GPT-6.1 Terra
Last verified October 27, 2026 · OpenAI pricing ↗$1.00/1M input · $5.00/1M output · 1.1M context · OpenAI
GPT-6.1 Terra costs $1.00 per 1M input tokens and $5.00 per 1M output tokens from OpenAI, with a 1.1M-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0035, or $35.00 per 10,000 requests. On that workload it is cheaper than 74 of the 167 other buyable models tracked here.
Count Tokens
—
Tokens
—
Input Cost
—
Output Cost
Estimate Monthly Cost
Monthly Cost Estimator
Quick:
<$0.0001/mo
Pick a preset above or enter custom usage
What GPT-6.1 Terra Costs Per Request
At $1.00 per 1M input and $5.00 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0035 | $35.00 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.011 | $110.00 |
| Coding-agent step | 30,000 / 2,000 | $0.040 | $400.00 |
GPT-6.1 Terra vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| GPT-6.1 Terra OpenAI | $1.00 | $5.00 | 1.1M | $0.011 |
| o4 Mini OpenAI | $1.10 | $4.40 | 200K | $0.011 |
| Claude Haiku 4.5 Anthropic | $1.00 | $5.00 | 200K | $0.011 |
| GLM-5.3 Zhipu | $1.40 | $4.40 | 1.0M | $0.014 |
Alternatives to GPT-6.1 Terra
Pricing Details
OpenAILaunched October 26, 2026 (changelog: visual reasoning, computer use, writing). No GPT-6 Terra existed; successor to GPT-5.6 Terra, which has no shutdown date and is still the named gpt-5-mini replacement. Card: $1.00 input, $0.05 cached (95% off), cache write $1.25 (30m) / $2.50 (12h), $5.00 output; exactly half of GPT-6.1 Sol on every line. Batch and Flex 50%: $0.50 / $0.025 / $0.625 / $2.50. Fast 2x: $2.00 / $0.10 / $2.50 / $10.00, identical to Sol Standard. No Ultrafast. LONG CONTEXT: over 272K input the whole request bills $2.00 / $0.10 / $2.50 / $7.50 (Fast $4.00 / $0.20 / $5.00 / $15.00). Regional processing +10%. Context 1,050,000 (922K input + 128K output). Knowledge cutoff June 1, 2026. Reasoning effort none / low / medium (default) / high / xhigh / max; unlike Sol 6.1 it supports none. Chat Completions, Responses, Batch; tool calling Responses only; no fine-tuning. Artificial Analysis Intelligence Index (read 2026-10-27), score and cost per task: max 48 $0.40 (130M output tokens), xhigh 45 $0.19, high 44 $0.13, medium 41 $0.10, low 36 $0.05, non-reasoning 33 $0.11; 90.9 tok/s at max. OpenAI-reported via press (launch post not directly readable): Terminal-Bench 4.0 max 50.3% vs GPT-5.6 Terra 21.5%. AVAILABILITY: ChatGPT Work and Codex; GitHub Copilot GA 2026-10-26 at list per-token rates; Amazon Bedrock GA 2026-10-26, AWS prints no rate, LiteLLM carries Global at list and US in-region at 1.1x. Model ID: gpt-6.1-terra.
Input / 1M tokens
$1
Output / 1M tokens
$5
Context Window
1.1M
Max Output
128K
Price History
Launched at current price on 2026-10-26. No price changes recorded since.
Frequently Asked Questions
Common questions about GPT-6.1 Terra pricing and usage
How much does GPT-6.1 Terra cost?
GPT-6.1 Terra costs $1 per 1 million input tokens and $5 per 1 million output tokens. This pricing is set by OpenAI.
What tokenizer does GPT-6.1 Terra use?
GPT-6.1 Terra uses the o200k_base tokenizer. This is OpenAI's latest tokenizer, optimized for efficiency with a vocabulary of ~200,000 tokens.
What is GPT-6.1 Terra's context window?
GPT-6.1 Terra supports a context window of 1.1M tokens (1,050,000 tokens). The maximum output length is 128K tokens.
How does GPT-6.1 Terra compare to other models?
On an 8,000-token-in, 600-token-out RAG answer, GPT-6.1 Terra costs $0.011 per request. The nearest-priced alternatives cost: o4 Mini (OpenAI) $0.011, Claude Haiku 4.5 (Anthropic) $0.011, GLM-5.3 (Zhipu) $0.014. The table above lists their full rates and context windows.
How do I count tokens for GPT-6.1 Terra?
Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for GPT-6.1 Terra using the o200k_base tokenizer.