GPT-5.6 Luna vs GPT-6.1 Terra: pricing and benchmarks
GPT-5.6 Luna is 80% cheaper on input tokens ($0.20 vs $1.00 per 1M). GPT-5.6 Luna is 76% cheaper on output tokens ($1.20 vs $5.00 per 1M). On our document Q&A workload (50,000 questions a month), GPT-5.6 Luna costs $116.00 a month versus $550.00 for GPT-6.1 Terra, 79% less. Epoch AI has not published a capability index score for GPT-6.1 Terra yet.
Which should you choose?
Epoch AI has not published a capability index score for GPT-6.1 Terra yet.
GPT-5.6 Luna costs $0.45 per 1M tokens (3:1 input-to-output mix) vs $2.00 for GPT-6.1 Terra, 78% less.
Pricing and specs
| GPT-5.6 Luna | GPT-6.1 Terra | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| API model ID | gpt-5.6-luna | gpt-6.1-terra |
| Input / 1M tokens | $0.20 | $1.00 |
| Cached input / 1M tokens | $0.02 | $0.05 |
| Output / 1M tokens | $1.20 | $5.00 |
| Long-context rates | $0.40 in / $1.80 out on long-context requests | $2.00 in / $7.50 out above 272K prompt tokens |
| Context window | 1.05M tokens | 1.05M tokens |
| Max output | 128K tokens | 128K tokens |
| Batch discount | 50% off | 50% off |
Benchmarks
| GPT-5.6 Luna | GPT-6.1 Terra | |
|---|---|---|
| Epoch Capabilities Index | 156.3 | — |
| GPQA Diamond· Science reasoning | 91.6% | — |
| FrontierMath (Tiers 1–3)· Advanced math | 82.1% | — |
| SimpleQA Verified· Factual accuracy | 41.0% | — |
| ARC-AGI-2· Abstract reasoning | 59.5% | — |
| DeepSWE· Coding | 67.2% | — |
| APEX-Agents· Agentic work | 43.0% | — |
Source: Epoch AI, best recorded result per model (CC BY 4.0). A dash means no published score. See all benchmarks
Monthly cost for real workloads
| Workload | GPT-5.6 Luna | GPT-6.1 Terra | Difference |
|---|---|---|---|
Support chatbot 100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each. | $78.00 | $350.00 | GPT-5.6 Luna 78% cheaper |
Document Q&A (RAG) 50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each. | $116.00 | $550.00 | GPT-5.6 Luna 79% cheaper |
Coding agent 10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens. | $53.60 | $234.00 | GPT-5.6 Luna 77% cheaper |
Cached chatbot The same 100,000-reply support chatbot, but 60% of each prompt (system prompt + conversation history) is served from the prompt cache. | $61.80 | $264.50 | GPT-5.6 Luna 77% cheaper |
Meeting notes 10,000 meetings a month summarized from ~12,000-token transcripts, ~1,000 output tokens each. | $36.00 | $170.00 | GPT-5.6 Luna 79% cheaper |
Bulk translation 200,000 short translations a month, ~800 input and ~800 output tokens each. | $224.00 | $960.00 | GPT-5.6 Luna 77% cheaper |
Content moderation 1,000,000 classifications a month, ~400 input tokens and ~80 output tokens each. | $176.00 | $800.00 | GPT-5.6 Luna 78% cheaper |
Article drafting 300 long-form articles a month written from a ~4,000-token brief and outline, ~5,000 output tokens each. | $2.04 | $8.70 | GPT-5.6 Luna 77% cheaper |
Code review bot 30,000 pull-request reviews a month, ~5,000 input tokens each (30% cached repository context) and ~700 output tokens. | $47.10 | $212.25 | GPT-5.6 Luna 78% cheaper |
Invoice extraction 100,000 documents a month parsed into structured JSON, ~1,200 input and ~250 output tokens each. | $54.00 | $245.00 | GPT-5.6 Luna 78% cheaper |
Estimates use standard list prices and ignore cache-write surcharges. Different tokenizers can count the same text differently, so test with your own prompts.
GPT-5.6 Luna vs GPT-6.1 Terra cost calculator
- $116.00/mo$0.0023 / req
- GPT-6.1 TerraOpenAI$550.00/mo$0.01 / req
Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.
GPT-5.6 Luna pricing notes
The GPT-5.6 model optimized for cost-sensitive, high-volume workloads.
- Cache writes are billed at $0.25 per 1M tokens.
- Fast mode costs 2x the standard rate; Flex costs half.
GPT-6.1 Terra pricing notes
OpenAI’s fast, efficient GPT-6.1 model for visual reasoning, computer use and writing, at half GPT-6.1 Sol’s price.
- Cache writes are billed at $1.25 (30-minute) or $2.50 (12-hour) per 1M tokens.
- Prompts over 272K input tokens use the long-context rates.
- Fast mode costs 2x the standard rate; Flex costs half.
Frequently asked questions
- Is GPT-5.6 Luna cheaper than GPT-6.1 Terra?
- GPT-5.6 Luna is 80% cheaper on input tokens ($0.20 vs $1.00 per 1M). GPT-5.6 Luna is 76% cheaper on output tokens ($1.20 vs $5.00 per 1M). On our document Q&A workload (50,000 questions a month), GPT-5.6 Luna costs $116.00 a month versus $550.00 for GPT-6.1 Terra, 79% less.
- Which is more capable, GPT-5.6 Luna or GPT-6.1 Terra?
- Epoch AI has not published a capability index score for GPT-6.1 Terra yet.
- How much does GPT-5.6 Luna cost per 1M tokens?
- GPT-5.6 Luna costs $0.20 per 1M input tokens and $1.20 per 1M output tokens, and $0.02 per 1M cached input tokens on OpenAI’s standard tier.
- How much does GPT-6.1 Terra cost per 1M tokens?
- GPT-6.1 Terra costs $1.00 per 1M input tokens and $5.00 per 1M output tokens, and $0.05 per 1M cached input tokens on OpenAI’s standard tier.
- Which has the larger context window, GPT-5.6 Luna or GPT-6.1 Terra?
- Both offer a 1.05M-token context window.