Loading model details
Hosted by a provider reached through SayGM. The route is sealed in transit and in use; the provider receives the prompt under its API terms.
Released
Jul 2026Knowledge cutoff
Feb 2026Modalities
Text · Tool calling · Image inputBest price on SayGM
-18.5%In
Cached
Out
per Mtok*
Create an API key and set it as GM_API_KEY in your terminal.
curl "https://api.saygm.com/v1/chat/completions" \
-H "Authorization: Bearer $GM_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-terra",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'SayGM's best available rate for gpt-5.6-terra next to OpenAI's own published list price — 18.5% off.
| Dimension | SayGM price | OpenAI list price |
|---|---|---|
| Input | $1.63per Mtok | $2.00 |
| Output | $9.78per Mtok | $12.00 |
| Cache read | $0.163per Mtok | $0.20 |
| Cache write | $2.0375per Mtok | $2.50 |
| Long-context inputabove 272,000 input tokens | $3.26per Mtok | $4.00 |
| Long-context outputabove 272,000 input tokens | $14.67per Mtok | $18.00 |
| Long-context cache readabove 272,000 input tokens | $0.326per Mtok | $0.40 |
| Long-context cache writeabove 272,000 input tokens | $4.075per Mtok | $5.00 |
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$1.64
$2.00Cached input
$0.16
$0.20Output
$9.82
$12.00Requests are load balanced across every provider serving this model, each offering its own rate, so what you pay is a blend rather than a single number. These are the blended rates actually paid — priced at what a provider offered, capped at list.
Measured over 6 windows: 1,848 requests and 2,192,261 input-side tokens. Most recent window closed 2026-09-25 04:38 UTC.
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 18.5% off | $1.63 | $9.78 |
| Provider 2 | 18.5% off | $1.63 | $9.78 |
| Provider 3 | 18.5% off | $1.63 | $9.78 |
| Provider 4 | 18.4% off | $1.63 | $9.79 |
| Provider 5 | 18.3% off | $1.63 | $9.80 |
| Provider 6 | 18.3% off | $1.63 | $9.80 |
| Provider 7 | 18.3% off | $1.63 | $9.80 |
| Provider 8 | 18.3% off | $1.63 | $9.80 |
| Provider 9 | 18.3% off | $1.63 | $9.80 |
| Provider 10 | 18.3% off | $1.63 | $9.80 |
| Provider 11 | 18.3% off | $1.63 | $9.80 |
| Provider 12 | 18.2% off | $1.64 | $9.82 |
| Provider 13 | 18.2% off | $1.64 | $9.82 |
| Provider 14 | 18.1% off | $1.64 | $9.83 |
| Provider 15 | 18.0% off | $1.64 | $9.84 |
| Provider 16 | 18.0% off | $1.64 | $9.84 |
| Provider 17 | 15.0% off | $1.70 | $10.20 |
Measured on the requests SayGM routed to this model.
Fixed-seed suites SayGM runs against this model.
Explore the OpenAI lab and compare related models.
The best available rate for gpt-5.6-terra on SayGM right now is $1.63 per million input tokens and $9.78 per million output tokens. A request above 272,000 input tokens bills at SayGM's long-context rate instead.
SayGM's best available rate for gpt-5.6-terra is 18.5% off OpenAI's list price.
Yes. gpt-5.6-terra is served on SayGM's OpenAI-compatible chat/completions surface, so an unmodified OpenAI SDK pointed at SayGM's base URL works with it.