GPT-5.6 Terra API pricing
Updated
Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), 4 tie for the lowest blended standard price for GPT-5.6 Terra; OpenAI charges USD 2 per 1M input tokens and USD 12 per 1M output tokens. The median across 6 standard prices is USD 2 / USD 12. That is OpenAI's own API. Each price is read from the provider's own pricing page.
What does OpenAI charge for GPT-5.6 Terra?
- Input
- USD 2
- Cached input
- USD 0.20
- Output
- USD 12
- Blended 3:1
- USD 4.50
USD per 1M tokens on OpenAI, model gpt-5.6-terra, standard tier. Source, checked 2026-11-14.
Other OpenAI tiers: batch USD 1 / USD 6 · flex / spot USD 1 / USD 6 · fast USD 4 / USD 24.
Is a host cheaper than OpenAI? They tie. DigitalOcean and OpenAI's own API both work out at USD 4.50 per 1M tokens on the 3:1 blend.
GPT-5.6 Terra price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 25% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | OpenAI tied cheapest makergpt-5.6-terraNotes and source quoteShort context (up to 272K input tokens); longer prompts bill at the long-context rate. “| gpt-5.6-terra | $2.00 | $12.00 | $0.20 | $2.50 | $5.00 | $4.00 | $18.00 | $0.40 | $5.00 | $10.00 |” | USD 2 | USD 0.20 | USD 12 | USD 4.50 | not stated | not stated | OpenAI page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | DigitalOcean tied cheapestNotes and source quotePrompts ≤ 272K tokens; long-context rates are higher. “GPT-5.6 Terra — Processing modePrompt lengthInputOutputCache writeCache read: Standard ≤ 272K tokens$2.00$12.00$2.50$0.20” | USD 2 | USD 0.20 | USD 12 | USD 4.50 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | Microsoft Azure tied cheapestNotes and source quoteAzure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $2.5 per 1M. “GPT-5.6-terra (short context) Global Input: $2 | Cached Input: $0.20 | Cache writes: $2.50 | Output: $12” | USD 2 | USD 0.20 | USD 12 | USD 4.50 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | Perplexity tied cheapestopenai/gpt-5.6-terraNotes and source quoteThird-party model resold through the Perplexity Agent API. Prompts over 272k tokens: 4.00 input, 18.00 output. Cached price derived from "90% off input". “`openai/gpt-5.6-terra` | 2.00 (≤272k) 4.00 (>272k) | 12.00 (≤272k) 18.00 (>272k) | 90% off input” | USD 2 | USD 0.20 | USD 12 | USD 4.50 | not stated | not stated | Perplexity page checked 2026-11-15 re-checked 2026-11-16 |
| 5 | Amazon Bedrockopenai.gpt-5.6-terraNotes and source quoteBedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. Global CRIS: $2.00 / cache read $0.20 / $12.00. Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card. “In-Region | $2.20 | $2.75 | $0.22 | $13.20” | USD 2.20 | USD 0.22 | USD 13.20 | USD 4.95 | 1,050,000 | not stated | Amazon Bedrock page checked 2026-11-14 re-checked 2026-11-16 |
| 6 | GMI Cloudopenai/gpt-5.6-terraNotes and source quoteLong-prompt tier: prompts over 272,000 tokens cost 5 in / 22.5 out. “Price ≤ 272k token Input $2.50 Output $15.00 Cache Read $0.25 Cache Write $3.125 > 272k token Input $5.00 Output $22.50” | USD 2.50 | USD 0.25 | USD 15 | USD 5.625 | 1,050,000 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| — | OpenAI maker batchgpt-5.6-terraNotes and source quoteShort context (up to 272K input tokens); longer prompts bill at the long-context rate. Batch API (asynchronous). “| gpt-5.6-terra | $1.00 | $6.00 | $0.10 | $1.25 | $2.50 | $2.00 | $9.00 | $0.20 | $2.50 | $5.00 |” | USD 1 | USD 0.10 | USD 6 | USD 2.25 | not stated | not stated | OpenAI page checked 2026-11-14 re-checked 2026-11-16 |
| — | OpenAI maker flex / spotgpt-5.6-terraNotes and source quoteShort context (up to 272K input tokens); longer prompts bill at the long-context rate. Flex processing. “| gpt-5.6-terra | $1.00 | $6.00 | $0.10 | $1.25 | $2.50 | $2.00 | $9.00 | $0.20 | $2.50 | $5.00 |” | USD 1 | USD 0.10 | USD 6 | USD 2.25 | not stated | not stated | OpenAI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DigitalOcean flex / spotNotes and source quotePrompts ≤ 272K tokens; long-context rates are higher. “GPT-5.6 Terra — Processing modePrompt lengthInputOutputCache writeCache read: Flex Mode ≤ 272K tokens$1.00$6.00$1.25$0.10” | USD 1 | USD 0.10 | USD 6 | USD 2.25 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
| — | Microsoft Azure flex / spotNotes and source quoteAzure OpenAI Global deployment, "Flex Pricing (1M Tokens)" column. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $1.25 per 1M. “GPT-5.6-terra (short context) Global Input: $1 | Cached Input: $0.10 | Cache writes: $1.25 | Output: $6” | USD 1 | USD 0.10 | USD 6 | USD 2.25 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| — | Microsoft Azure priorityNotes and source quoteAzure OpenAI Global deployment, "Priority Processing (1M Tokens)" column. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $5 per 1M. “GPT-5.6-terra (short context) Global Input: $4 | Cached Input: $0.40 | Cache writes: $5 | Output: $24” | USD 4 | USD 0.40 | USD 24 | USD 9 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| — | OpenAI maker fastgpt-5.6-terraNotes and source quoteShort context (up to 272K input tokens); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing). “| gpt-5.6-terra | $4.00 | $24.00 | $0.40 | $5.00 | $10.00 | $8.00 | $36.00 | $0.80 | $10.00 | $20.00 |” | USD 4 | USD 0.40 | USD 24 | USD 9 | not stated | not stated | OpenAI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DigitalOcean fastNotes and source quotePrompts ≤ 272K tokens; long-context rates are higher. “GPT-5.6 Terra — Processing modePrompt lengthInputOutputCache writeCache read: Fast Mode ≤ 272K tokens$4.00$24.00$5.00$0.40” | USD 4 | USD 0.40 | USD 24 | USD 9 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Other tiers (batch, flex / spot, priority and fast): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does GPT-5.6 Terra cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| OpenAI (maker) | USD 298.80 | USD 530.40 | USD 1,926 |
| DigitalOcean | USD 298.80 | USD 530.40 | USD 1,926 |
| Microsoft Azure | USD 298.80 | USD 530.40 | USD 1,926 |
| Perplexity | USD 298.80 | USD 530.40 | USD 1,926 |
| Amazon Bedrock | USD 328.68 | USD 583.44 | USD 2,119 |
| GMI Cloud | USD 373.50 | USD 663.00 | USD 2,408 |
For the support chatbot, the cheapest price (OpenAI and 3 others, tied, USD 298.80 a month) saves USD 0 against the median (USD 298.80). For the coding agent the gap is USD 0 a month.
Which GPT-5.6 Terra provider is cheapest for your traffic?
OpenAI, DigitalOcean, Microsoft Azure and Perplexity share the lowest input price (USD 2) and the lowest output price (USD 12), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| OpenAI (maker) | USD 4.50 cheapest | USD 3.825 cheapest | USD 3.285 cheapest |
| DigitalOcean | USD 4.50 cheapest | USD 3.825 cheapest | USD 3.285 cheapest |
| Microsoft Azure | USD 4.50 cheapest | USD 3.825 cheapest | USD 3.285 cheapest |
| Perplexity | USD 4.50 cheapest | USD 3.825 cheapest | USD 3.285 cheapest |
| Amazon Bedrock | USD 4.95 | USD 4.207 | USD 3.613 |
| GMI Cloud | USD 5.625 | USD 4.781 | USD 4.106 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
All 6 providers publish a cached-input price below the input price: OpenAI (90% off), DigitalOcean (90% off), Microsoft Azure (90% off), Perplexity (90% off), Amazon Bedrock (90% off), GMI Cloud (90% off).
Amazon Bedrock and GMI Cloud state a context window of 1,050,000 tokens; OpenAI, DigitalOcean, Microsoft Azure and Perplexity do not state one.
Estimate your own bill
- LLM API cost calculator with GPT-5.6 Terra preloaded: your traffic and cache rate, against any of 429 models.
- GPT token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does GPT-5.6 Terra compare with other OpenAI models?
The OpenAI models whose cheapest standard price is closest to GPT-5.6 Terra's (USD 4.50 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| GPT-4o | USD 2.50 | USD 10 | — | 2 |
| GPT-5.2 | USD 1.75 | USD 14 | — | 3 |
| GPT-5.3 Codex | USD 1.75 | USD 14 | — | 3 |
| GPT-6 Sol | USD 2 | USD 10 | 1,050,000 | 6 |
| GPT-6.1 Sol | USD 2 | USD 10 | 1,050,000 | 6 |
| GPT-5.4 | USD 2.50 | USD 15 | 1,050,000 | 4 |
Priced closest from other makers: Gemini 3.1 Pro Preview (Google, USD 4.50) · Claude Sonnet 5 (Anthropic, USD 4) · Claude Sonnet 5.5 (Anthropic, USD 4).
Compare GPT-5.6 Terra with
- GPT-6.1 Terra vs GPT-5.6 Terra: API price side by side
- GPT-5.6 Sol vs GPT-5.6 Terra: API price side by side
- GPT-5.6 Terra vs GPT-5.6 Luna: API price side by side
- GPT-5.6 Terra vs GPT-5.5: API price side by side
Also compared: vs GPT-6.1 Terra · vs GPT-5.6 Sol · vs GPT-5.6 Luna · vs GPT-5.5.
Every GPT-5.6 Terra price comparison · All model-vs-model price comparisons
All 429 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the GPT-5.6 Terra API cost per token?
From USD 2 per 1M input tokens (USD 0.000002 per token) and USD 12 per 1M output tokens (USD 0.000012 per token) at the lowest standard prices we found. The median of 6 standard prices is USD 2 input and USD 12 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for GPT-5.6 Terra?
Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), 4 are tied for the lowest price: OpenAI, DigitalOcean, Microsoft Azure and Perplexity, each USD 4.50 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 2 (OpenAI and 3 others, tied); for output alone, USD 12 (OpenAI and 3 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Is GPT-5.6 Terra cheaper from a host than from OpenAI?
They tie. DigitalOcean and OpenAI's own API both work out at USD 4.50 per 1M tokens on the 3:1 blend.
Does GPT-5.6 Terra have cached input pricing?
All 6 standard prices include one. The lowest is USD 0.20 per 1M at OpenAI; the median is USD 0.20. Providers without one bill cached input at the input price. What cached input means.
What is the GPT-5.6 Terra context window?
1,050,000 tokens on every provider that states it.
How much does a coding agent cost per month on GPT-5.6 Terra?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 1,926 a month at OpenAI, USD 1,926 at the median price and USD 2,408 at GMI Cloud. Try your own numbers.
Is there a batch, flex or priority price for GPT-5.6 Terra?
Yes: batch from OpenAI at USD 1 / USD 6; flex / spot from OpenAI at USD 1 / USD 6; priority from Microsoft Azure at USD 4 / USD 24; fast from OpenAI at USD 4 / USD 24 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is GPT-5.6 Terra free to use through an API?
No provider in our data lists a free price for GPT-5.6 Terra as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.