Polarison

OpenAI

GPT-5.6 Terra pricing and benchmarks

The GPT-5.6 model that balances intelligence and cost.

Input
$2.00
per 1M tokens
Cached input
$0.20
per 1M tokens
Output
$12.00
per 1M tokens
Capability index
159.1
#5 of 16 tracked

How capable is GPT-5.6 Terra?

GPT-5.6 Terra scores 159.1 on the Epoch Capabilities Index (confidence interval 157.0161.8), ranking #5 of the 16 rated models we track. It is a best-value pick: no cheaper model we track scores higher.

BenchmarkTestsScore
GPQA DiamondScience reasoning
91.1%
FrontierMath (Tiers 1–3)Advanced math
86.0%
SimpleQA VerifiedFactual accuracy
43.2%
ARC-AGI-2Abstract reasoning
83.9%
DeepSWECoding
69.6%
APEX-AgentsAgentic work

Source: Epoch AI (as “GPT-5.6 Terra”), best recorded result, CC BY 4.0. A dash means no published score. Compare all models

What GPT-5.6 Terra costs in practice

WorkloadMonthly cost
Support chatbot
100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each.
$780.00
Document Q&A (RAG)
50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each.
$1,160
Coding agent
10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens.
$536.00

Pricing details

  • Cache writes are billed at $2.50 per 1M tokens.
  • Fast mode costs 2x the standard rate; Flex costs half.

Estimate your GPT-5.6 Terra bill

Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.