CalculateTokens

GPT-5.4 vs GPT-5.6 TerraSide-by-side pricing

Side-by-side API pricing and tokenizer details for GPT-5.4 (OpenAI) and GPT-5.6 Terra (OpenAI).

Side-by-side pricing

FeatureGPT-5.4GPT-5.6 Terra
ProviderOpenAIOpenAI
Input (per 1M tokens)$2.50$2.50
Output (per 1M tokens)$15.00$15.00
Long-context pricingOver 272K tokens: $5.00 in / $22.50 outOver 272K tokens: $5.00 in / $22.50 out
Context cachingYes — 90% off cached tokensYes — 90% off cached tokens
Batch API discount50% off50% off
Context window1.1M tokens1.1M tokens
Tokenizero200k_base (tiktoken)o200k_base (tiktoken)

Real-world cost example

1,000 API requests per month, each with 500 input tokens and 200 output tokens (500K input + 200K output total).

GPT-5.4
$4.2500
Input: $1.2500 +Output: $3.0000
GPT-5.6 Terra
$4.2500
Input: $1.2500 +Output: $3.0000

Frequently asked questions

Both models cost the same for this workload ($4.2500).
GPT-5.4 supports a 1.1M token context window. GPT-5.6 Terra supports a 1.1M token context window. A larger context window lets you include more text — documents, conversation history, or code — in a single API call.
GPT-5.4 supports context caching (90% off repeated tokens). It offers a 50% Batch API discount. GPT-5.6 Terra supports context caching (90% off repeated tokens). It offers a 50% Batch API discount.
Yes, both GPT-5.4 and GPT-5.6 Terra use the o200k_base (tiktoken). The same text produces identical token counts on both models, so any cost difference is purely due to the rate each provider charges per token.
GPT-5.4 (OpenAI): $2.5 input / $15 output per 1M tokens. GPT-5.6 Terra (OpenAI): $2.5 input / $15 output per 1M tokens. Rates shown before caching or batch discounts.
Both models cost the same for an 80% output / 20% input workload: $12.5000 per 1M total tokens. For your exact ratio, paste a real prompt into the calculator above.
GPT-5.4 has a 1.1M-token context window — approximately 788K words or ~3K pages of standard text. GPT-5.6 Terra has a 1.1M-token context window — approximately 788K words or ~3K pages. (Estimates assume ~0.75 words per token.)

Calculate costs for your actual prompt

Paste your prompt into the calculator and get exact token counts using each model's real tokenizer — all in your browser.

Open calculator

Data provenance: Prices sourced directly from provider pricing pages.

GPT-5.4 prices last verified from OpenAI pricing page.

GPT-5.6 Terra prices last verified from OpenAI pricing page.

Prices may change. Always verify against the provider's current pricing page before making purchasing decisions.