FAST GPT-6 TIERGPT-6 FAMILY1.05M CONTEXTCACHE READS AT 5%TEXT + VISION
GPT-6.1 Terra API Pricing
GPT-6.1 Terra is OpenAI's fast, efficient GPT-6 model, released October 26, 2026 at $1.00/M input, $0.05/M cached input and $5.00/M output. OpenAI pitches it at visual reasoning, precise computer use and clear writing, and lists it between GPT-6.1 Sol and GPT-6 Luna. Against GPT-5.6 Terra, which stays on the price list at $2.00 / $12.00, input is halved and output falls further. Prompts over 272K input tokens bill on the long-context card at $2.00/M input and $7.50/M output.
Input - per 1M tokens
$1.00/M
Short context up to 272K input standard
Output - per 1M tokens
$5.00/M
Long context output is $7.5/M standard
Cached input - 95% off
$0.05/M
Prompt cache read price -95%
Effective - agentic blend
$0.645/M
92/8 split - 82% cache
§ 01 / TERMINAL
GPT-6.1 Terra API cost calculator.
Live calculator pre-loaded with GPT-6.1 Terra's standard short-context rates. Reasoning effort runs from none to max, and reasoning tokens bill as output, so put them in the reasoning field. Cross 272K input tokens in one prompt and the long-context card applies instead.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
GPT-6.1 Terra cost on real workloads.
COMPUTER USE
Multi-step app workflow
$0.051/task
VISION
Product photo to catalog match
$0.0041/item
LONG DOC ANALYSIS
Reading 150-page contracts
$0.104/doc
WRITING
Draft and revise a report section
$0.018/draft
Exact · o200k_base Auto-counts as you type
Counted with the o200k_base BPE encoding — the same tokenizer the API uses — entirely in your browser. The encoder loads on your first keystroke (~1 MB, one time); your text never leaves this page.
Characters 609
Words 103
Tokens (exact) 153 tokens
Cost as input · uncached $0.00015 USD
Cost as output · uncached $0.00076 USD
Cost as cached input $0.00001 USD
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| GPT-6.1 Terra Current | $1.00 cache $0.05 | $5.00 | $0.645 agentic 92/8 | 1.05M | Visual reasoning, computer use and writing |
| GPT-6.1 Sol | $2.00 cache $0.10 | $10.00 | $1.29 +2.0× | 1.05M | OpenAI's balanced tier, near-Astra work |
| GPT-6 Luna | $0.10 cache $0.01 | $0.50 | $0.0682 −9.4× | 1.05M | High-volume routing tier |
| GPT-5.6 Terra | $2.00 cache $0.20 | $12.00 | $1.52 +2.4× | 1.05M | The previous Terra, still on the price list |
| Claude Haiku 5.5 | $0.10 cache $0.01 | $0.50 | $0.0682 −9.4× | 1M | Anthropic's fast, high-volume tier |
| Gemini 3.8 Flash | $0.75 cache $0.075 | $3.75 | $0.481 −25% · promo | 1M | Multimodal high-volume alternative |
| Grok 4.3 | $1.25 cache $0.20 | $2.50 | $0.558 −13% | 1M | Cheaper output on a 1M context |
Compare siblings
GPT-6.1 Terra API pricing FAQ.
GPT-6.1 Terra pricing questions - the standard card, what changed from GPT-5.6 Terra, and where it sits between 6.1 Sol and 6 Luna.
Q · 01 How much does GPT-6.1 Terra cost? +
OpenAI lists
gpt-6.1-terra at $1.00/M input, $0.05/M cached input, $1.25/M cache writes and $5.00/M output for prompts up to 272K input tokens. Under our standard blend (92% input, 82% cache hits) that works out to $0.645/M. Cache writes with 12-hour retention cost twice the 30-minute rate.Q · 02 What changed from GPT-5.6 Terra? +
Price, mostly. GPT-5.6 Terra lists at
$2.00/M input, $0.20/M cached and $12.00/M output and blends to $1.52/M; 6.1 Terra blends to $0.645/M. The cache read drops from 10% of input to 5%, as it did between GPT-6 Sol and GPT-6.1 Sol. OpenAI's migration advice is to compare both on representative images and workflows at the same reasoning effort, and to move tool calls from Chat Completions to the Responses API. GPT-5.6 Terra stays on the price list with no deprecation date.Q · 03 When does long-context pricing apply? +
When a prompt exceeds
272K input tokens. The whole request then bills at $2.00/M input, $0.10/M cached input and $7.50/M output - input and cache rates double, output rises by half.Q · 04 How much cheaper are Batch and Flex? +
Both are half the standard card:
$0.50/M input and $2.50/M output, with cached input at $0.025/M. Fast mode runs at double standard, $2/M and $10/M.Q · 05 How does it compare with GPT-6.1 Sol and GPT-6 Luna? +
GPT-6.1 Sol lists at
$2.00 / $10.00 and blends to $1.29/M; GPT-6 Luna lists at $0.10 / $0.50 and blends to $0.0682/M. OpenAI describes Sol as near-Astra performance for complex coding and professional work, Terra as fast and efficient for visual reasoning, computer use and writing, and Luna as the fastest, most cost-effective tier for focused high-volume tasks.Q · 06 How does it compare with Claude Haiku 4.5? +
Claude Haiku 4.5 has the same input and output sticker,
$1.00 / $5.00, but reads cache at $0.10/M against $0.05/M here, so on a cache-heavy agent blend the two come to $0.682/M and $0.645/M. Haiku 4.5 has a 200K context and no long-context card; 6.1 Terra has 1.05M with a price step above 272K.Q · 07 What is GPT-6.1 Terra Pro? +
Not a separate model. Some resellers list a "GPT-6.1 Terra Pro"; OpenAI sells no such id, and its price list and model pages carry only
gpt-6.1-terra. Earlier "Pro" listings of GPT-6 models were the base model called with reasoning.mode set to pro, which OpenAI bills at the model's standard token rates while spending more tokens.Q · 08 What is the context window? +
1.05M tokens, of which up to 922K can be input, with 128K max output and a knowledge cutoff of June 1, 2026. It takes text and image input and returns text, on the Responses and Chat Completions APIs; tool calling needs the Responses API.Q · 09 Does regional processing cost more? +
Yes, 10% on regional data-residency endpoints where they are available, as for every OpenAI model released since March 5, 2026.