GPT-5.6 삼형제: Luna·Terra·Sol

생각 덩어리

세 사이즈 — Luna·Terra·Sol과 토큰당 가격

OpenAI’s latest flagship model hit general availability this morning, and comes in three sizes: Luna, Terra, and Sol (from smallest to largest).

The new models are priced per 1M input/output tokens as Luna $1/$6, Terra $2.50/$15, Sol $5/$30. For comparison, the Claude Opus series are $5/$25 and the Claude Fable 5 is $10/$50, but price-per-million tokens doesn’t tell us much now that the number of reasoning tokens can differ so much between models for the same task.

공통 스펙 — 컷오프·컨텍스트·최대 출력

All three models have a February 16th 2026 knowledge cutoff, a million token context window, and 128,000 maximum output tokens.

Agents’ Last Exam — Sol 53.6, Fable를 13.1점 차로 앞서다

We trained GPT-5.6 to get more useful work from every token. On Agents’ Last Exam, an evaluation of long-running professional workflows across 55 fields, GPT-5.6 Sol sets a new high of 53.6, eclipsing Claude Fable 5 (adaptive reasoning) by 13.1 points. Even at medium reasoning, it beats Fable 5 by 11.4 points at roughly one-quarter the estimated cost. That efficiency extends to smaller models, which are essential to making intelligence more abundant and affordable: GPT-5.6 Terra and GPT-5.6 Luna outperform Fable 5 at around one-sixteenth the cost.

SWE-Bench Pro의 완패와 벤치마크 흔들기 — 공교로운 타이밍

Amusingly, one self-reported benchmark that Fable 5 crushed the GPT-5.6 family on was SWE-Bench Pro, where Fable 5 got 80%...

In light of these results, we estimate that ~30% of SWE-bench Pro tasks are broken, and advise that model developers carefully examine results

직접 써본 소감 — 유능하나 Fable보다 낫진 않다

I’ve had some early access to GPT-5.6 Sol—it’s definitely very competent, though so far it hasn’t struck me as better than Fable at the kind of complex coding tasks I’ve been using with Anthropic’s model.

새 API 기능들 — Programmatic Tool Calling·Multi-agent·Prompt cache breakpoints

Programmatic Tool Calling allows the models to “compose and run JavaScript that orchestrates tool calls”—which sounds to me like it could help bridge the gap between MCPs and full terminal sessions that can compose CLI utilities in useful ways.

Multi-agent lets the model “spin up subagents for parallel, focused work”—the sub-agent pattern now baked into the core API.

Prompt cache breakpoints brings the Claude model of prompt caching to OpenAI, letting you be explicit about where the cache breakpoints are rather than relying on the API to detect them automatically.

18마리 펠리컨 — 0.71센트부터 48.55센트까지

Here’s a full page with 18 different pelicans —for reasoning efforts none, low, medium, high, xhigh, and max across the three different models. It also lists their token and calculated costs—the least expensive was gpt-5.6-luna at effort none for 0.71 cents, the most expensive was gpt-5.6-sol at max reasoning level for 48.55 cents.