For coding agents, GPT-5.6 Terra costs 10.0x as much as GPT-5.6 Luna per request ($0.084 vs $0.0084 on our measured traffic), because GPT-5.6 Terra lists at $2 input, $0.20 cached input and $12 output per million tokens against $0.20, $0.02 and $1.20 for GPT-5.6 Luna, and both charge more for long prompts.
Run any of these models in your agent from $19/month
See plans| Cost at list price | GPT-5.6 Luna | GPT-5.6 Terra |
|---|---|---|
| Prompt under 100K tokens50% of requests, 87% of input cached | $0.0032 | $0.032 |
| Prompt of 100K to 272K39% of requests, 88% of input cached | $0.0080 | $0.080 |
| Prompt over 272K tokens11% of requests, 86% of input cached | $0.034 | $0.34 |
| Average request | $0.0084 | $0.084 |
| 100 requests | $0.84 | $8.40 |
| Median session16 requests; a session ends after 10 idle minutes | $0.092 | $0.92 |
| A month of regular usemedian of 20 users active on 5+ days | $11.83 | $118 |
Each logged request priced at the vendor’s list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.
| Artificial Analysis | GPT-5.6 Luna | GPT-5.6 Terra |
|---|---|---|
| Intelligence Index10 evaluations, 0 to 100 | 37 | 42 |
| Terminal-Bench 4.0agentic coding in a terminal | 11.6% | 35.4% |
| Output speedmedian | 123 tokens/s | 135 tokens/s |
| Time to first answer tokenincludes thinking time | 117 s | 2.2 min |
Source: Artificial Analysis (artificialanalysis.ai). Measured variants: GPT-5.6 Luna (Max), speed on OpenAI; GPT-5.6 Terra (Max), speed on OpenAI. Fetched October 13, 2026. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.
GPT-5.6 Luna is superseded: GPT-6 Luna costs $0.0041 per request. GPT-5.6 Luna scores close to it on the benchmarks above, so the cheaper request is not bought with much lower ability.
Pick a winner in each dimension. You can change your vote any time.
Correctness and depth of what it produces
Tool calls, instruction-following, and multi-step tasks
Tokens per second and time-to-first-token
How much capability you get per dollar
Consistent results: fewer refusals, loops and format breaks
Setting it up? GPT-5.6 Luna: model ID, providers and agent config · GPT-5.6 Terra: model ID, providers and agent config
The agent matters as much as the model. Compare AI agents →
Every model on this page is included with Standard Compute