Model comparison
GPT-5.6 Sol vs GPT-5.6 Terra: flagship or middle tier?
GPT-5.6 Sol costs about twice GPT-5.6 Terra, on promotional rates. How Terra's output price narrows the gap and why Codex points both to GPT-6 Sol.
· Prices as of September 28, 2026
GPT-5.6 Sol
OpenAI · Released July 9, 2026 · Previous generation
The flagship of the July 2026 GPT-5.6 family, now succeeded by GPT-6 Sol and on promotional pricing.
GPT-5.6 Sol facts and comparisonsGPT-5.6 Terra
OpenAI · Released July 9, 2026 · Previous generation
The middle tier of GPT-5.6, balancing intelligence and cost, which roughly corresponds to earlier GPT-5 mini models.
GPT-5.6 Terra facts and comparisons
The short answer
GPT-5.6 Sol costs 2x GPT-5.6 Terra for input and caching but only 1.7x for output, so the example agentic coding session costs $4.20 against $2.20. OpenAI pitched Sol as the GPT-5.6 flagship for complex professional work and Terra as the tier that balances intelligence and cost. Both are previous-generation models now, and Codex suggests moving from either one to GPT-6 Sol.
Choose GPT-5.6 Sol if
- You want the GPT-5.6 flagship, which OpenAI built for complex professional work.
- Your Codex work happens in Codex cloud on a ChatGPT plan, which runs Sol.
- Your scripts request gpt-5.6, the API id that resolves to Sol.
Choose GPT-5.6 Terra if
- You want GPT-5.6 at about half the cost: $2 input and $12 output per million tokens.
- You are replacing an earlier GPT-5 mini model, the slot OpenAI places Terra in.
- You prefer rates that are not promotional; OpenAI cut Terra's price by 20% on July 30, 2026, with no end date attached.
Side by side
Specs and prices
| Fact | GPT-5.6 Sol | GPT-5.6 Terra |
|---|---|---|
| Maker | OpenAI | OpenAI |
| API model id | gpt-5.6-sol | gpt-5.6-terra |
| Released | July 9, 2026 | July 9, 2026 |
| Status | Previous generation | Previous generation |
| Context window | 1.05M tokens | 1.05M tokens |
| Max output | 128K tokens | 128K tokens |
| Open weights | No | No |
| Input, per 1M tokens | $4 | $2 |
| Cache hit, per 1M | $0.40 | $0.20 |
| Cache write, per 1M | $5 | $2.50 |
| Output, per 1M tokens | $20 | $12 |
| Runs in | Codex, Cursor, OpenCode, OpenRouter, and GitHub Copilot | Codex, Cursor, OpenCode, OpenRouter, and GitHub Copilot |
Standard API rates in US dollars, as published by each maker on September 28, 2026. Batch and priority tiers, taxes, and subscription plans are not included. GPT-5.6 Sol: Requests over 272K input tokens cost 2x for input and cache and 1.5x for output, for the whole request. These are promotional rates, available at least through November 21, 2026. GPT-5.6 Terra: Requests over 272K input tokens cost 2x for input and cache and 1.5x for output, for the whole request.
Cost
What the same work costs
The same token counts, priced at each model’s published rates. Cached tokens are billed at each maker’s cache prices, so the session shows what caching is worth on each model.
Real sessions differ: the two models count the same code as different numbers of tokens, and reasoning settings change how much each one writes. Your own history is the real test.
| Workload | GPT-5.6 Sol | GPT-5.6 Terra |
|---|---|---|
| Agentic coding session, 100K input, 400K written to cache, 2M read from cache, 50K output | $4.20 | $2.20 |
| Large one-off review, 150K input with no cache hits, 10K output | $0.80 | $0.42 |
| Output-heavy generation, 30K input, 80K output | $1.72 | $1.02 |
| A month of sessions, 110 sessions: 5 a day, 22 working days | $462.00 | $242.00 |
| Where the session’s cost goes | ||
| Cache writes | $2.00 | $1.00 |
| Cache reads | $0.80 | $0.40 |
| Uncached input | $0.40 | $0.20 |
| Output | $1.00 | $0.60 |
- caching saves on the session with GPT-5.6 Sol (62%)
- $6.80
- caching saves on the session with GPT-5.6 Terra (61%)
- $3.40
How much cheaper is GPT-5.6 Terra than GPT-5.6 Sol?
Per million tokens, GPT-5.6 Sol asks $4 for input, $20 for output, $5 to write the cache, and $0.40 to read it. GPT-5.6 Terra asks $0.20 to read the cache, $2.50 to write it, $2 for input, and $12 for output. Input and caching sit exactly 2x apart, but output sits 1.7x apart, because Terra's output is priced above half of Sol's.
That output price shapes the gap. The uncached review costs $0.80 against $0.42, and the session $4.20 against $2.20, both about 1.9x. The output-heavy generation narrows to 1.7x, $1.72 against $1.02. Work that writes a lot gains less from moving down a tier.
In the session, output is 24% of Sol's cost and 27% of Terra's. Cache writes lead on both, $2.00 on Sol and $1.00 on Terra, since OpenAI bills writes at 1.25x input from GPT-5.6 on. A month of 110 sessions comes to $462.00 on Sol and $242.00 on Terra, a difference of $220.00.
Does GPT-5.6 Sol's promotion change the comparison?
It can. GPT-5.6 Sol's rates are promotional, available at least through November 21, 2026, and the sources behind this page do not give its price after that. Terra's rates carry no promotional note. OpenAI cut Terra's price by 20% on July 30, 2026, three weeks after the family launched.
So today's 1.9x session gap rests on a promotion on one side. If Sol's price moves after November 21, the gap moves with it, while Terra's side stays where it is unless OpenAI announces otherwise.
Both GPT-5.6 tiers now point to GPT-6 Sol
GPT-5.6 was OpenAI's July 2026 family. OpenAI called Sol its flagship model for complex professional work, and Terra the GPT-5.6 model that balances intelligence and cost, placing it roughly where earlier GPT-5 mini models sat. It credits the whole family with token efficiency, better frontend design, and inferring the user's underlying goal from context.
Both are previous-generation models now. Codex suggests moving from GPT-5.6 Sol and from GPT-5.6 Terra to GPT-6 Sol, and Terra stays available in the API. Sol also still powers Codex cloud chats on ChatGPT plans, and it is what the API id gpt-5.6 resolves to.
Neither differs on limits: each has a 1.05M context window and writes up to 128K tokens, and a request over 272K input tokens costs 2x for input and cache and 1.5x for output. Both are available in Codex, Cursor, OpenCode, OpenRouter, and GitHub Copilot.
If you split work between the two tiers, EveryToken reads your local Codex, Cursor, and OpenCode history and prices each request per model, which shows how your spending divides between them.
Prompt caching
How OpenAI bills cached tokens
OpenAI
Prompt caching is on by default. From GPT-5.6 on you can also mark up to four explicit cache breakpoints, while GPT-5.5 and earlier cache automatically only.
From GPT-5.6 on, a cache write costs 1.25x the uncached input price and a cache hit costs 0.1x. GPT-5.5 and earlier add no charge for writing the cache: written tokens are billed as ordinary input, and a hit costs 0.1x on the models compared here.
On GPT-5.6 and later, a cached prefix stays reusable for at least 30 minutes after its last use, and caching starts at 1,024 input tokens.
Source: OpenAI: Prompt caching
Your own numbers
See what GPT-5.6 Sol and GPT-5.6 Terra really cost you.
everyaitoken reads your Codex, Cursor, OpenCode, and OpenRouter history on your Mac and prices every request at API rates, with what caching saved or cost. $9 once.
FAQ
Questions
Is GPT-5.6 Terra half the price of GPT-5.6 Sol?
On input and both cache rates, yes. Output costs $12 per million tokens on Terra against $20 on Sol, which is 40% less rather than half.
Which GPT-5.6 model does Codex use?
Sol is the model behind Codex cloud chats on ChatGPT plans. For other Codex use, Codex suggests moving from both GPT-5.6 Sol and GPT-5.6 Terra to GPT-6 Sol.
When do GPT-5.6 Sol's promotional rates end?
The promotion runs at least through November 21, 2026, according to OpenAI's pricing. This page has no source yet for the price after that.
What did GPT-5.6 Terra replace?
OpenAI's positioning places GPT-5.6 Terra roughly where earlier GPT-5 mini models sat, as the middle tier that balances intelligence and cost.