Model comparison
GPT-5.6 Sol vs GPT-5.6 Terra
GPTCompare published specifications, vendor API list prices and measured Borg performance. Both models are included in Borg.
GPT-5.6 Sol
GPT-5.6 Terra
Included in Borg
At a glance
| Specification | GPT-5.6 Sol | GPT-5.6 Terra |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Release | 2026-07-09 Vendor source | 2026-07-09 Vendor source |
| Context | 1,050,000 tokens Vendor source | 1,050,000 tokens Vendor source |
| Modalities | Input: text, image; output: text | Input: text, image; output: text |
| Reasoning / thinking modes | Yes / Not published | Yes / Not published |
| Open weights | No | No |
| Vendor API list price / 1M tokens | $4 input / $20 output Standard global rates for prompts up to 272,000 input tokens. Above 272,000 input tokens, input and cached-input rates are 2× and output rates are 1.5× for the full request. Promotional pricing is guaranteed at least through November 21, 2026; a later rate has not been announced. | $2 input / $12 output Standard global rates for prompts up to 272,000 input tokens. Above 272,000 input tokens, input and cached-input rates are 2× and output rates are 1.5× for the full request. |
| Borg | Included in Borg subscription | Included in Borg subscription |
Measured on Borg
Metrics are not directly comparable to vendor benchmark claims. Models served different requests; this is observed gateway traffic, not a controlled head-to-head test.
Time to first token (gateway proxy)
Output tokens per second (whole turn)
| Metric | GPT-5.6 Sol | GPT-5.6 Terra |
|---|---|---|
| Time to first token (gateway proxy) p50 | 4614 ms (5283 samples) | 5138 ms (2845 samples) |
| Tokens per second (end to end) p50 | 14.3 output tokens per second (244151 samples) | 18.7 output tokens per second (37871 samples) |
| Request success rate | Not published | Not published |
| Coding bench pass rate | Not published | Not published |
Measurement window, samples and methodology
The fleet reference is the median of published model medians, not a request-weighted result. Prompt lengths, reasoning settings and traffic differ between models.
GPT-5.6 Sol: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 278070 requests. Minimum 100 samples per published request metric.
GPT-5.6 Terra: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 45567 requests. Minimum 100 samples per published request metric.
Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.
- Time to first token (gateway proxy): time until the first streamed response event reaches the gateway; our closest available measure of time to first token
- Tokens per second (end to end): tokens per second, end to end: provider-reported output tokens divided by the whole turn's elapsed time, including queueing and reasoning; not a streaming per-token rate
How to choose
GPT-5.6 Sol is listed for complex professional reasoning, whereas GPT-5.6 Terra is listed for document review with judgment. Choosing between GPT-5.6 Sol and GPT-5.6 Terra requires checking published specifications against observed Borg traffic for your workflow.
Key differences
| Spec | GPT-5.6 Sol | GPT-5.6 Terra |
|---|---|---|
| Context window | 1,050,000 tokens Vendor source | 1,050,000 tokens Vendor source |
| Reasoning modes | Yes / Not published | Yes / Not published |
| Release date | 2026-07-09 Vendor source | 2026-07-09 Vendor source |
| API price input / 1M | 4 Standard global rates for prompts up to 272,000 input tokens. Above 272,000 input tokens, input and cached-input rates are 2× and output rates are 1.5× for the full request. Promotional pricing is guaranteed at least through November 21, 2026; a later rate has not been announced. | 2 Standard global rates for prompts up to 272,000 input tokens. Above 272,000 input tokens, input and cached-input rates are 2× and output rates are 1.5× for the full request. Lower listed rate |
| API price output / 1M | 20 Standard global rates for prompts up to 272,000 input tokens. Above 272,000 input tokens, input and cached-input rates are 2× and output rates are 1.5× for the full request. Promotional pricing is guaranteed at least through November 21, 2026; a later rate has not been announced. | 12 Standard global rates for prompts up to 272,000 input tokens. Above 272,000 input tokens, input and cached-input rates are 2× and output rates are 1.5× for the full request. Lower listed rate |
| Time to first token (gateway proxy) | 4614 ms (5283 samples) Lower median | 5138 ms (2845 samples) |
| Output tokens per second (whole turn) | 14.3 output tokens/s (whole turn) (244151 samples) | 18.7 output tokens/s (whole turn) (37871 samples) Higher measured rate |
| Request success | Not published | Not published |
| Coding bench | Not published | Not published |
FAQ
How do GPT-5.6 Sol and GPT-5.6 Terra compare for coding?
GPT-5.6 Sol has a Borg coding benchmark of not published; GPT-5.6 Terra has not published. The GPT-5.6 Sol–GPT-5.6 Terra coding comparison cannot establish an overall winner from this small test alone.
How quickly do GPT-5.6 Sol and GPT-5.6 Terra start responding on Borg?
Borg median first response for GPT-5.6 Sol is 4,614 ms; for GPT-5.6 Terra it is 5,138 ms. The GPT-5.6 Sol–GPT-5.6 Terra gateway medians are observations, not guaranteed latency for individual requests.
What are the API prices for GPT-5.6 Sol and GPT-5.6 Terra?
The listed API rate for GPT-5.6 Sol is $4 input / $20 output per 1M tokens; for GPT-5.6 Terra it is $2 input / $12 output per 1M tokens. Neither GPT-5.6 Sol nor GPT-5.6 Terra has its Borg subscription charge represented by those provider API rates. GPT-5.6 Sol vendor source · GPT-5.6 Terra vendor source