GPT-6.1 Terra Pro vs GPT-6 Luna: API Pricing, Limits & Cost Delta
Side-by-side 2026 engineering comparison between OpenAI GPT-6.1 Terra Pro and OpenAI GPT-6 Luna—covering uncached input, cached prefix reads, output rates, max completion tokens, and live 30-day workload savings.
Interactive Workload Cost Delta Simulator
Side-by-Side Unit Price & Capability Matrix
| Dimension | GPT-6.1 Terra Pro | GPT-6 Luna |
|---|---|---|
| Provider & Release Date | OpenAI (2026-10-26) | OpenAI (2026-09-22) |
| Primary Workload Tier | Frontier Reasoning | Coding & Agent |
| Uncached Input ($ / 1M tokens) | $1 | $0.1 |
| Cached Prompt Read ($ / 1M tokens) | $0.05 | $0.01 |
| Output Completion ($ / 1M tokens) | $5 | $0.5 |
| 50% Async Batch API | Supported | Supported |
| Context Window (tokens) | 1,050,000 | 1,050,000 |
| Max Output Tokens | 128,000 | 128,000 |
| Function / Tool Calling | Supported | Supported |
| Strict JSON Schema Outputs | Supported | Supported |
| Reasoning Token Mode | Supported | Supported |
| Accepted Input Modalities | text, file, image | text, file, image |
Decision Rubric: When to Pick GPT-6.1 Terra Pro vs GPT-6 Luna
When to choose GPT-6.1 Terra Pro (OpenAI)
Select GPT-6.1 Terra Pro when your workload prioritizes its Frontier Reasoning profile ($1/1M input, $0.05/1M cached read, $5/1M output) with up to 1,050,000 context tokens and 128,000 max output tokens (50% Batch API supported).
GPT-6.1 Terra Pro full pricing sheet →When to choose GPT-6 Luna (OpenAI)
Select GPT-6 Luna when your workload prioritizes its Coding & Agent profile ($0.1/1M input, $0.01/1M cached read, $0.5/1M output) with up to 1,050,000 context tokens and 128,000 max output tokens (50% Batch API supported).
GPT-6 Luna full pricing sheet →Frequently Asked Questions
Is GPT-6.1 Terra Pro cheaper than GPT-6 Luna for production API workloads?
On standard uncached rates, GPT-6.1 Terra Pro bills $1/1M input and $5/1M output versus GPT-6 Luna at $0.1/1M input and $0.5/1M output. On a typical 1,000 calls/day workload (4,000 input tokens at 50% cache hit + 800 output tokens), GPT-6 Luna saves $164.40/month (90% lower).
How do GPT-6.1 Terra Pro and GPT-6 Luna compare on context window and max output tokens?
GPT-6.1 Terra Pro offers a 1,050,000-token context window with 128,000 max output tokens (text, file, image), while GPT-6 Luna provides a 1,050,000-token context window with 128,000 max output tokens (text, file, image).
Can I switch between GPT-6.1 Terra Pro and GPT-6 Luna with strict JSON Schema tool calling?
Both models can be evaluated locally in DevToken: GPT-6.1 Terra Pro (tools: Supported, strict JSON Schema: Supported) vs GPT-6 Luna (tools: Supported, strict JSON Schema: Supported). Always verify rate-limit headroom in the 429 Calculator before cutover.