates, Batch API 50% off, and prompt-cache savings — compared to Claude, Gemini, and DeepSeek.

Last updated: 2026-09-26

1,000
2,000
400
1,000 × 2,000in + 400out = 2,000,000 input,400,000 output tokens

Estimated cost across 18 models

google Cheapest

Gemini 2.5 Flash-Lite

$0.360/ month
$4.32 / year
openai

GPT-6 luna

$0.400/ month
$4.80 / year
deepseek

DeepSeek V4.1-Flash

$1.08/ month
$12.96 / year
Peak hours
google

Gemini 3.1 Flash-Lite

$1.10/ month
$13.20 / year
google

Gemini 2.5 Flash

$2.70/ month
$32.40 / year
Long context ≥200,000
google

Gemini 3.8 Flash

$3.00/ month
$36.00 / year
anthropic

Claude Haiku 4.5

$4.00/ month
$48.00 / year
deepseek

DeepSeek V4-Pro

$4.22/ month
$50.69 / year
Peak hours
grok

Grok 4.7

$6.40/ month
$76.80 / year
openai

GPT-6 sol

$8.00/ month
$96.00 / year
anthropic

Sonnet 5

$8.00/ month
$96.00 / year
google

Gemini 3.1 Pro Preview

$8.80/ month
$106 / year
google

Gemini 2.5 Pro

$11.00/ month
$132 / year
Long context ≥200,000
openai

GPT-5.6 sol

$16.00/ month
$192 / year
anthropic

Opus 5.5

$16.00/ month
$192 / year
openai

GPT-6 astra

$40.00/ month
$480 / year
anthropic

Fable 5.1

$40.00/ month
$480 / year
openai

GPT-5.6 cyber

$55.00/ month
$660 / year

Prices verified 2026-09-26. Source: official provider pricing pages. · Machine-readable: /api/prices.json

Quick takeaways
  • 1GPT-5 cached input drops to $0.125/M — a 90% discount vs the $1.25/M standard rate.
  • 2The Batch API runs at 50% off with a 24-hour SLA — ideal for evals, bulk summarization, and dataset generation.
  • 3GPT-6 astra is the most expensive active model at $10 input / $50 output per 1M tokens.
  • 4GPT-6 luna is the cheapest active model at $0.10 input / $0.50 output per 1M tokens.

Batch API · 50% off

OpenAI's Batch API processes requests asynchronously with a 24-hour SLA at half the standard rate — both input and output bill at 50%. You submit a JSONL file of requests, poll for completion, and there are no rate limits on the queue. Ideal for non-urgent workloads: evals, bulk summarization, dataset generation, and large backfills.

50% off · 24-hour SLA · no queue rate-limits

Prompt caching · ~90% off

OpenAI automatically caches prompt prefixes (≥1,024 tokens) for 5–10 minutes (longer on GPT-5/6). Cached reads bill at roughly 10% of the standard input rate. For repeat-prefix workloads (system prompts, tool schemas, large documents) caching is the single biggest cost lever — most production stacks see a 50–80% input reduction once caching is on.

  • GPT-6 astra: $1.000/M (90% off)
  • GPT-6 sol: $0.200/M (90% off)
  • GPT-6 luna: $0.010/M (90% off)
Token Cost Calculator

How to bring the bill down

  1. 1Use GPT-5 nano or GPT-6 luna for routing / classification — output is roughly 8–20× cheaper than the flagship.
  2. 2Enable cached input — OpenAI auto-caches prefix repeats for ~90% off the standard input rate.
  3. 3Route non-urgent jobs through the Batch API for 50% off (24-hour SLA, no queue rate-limits).
  4. 4Set max_tokens explicitly — output is the expensive side; capping it prevents runaway replies.
  5. 5ChatGPT Plus ($20/mo) does NOT replace API access — high-volume workloads still need the API.
Token Cost Calculator

calculator.faqTitle

GPT-6 astra is $10 input / $50 output per 1M; GPT-6 sol is $2 / $10; GPT-6 luna is $0.10 / $0.50. Older GPT-5 (now delisted) was $1.25 / $10 with cached input at $0.125/M. Use the calculator above to compare every active model at your exact usage.
More calculators

Pick the right page for your use case

Token Cost Calculator

Compare prices across OpenAI, Claude, Gemini, DeepSeek, and Grok. Real tokenizer for OpenAI, accurate estimates for the rest.

Open

OpenRouter Pricing Calculator

See what your tokens actually cost after the OpenRouter markup — and when going direct to the provider is cheaper.

Open

Claude Token Cost Calculator

Cost per token and monthly estimates for Claude Opus, Sonnet, and Haiku — with the Anthropic API.

Open

DeepSeek API Pricing

V4-Pro and V4.1-Flash per-token rates, off-peak hours, and prompt-cache savings — compared to Claude, GPT, and Gemini.

Open