GPT-6.1 Terra API pricing and discount
Call GPT-6.1 Terra through one OpenAI-compatible endpoint, billed $0.65 per 1M input tokens, 35% below OpenAI’s list price. Routes are verified before they serve you and re-checked continuously.
- 1.1M context
- Reasoning
- Coding ready
- OpenAI-compatible
New accounts start with free credit. Then prepaid from $5, no subscription.
- Input, per 1M tokens
- $0.65was
$1.00 - Output, per 1M tokens
- $3.25was
$5.00
Same model, same tokens, less to pay. Billed per request from prepaid credits; every response reports the cost.
- 1.1Mtokens
- Context window
- 128ktokens
- Maximum output
- 35%off
- Below OpenAI’s list price
- 88%
- Of input usually cached
- 42%
- Of requests use reasoning
- Live
- Callable now, every key
What your GPT-6.1 Terra workload costs
Move the sliders to your request size and volume. It starts on a typical request from real traffic.
Starts on a typical GPT-6.1 Terra request (33.3k in, 353 out). Reasoning tokens bill as output; cached input bills at the normal input rate on OSMEXO today.
- Per request
- $0.023
- Per 1,000 requests
- $22.78
- You save / month
- $368
Estimate: (input × input price + output × output price) ÷ 1M per request, × requests per day × 30. Before any vendor cache discount.
Where GPT-6.1 Terra fits
What developers use GPT-6.1 Terra for, where it ranks highest, and what a typical request looks like, from OSMEXO Intelligence.
Ranks highest on
- Intelligence index#11 of 49051.3
- Humanity's Last Exam#24 of 46546.2%
- Terminal-Bench 4.0#9 of 15355.6%
Bar = score against the best model. Benchmark data: Artificial Analysis.
A typical request
33k tokens in · 353 out
- 88% of input tokens are usually cached
- Reasoning is on in 42% of requests
- 0.36 tool calls per request on average
Averages across recent traffic for GPT-6.1 Terra; cache discounts not applied.
Call it from your code or coding agent
Change the base URL and the key; keep your code. Streaming, tool calls, structured output and vision behave as they do upstream, and every response carries the billed cost beside the list price.
openai/gpt-6.1-terrafrom openai import OpenAI
client = OpenAI(
base_url="https://api.osmexo.com/v1", # was the vendor's URL
api_key="osm-...",
)
r = client.chat.completions.create(
model="openai/gpt-6.1-terra",
messages=[{"role": "user", "content": "Hello"}],
)
Check it is the real GPT-6.1 Terra, with your own key
Every route passes these checks against OpenAI’s own API before it serves anyone. Run the same battery yourself: one OpenRouter key verifies any text model, a direct OpenAI key works too, and exit code 0 means the same model.
- 1Tokenizer fingerprint
The same prompt must cost the same token count as on the vendor’s API.
- 2Knowledge cutoff probe
The route must name the same training cutoff and maker as the vendor’s model.
- 3Hidden-prompt probe
Asks for any operator system prompt, so a wrapper that injects one is caught.
- 4Exact-output tests
Deterministic tasks, such as reversing a string, must give the vendor’s answer.
- Approved route
Scored 0 to 100; 85 or more goes live, then is re-checked continuously.
curl -fsSLO https://dashboard.osmexo.com/verify.mjs
OSMEXO_API_KEY=osm-... VENDOR_API_KEY=sk-or-... \
node verify.mjs --model openai/gpt-6.1-terra --vendor openrouter
- streamed tool calls
- parallel tools
- tool round trip
- files written via tools
- long file (15k tokens)
How much does GPT-6.1 Terra cost through OSMEXO?
$0.65 per 1M input tokens and $3.25 per 1M output tokens, billed per request from prepaid credits. That is 35% below OpenAI’s list price of $1.00 / $5.00. The price on this page refreshes from the catalog every few minutes.
Is this the same GPT-6.1 Terra as calling OpenAI directly?
Yes. Every route for GPT-6.1 Terra is probed against the vendor’s own API before it serves anyone: tokenizer fingerprint, knowledge cutoff, a hidden-prompt probe and exact-output tasks, scored 0 to 100 with 85 as the approval threshold. You can run the same check from your machine with your own vendor key; the command is on this page.
How do I call GPT-6.1 Terra with the OpenAI SDK?
Point the official OpenAI SDK at https://api.osmexo.com/v1 with your OSMEXO key and use the model id openai/gpt-6.1-terra. Streaming, tool calls, structured output and vision work as they do upstream. Coding agents such as OpenCode, Cline, Roo Code, Continue and Aider take the same base URL and key.
What happens if a provider for GPT-6.1 Terra goes down?
The gateway retries and falls back to the next verified route for GPT-6.1 Terra before the first token is sent, so your users see a slower answer instead of an error. Every response reports which route answered, what it cost, and what the same tokens would have cost at list price.