AI model comparison
GPT-6 Luna vs Claude Opus 5
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
OpenAI
GPT-6 Luna
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.
- Input / 1M
- $0.10
- Output / 1M
- $0.50
- Context
- 1.05M
Anthropic
Claude Opus 5
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.
- Input / 1M
- $5
- Output / 1M
- $25
- Context
- 1M
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
GPT-6 Luna
50x cheaper for a typical chat
Higher intelligence score
Claude Opus 5
50.8 vs 38.1 on Artificial Analysis
Larger context window
GPT-6 Luna
1.05M vs 1M tokens
Newer release
GPT-6 Luna
Released September 22, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
GPT-6 Luna38.1Claude Opus 550.8Coding index
GPT-6 LunaNot availableClaude Opus 578Agentic index
GPT-6 LunaNot availableClaude Opus 556.5Pricing
GPT-6 Luna vs Claude Opus 5 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | GPT-6 Luna | Claude Opus 5 |
|---|---|---|
| Input tokensPer 1M tokens | $0.10 | $5 |
| Output tokensPer 1M tokens | $0.50 | $25 |
| Cached input (read)Per 1M tokens | $0.01 | $0.50 |
| Cache writePer 1M tokens | $0.13 | $6.25 |
| Long-context pricingPer 1M tokens, for very long prompts | $0.20 in / $0.75 out above 272K | Same rate at any length |
| Web searchPer request | $0.01 | $0.01 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
GPT-6 Luna$0.45Claude Opus 5$22.50Coding task
30K in, 4K out
GPT-6 Luna$5$2.30 cachedClaude Opus 5$250$115 cachedLong document summary
150K in, 2K out
GPT-6 Luna$16$2.50 cachedClaude Opus 5$800$125 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | GPT-6 Luna | Claude Opus 5 |
|---|---|---|
| Context window | 1.05M tokens | 1M tokens |
| Max output | 128K tokens | 128K tokens |
| Input types | File, Image, Text | File, Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | Max, Extra high, High, Medium, Low, None | Max, Extra high, High, Medium, Low |
| Default reasoning effort | Medium | High |
| Release date | September 22, 2026 | July 24, 2026 |
Features
Supported features
API features available for each model.
| Metric | GPT-6 Luna | Claude Opus 5 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Not supported | Not supported |
| Stop sequences | Not supported | Supported |
| Deterministic seed | Supported | Not supported |
| Verbosity control | Supported | Supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
GPT-6 LunaView full model details- GPT-6 Luna vs DeepSeek V4.1 Flash
- GPT-6 Luna vs GLM 5.3 Flash
- GPT-6 Luna vs MiMo-V2.6-Flash
- GPT-6 Luna vs Hy4 preview
- GPT-6 Luna vs DeepSeek V4 Flash 0731
- GPT-6 Luna vs Claude Opus 5.5
- GPT-6 Luna vs GLM 5.3
- GPT-6 Luna vs DeepSeek V4 Flash 0423
- GPT-6 Luna vs Step 5 Preview
- GPT-6 Luna vs Gemini 3.8 Flash
- GPT-6 Luna vs Hy3
- GPT-6 Luna vs GPT-5.6 Luna
- GPT-6 Luna vs GPT-6.1 Sol
- GPT-6 Luna vs Muse Spark 1.3 Contributor
- GPT-6 Luna vs Claude Sonnet 5.5
- GPT-6 Luna vs MiMo-V2.6-Pro
- GPT-6 Luna vs DeepSeek V4 Pro 0813
- GPT-6 Luna vs GPT-6 Astra
- GPT-6 Luna vs Claude Fable 5.1
- GPT-6 Luna vs DeepSeek V4 Pro 0423
- GPT-6 Luna vs Solar Pro 4
- GPT-6 Luna vs GPT-6 Luna Pro
- GPT-6 Luna vs Claude Haiku 5.5
- GPT-6 Luna vs Ling 3.1 Flash
- GPT-6 Luna vs Qwen3.8 Flash
- GPT-6 Luna vs Qwen3.7 Flash
- GPT-6 Luna vs DeepSeek V4 Flash Vision Exp
- GPT-6 Luna vs GLM 5.3 FlashX
- GPT-6 Luna vs GPT-5.6 Luna Pro
Claude Opus 5View full model details- Claude Opus 5 vs Claude Opus 5.5
- Claude Opus 5 vs Claude Sonnet 5.5
- Claude Opus 5 vs Claude Fable 5.1
- Claude Opus 5 vs GPT-6 Astra
- Claude Opus 5 vs GPT-6.1 Sol
- Claude Opus 5 vs Claude Fable 5
- Claude Opus 5 vs Muse Spark 1.3
- Claude Opus 5 vs GPT-6 Sol
- Claude Opus 5 vs GPT-5.6 Sol
- Claude Opus 5 vs Kimi K3
- Claude Opus 5 vs GLM 5.3 Flash
- Claude Opus 5 vs Claude Opus 4.8
- Claude Opus 5 vs DeepSeek V4.1 Flash
- Claude Opus 5 vs Claude Opus 4.7
- Claude Opus 5 vs MiMo-V2.6-Flash
- Claude Opus 5 vs Hy4 preview
- Claude Opus 5 vs DeepSeek V4 Flash 0731
Our take
GPT-6 Luna is 50x cheaper for a typical chat. Claude Opus 5 scores higher on the Artificial Analysis Intelligence Index (50.8 vs 38.1). GPT-6 Luna has the larger context window (1.05M vs 1M tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is GPT-6 Luna or Claude Opus 5 cheaper?
GPT-6 Luna is cheaper for a typical chat (2K input tokens and 500 output tokens). GPT-6 Luna costs $0.10 per 1M input tokens and $0.50 per 1M output tokens, while Claude Opus 5 costs $5 per 1M input tokens and $25 per 1M output tokens.
Which has a bigger context window, GPT-6 Luna or Claude Opus 5?
GPT-6 Luna supports up to 1.05M tokens of context, compared with 1M for Claude Opus 5.
Is GPT-6 Luna smarter than Claude Opus 5?
On the Artificial Analysis Intelligence Index, GPT-6 Luna scores 38.1 and Claude Opus 5 scores 50.8, putting Claude Opus 5 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use GPT-6 Luna and Claude Opus 5 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see GPT-6 Luna and Claude Opus 5 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to GPT-6 Luna and Claude Opus 5 at the same time. Compare the answers side by side and keep the best one.