GPT-6.1 Terra vs GPT-6 Luna: API cost
Both models are in our efficient tier, based on how OpenAI describes them. GPT-6 Luna is cheaper in all 5 standard workloads priced on both.
The biggest difference is the bulk tagging workload: GPT-6.1 Terra costs $2,738 a month against $273.75 for GPT-6 Luna, 10× as much. 89% of that difference comes from input tokens: GPT-6.1 Terra charges $1.00 per million of them, against $0.10. The gap is narrowest for the cached-prompt assistant workload, where GPT-6 Luna costs 89% less.
Prices on this page last verified on Sources
Monthly cost at five standard workloads
| Workload | Tokens in / out | GPT-6.1 Terra | GPT-6 Luna | Difference a month | Pricier by | Most of the gap |
|---|---|---|---|---|---|---|
| Short chat10,000 requests a day | 1,000 / 300 | $760.42 | $76.04 | $684.38 (GPT-6 Luna cheaper) | 10× | Output tokens |
| Long-document questions1,000 requests a day | 30,100 / 500 | $991.58 | $99.16 | $892.42 (GPT-6 Luna cheaper) | 10× | Input tokens |
| Bulk tagging200,000 requests a day | 400 / 10 | $2,738 | $273.75 | $2,464 (GPT-6 Luna cheaper) | 10× | Input tokens |
| Long-form writing500 requests a day | 1,500 / 3,000 | $250.94 | $25.09 | $225.84 (GPT-6 Luna cheaper) | 10× | Output tokens |
| Cached-prompt assistant20,000 requests a day | 8,000 / 400 | $2,616 | $279.83 | $2,336 (GPT-6 Luna cheaper) | 9.3× | Input tokens |
Published prices side by side
Per million tokens, for the first price tier of each model (GPT-6.1 Terra: prompts up to 272k input tokens; GPT-6 Luna: prompts up to 272k input tokens).
| Price | GPT-6.1 Terra | GPT-6 Luna |
|---|---|---|
| Input | $1.00 | $0.10 |
| Cached input | $0.05 | $0.01 |
| Output | $5.00 | $0.50 |
| Batch input | $0.50 | $0.05 |
| Batch cached input | $0.025 | $0.005 |
| Batch output | $2.50 | $0.25 |
Why these two are compared
We only compare models in the same capability tier, read from each provider’s own description of the model. Both are in our efficient tier:
- GPT-6.1 Terra: Provider text: "A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing." Described as fast and efficient: efficient. developers.openai.com (checked )
- GPT-6 Luna: Provider text: "Our most efficient model for focused, high-volume tasks." Described as efficient and high-volume: efficient. developers.openai.com (checked )
Workload assumptions
Short chat
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Instructions | 300 | No | Short instructions, treated as uncached. |
| Message and recent turns | 700 | No | Changes with every request. |
| Total | 1,000 | None cached |
- Requests a day: 10,000
- A popular in-app assistant.
- Output tokens per request: 300
- A reply of about 220 words.
- Batch API: not used
- Real-time replies.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Long-document questions
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Document | 30,000 | No | About 22,000 words, different every time. |
| Question | 100 | No | One or two sentences. |
| Total | 30,100 | None cached |
- Requests a day: 1,000
- A research or legal team asking questions of whole documents.
- Output tokens per request: 500
- An answer of about 370 words.
- Batch API: not used
- Real-time answers.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Bulk tagging
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Instructions and labels | 300 | No | Short instructions, treated as uncached. |
| Item | 100 | No | A short text. |
| Total | 400 | None cached |
- Requests a day: 200,000
- Items such as tickets, reviews or records tagged as they arrive.
- Output tokens per request: 10
- One label.
- Batch API: not used
- Tagged as items arrive.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Long-form writing
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Brief and style notes | 1,500 | No | Different for each piece. |
| Total | 1,500 | None cached |
- Requests a day: 500
- Articles, reports or long emails drafted a day.
- Output tokens per request: 3,000
- About 2,200 words.
- Batch API: not used
- Drafts are wanted straight away.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Cached-prompt assistant
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Instructions and tool definitions | 6,000 | Yes | The same on every request, so read from the prompt cache. |
| Conversation and request | 2,000 | No | Changes with every request. |
| Total | 8,000 | 75% cached |
- Requests a day: 20,000
- A busy assistant with long instructions and tool definitions.
- Output tokens per request: 400
- A reply of about 300 words.
- Batch API: not used
- Real-time replies.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Your traffic looks different? Enter your own figures in the calculator.
Related pages
Full cost profiles
Related comparisons
Sources
Sources: developers.openai.com (checked )
Prices are list prices as each provider publishes them, used unchanged. How the figures are calculated: methodology.