OPENAI MODEL GUIDE

GPT-6.1 Terra API

GPT-6.1 Terra is tuned for visual reasoning, screen-based tasks, and concise writing.

Get API Key Model pricing calculator View Docs

Core specificationsModel Plaza checked November 10, 2026

Model IDgpt-6.1-terra

Context / max output1,050,000 / 128,000

Input and outputText and image input; text output

Thinkingnone / low / medium / high / xhigh / max

Vendor statusActive

LLMFly AI input / output per 1M$0.3 / $1.5 (70% OFF)

Selection verdictGPT-6.1 Terra bills at $0.3 input / $1.5 output per 1M tokens on LLMFly AI (0.3x standard tier).

Best fit

Try it for product photo matching, reading technical drawings, and scoped edits. Compare with GPT-6.1 Sol on the same inputs when a task spans several systems.

Avoid when

Broad refactors that repeatedly fail your acceptance tests on Terra.

OpenAI API cost estimate

Enter token counts for one representative request; every usage item is multiplied by the request count.

ChatGPT(Codex)0.3xCurrent multiplier

Estimated LLMFly AI cost$0.045GPT-6.1 Terra · 1 request

Vendor reference cost$0.15Estimated savings$0.10570.0%

Cost breakdown

Rates are per 1M tokens

Input$0.03

LLMFly AI: $0.3
Vendor reference: $1
Total tokens: 100,000

Output$0.015

LLMFly AI: $1.5
Vendor reference: $5
Total tokens: 10,000

Cache write$0.00

LLMFly AI: $0.375
Vendor reference: $1.25
Total tokens: 0

Cache read$0.00

LLMFly AI: $0.015
Vendor reference: $0.05
Total tokens: 0

Choosing and integrating

GPT-6.1 Terra API pricing breakdown

GPT-6.1 Terra (gpt-6.1-terra) is billed by token usage. Prices below are USD per 1M tokens. LLMFly AI rates already include the 0.3x group multiplier; do not apply it again. Provider reference prices are separate. These rates come from the site's Model Plaza snapshot; confirm live catalog and account rates before calling.

Example: a request with 10,000 uncached input tokens and 1,000 output tokens costs approximately $0.0045 in LLMFly AI token charges. This excludes cache writes, tools, retries, and other additional fees.

Platform and provider prices use their own input-token tiers. Do not apply provider long-context multipliers to platform prices.
Not listed does not mean free. Account for cache reads, cache writes, and uncached input in their respective billing categories.
Token cost = tokens in each billing category × its price per million ÷ 1,000,000. Add tools and other charges separately.

Price source	Input tokens per request	Input	Output	Cache write	Cache read	1h cache write
LLMFly AI	≤272K	$0.3	$1.5	$0.375	$0.015	Not listed
LLMFly AI	>272K	$0.6	$2.25	$0.75	$0.03	Not listed
Provider reference	≤272K	$1	$5	$1.25	$0.05	Not listed
Provider reference	>272K	$2	$7.5	$2.5	$0.1	Not listed

Pricing tiers and additional charges

Above 272,000 input tokens, the higher tier applies to the entire request. OpenAI lists cache writes for 30 minutes and 12 hours.

GPT-6.1 Terra capabilities and workloads

OpenAI documents structured output and function calling. Its native tool calls require the Responses API.

Limits to check before migration

For screen automation, validate target selection and the final state of the application. Confirm that your route exposes the tool schema you need.

Comparing GPT-6.1 Terra with sibling models

Try it for product photo matching, reading technical drawings, and scoped edits. Compare with GPT-6.1 Sol on the same inputs when a task spans several systems.

Model ID	Context / max output	LLMFly AI in / out	Vendor reference in / out
gpt-6.1-sol	1,050,000 / 128,000	$0.6 / $3	$2 / $10
gpt-6-sol	1,050,000 / 128,000	$0.6 / $3	$2 / $10
gpt-6.1-terra	1,050,000 / 128,000	$0.3 / $1.5	$1 / $5
gpt-5.6-sol	—	$1.5 / $9	$5 / $30
gpt-5.6-terra	—	$0.6 / $3.6	$2 / $12

Use the exact model ID when connecting

Set LLMFLY_API_KEY to a key with access to this model, then send this text request.

Send a minimal text request and inspect the response and usage.
Test streaming, tool calls, and structured output separately if your application needs them.
Check retry behavior and spending limits before increasing traffic.

request.example

curl https://app.llmfly.ai/v1/responses \
  -H "Authorization: Bearer $LLMFLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-6.1-terra",
  "input": "Reply with OK."
}'

Vendor capability versus gateway access

GPT-6.1 Terra runs under the ChatGPT(Codex) group (0.3x multiplier) in Model Plaza. Prefer the /v1/responses endpoint when combining reasoning with tool calls, and verify per-request input tiers and billed totals in your console usage log before production rollout.

Frequently asked questions

What should I put in the model field?

Use the exact ID gpt-6.1-terra, not the display name.

How is the discount calculated?

The current 0.3x multiplier is applied to the base rate, giving 70% off the catalog's official reference. Amounts are shown per million tokens.

Do these prices include every possible fee?

Not necessarily. Check cache-write duration, tools, and other route charges separately. Use the full pricing table and actual usage records to reconcile a bill.

What are the context and output limits?

Vendor documentation lists 1,050,000 context and 128,000 maximum output; confirm gateway route limits separately.

Use the GPT-6.1 Terra API

LLMFly AI provides this model. Use the exact ID gpt-6.1-terra and confirm current account pricing in Model Plaza.

View model and rates