Price tracker · as of 2026-10-21

GPT-5.6 Luna Price Tracker

Official OpenAI rates as of 2026-10-21: $0.20 input, $1.20 output and $0.02 cached input per 1M tokens for GPT-5.6 Luna; $0.10 input and $0.50 output for the newer GPT-6 Luna. OpenAI's changelog records that from 2026-07-30 GPT-5.6 Luna costs 80% less and GPT-5.6 Terra 20% less. This page tracks official short-context API rates and what changed for Codex usage counting.

#Luna $0.20/$1.20 #Terra $2/$12 #Sol $4/$20 (promo) #OpenAI API

Current short-context official rates (OpenAI rate card)

Checked against the official rate card and model pages on 2026-10-21: the official price of $0.20 input / $1.20 output / $0.02 cached input per 1M tokens corresponds to GPT-5.6 Luna; Terra is $2 / $12 and Sol is now $4 / $20, with the page noting that promotional pricing runs at least through 2026-11-21. Cached input is typically 10% of uncached input. Prices can change, so re-check the official table before large runs.

Last checked: 2026-10-21 (official OpenAI rate card, model pages and deprecation table).

Family price table

Short-context standard rates, per 1M tokens. Long context costs about $0.40 input / $1.80 output for the Luna tier. Re-checked 2026-10-21: the official model page states that prompts over 272K input tokens are billed at 2x input and 1.5x output for the whole request.

Tier	Input	Output	Cached input	Notes
gpt-5.6-luna	$0.20	$1.20	$0.02	80% cut on 2026-07-30 (was $1 / $6)
gpt-5.6-terra	$2.00	$12.00	$0.20	20% cut on 2026-07-30 (was $2.50 / $15)
gpt-5.6-sol	$4.00	$20.00	$0.50	Official price $4/$20, promotional through at least 2026-11-21; Fast mode is about 2.5x faster at twice the price.

Luna details worth budgeting for

Context and long prompts

API context is about 1.05M tokens. Over 272K input tokens the whole request is billed at the higher long-context rate, about $0.40 input / $1.80 output for the Luna tier. Re-checked on the official model page on 2026-10-21: context is 1,050,000 tokens, max output is 128,000 tokens and the knowledge cutoff is 2026-02-16, for GPT-5.6 Luna.

Subscriptions and Codex

Plan prices and overall quotas did not drop. OpenAI states the lower Luna and Terra rates are reflected in how usage is counted against paid ChatGPT Work and Codex subscriptions — the same quota can cover more Luna/Terra work.

LiteLLM note

On the LiteLLM openai key, $0.20/$1.20 is listed for GPT-5.6 Luna (checked 2026-08-02). Some entries under other prefixes may still carry the old price — this page follows the official OpenAI rate card and model pages.

Routing suggestion (cost, not a quality ranking)

Match tier to the job. These are practical defaults, not benchmark claims.

Luna — high-volume execution

Bulk tool calls, well-specified edits, tests, classification, and cheap agent steps after a plan exists.

Terra — everyday coding default

Balanced day-to-day coding and agent work when you want better quality than Luna without Sol spend.

Sol — planning and hard cases

Ambiguous design, hard bugs, and high-stakes plans. Use Sol Fast when latency matters and 2x list price is acceptable.

Price timeline

Filled events first. Empty slots stay hidden until new i18n keys are added.

2026-07-09

GPT-5.6 family general availability

Sol / Terra / Luna GA on 2026-07-09. Launch short-context list prices: Sol $5/$30, Terra $2.50/$15, Luna $1/$6 per 1M tokens.

2026-07-30

Luna −80%, Terra −20%

OpenAI announced lower Luna and Terra prices effective that day: Luna $0.20/$1.20, Terra $2/$12. Sol list price unchanged; Sol Fast mode introduced in the API.

2026-08-02

Tracker page published on QCode

Rates above re-checked against OpenAI model/pricing docs and LiteLLM openai keys. Future cuts can be appended as new timeline slots without a template change.

Primary sources

OpenAI's official rate card, the GPT-5.6 Luna and GPT-6 Luna model pages, the list of models removed from the API, and the API changelog (2026-07-30 price cut, 2026-08-21 Sol repricing): developers.openai.com/api/docs/pricing, developers.openai.com/api/docs/models/gpt-5.6-luna, developers.openai.com/api/docs/models/gpt-6-luna, developers.openai.com/api/docs/deprecations, developers.openai.com/api/docs/changelog (fetched 2026-10-21); LiteLLM model_prices_and_context_window.json (openai key, 2026-08-02).

FAQ

What is the current GPT-5.6 Luna price?

As of 2026-10-21, the official OpenAI rate card lists $0.20 input, $1.20 output and $0.02 cached input per 1M tokens for GPT-5.6 Luna; context is 1,050,000 tokens and max output is 128,000 tokens.

Did Sol get cheaper too?

The price list wasn't re-cut across the board, but Sol now carries a promotional rate: the 2026-09-12 archive of the official pricing page shows gpt-5.6-sol at $4/$20 (promotional at least through 2026-11-21), down from the $5/$30 launch list. OpenAI also introduced Fast mode for Sol at about 2x price for up to about 2.5x speed, without claiming higher intelligence.

Did Codex subscription prices fall?

OpenAI did not lower subscription sticker prices in the July 30 note. It said lower Luna and Terra rates are reflected in how usage is counted against paid Codex and ChatGPT Work plans.

Can I call Luna through QCode?

Not available. QCode does not currently support gpt-6-luna or gpt-5.6-luna, so please use another GPT model, such as gpt-6.1-sol, gpt-6-sol or gpt-5.6-terra — the same key, just a different model. OpenAI's deprecation table lists gpt-4.1-nano-2025-04-14 as removed from the API on 2026-10-23. Before a large run, check live unit prices on /models.

Create a QCode account

One key across Claude, GPT and Chinese models, billed per token — live rates on /models.

Create account

Models and live rates View plans