Models, measured side by side
GPT-6 Luna vs GPT-6 Sol
Compare GPT-6 Luna, GPT-6 Sol by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
GPT-6 Luna
$4.50 / mo
GPT-6 Sol
$90 / mo
Performance comparison
GPT-6 Luna
38.1
GPT-6 Sol
47.6
Overview
Pricing & capacity
| Pricing & capacity | GPT-6 Luna | GPT-6 Sol |
|---|---|---|
| Input / 1M tokens | $0.10 | $2.00 |
| Output / 1M tokens | $0.50 | $10 |
| Cached input / 1M | $0.01 | $0.20 |
| Monthly cost | $4.50 | $90 |
| Context window | 1.1M | 1.1M |
| Maximum output | 128K | 128K |
Input / 1M tokens
- GPT-6 Luna
- $0.10
- GPT-6 Sol
- $2.00
Output / 1M tokens
- GPT-6 Luna
- $0.50
- GPT-6 Sol
- $10
Cached input / 1M
- GPT-6 Luna
- $0.01
- GPT-6 Sol
- $0.20
Monthly cost
- GPT-6 Luna
- $4.50
- GPT-6 Sol
- $90
Context window
- GPT-6 Luna
- 1.1M
- GPT-6 Sol
- 1.1M
Maximum output
- GPT-6 Luna
- 128K
- GPT-6 Sol
- 128K
Benchmarks & performance
| Benchmarks & performance | GPT-6 Luna | GPT-6 Sol |
|---|---|---|
| Arena Elo | 1,211 | 1,266 |
| MMLU-Pro | 75.4% | 84.6% |
| Intelligence Index | 38.1 | 47.6 |
| Humanity’s Last Exam | 38.5% | 47.9% |
| SciCode | 54.6% | 57.6% |
| Output speed | 141 tokens/s | 107 tokens/s |
| Time to first token | 95.97 s | 107.76 s |
| DesignArena rating | 1,277 | 1,300 |
| DesignArena win rate | 48.5% | 53.2% |
Arena Elo
- GPT-6 Luna
- 1,211
- GPT-6 Sol
- 1,266
MMLU-Pro
- GPT-6 Luna
- 75.4%
- GPT-6 Sol
- 84.6%
Intelligence Index
- GPT-6 Luna
- 38.1
- GPT-6 Sol
- 47.6
Humanity’s Last Exam
- GPT-6 Luna
- 38.5%
- GPT-6 Sol
- 47.9%
SciCode
- GPT-6 Luna
- 54.6%
- GPT-6 Sol
- 57.6%
Output speed
- GPT-6 Luna
- 141 tokens/s
- GPT-6 Sol
- 107 tokens/s
Time to first token
- GPT-6 Luna
- 95.97 s
- GPT-6 Sol
- 107.76 s
DesignArena rating
- GPT-6 Luna
- 1,277
- GPT-6 Sol
- 1,300
DesignArena win rate
- GPT-6 Luna
- 48.5%
- GPT-6 Sol
- 53.2%
Tools & features
| Tools & features | GPT-6 Luna | GPT-6 Sol |
|---|---|---|
| Function calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Prompt caching | Supported | Supported |
Function calling
- GPT-6 Luna
- Supported
- GPT-6 Sol
- Supported
Structured outputs
- GPT-6 Luna
- Supported
- GPT-6 Sol
- Supported
JSON mode
- GPT-6 Luna
- Supported
- GPT-6 Sol
- Supported
Reasoning
- GPT-6 Luna
- Supported
- GPT-6 Sol
- Supported
Deterministic seed
- GPT-6 Luna
- Supported
- GPT-6 Sol
- Supported
Prompt caching
- GPT-6 Luna
- Supported
- GPT-6 Sol
- Supported
API & availability
| API & availability | GPT-6 Luna | GPT-6 Sol |
|---|---|---|
| API identifier | gpt-6-luna | gpt-6-sol |
| API providers | OpenAI, OpenAI, Azure, Azure, Azure, Amazon Bedrock, OpenAI | Not listed |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- GPT-6 Luna
gpt-6-luna- GPT-6 Sol
gpt-6-sol
API providers
- GPT-6 Luna
- OpenAI, OpenAI, Azure, Azure, Azure, Amazon Bedrock, OpenAI
- GPT-6 Sol
- Not listed
Prices checked
- GPT-6 Luna
- Oct 8, 2026
- GPT-6 Sol
- Oct 8, 2026
About the models
GPT-6 Luna
Smallest, fastest GPT-6 model for high-volume classification, extraction and chat. Long-context requests bill at $0.20 input / $0.75 output per 1M.
Full pricing & detailsGPT-6 Sol
Balanced GPT-6 model: near-flagship quality at a fifth of Astra's price. Long-context requests (above 272K input) bill at $4 input / $15 output per 1M.
Full pricing & detailsComparison FAQ
GPT-6 Luna: $0.10 input and $0.50 output per million tokens. GPT-6 Sol: $2.00 input and $10 output per million tokens. The cheaper choice depends on your input-to-output ratio; a model can have a lower input rate but a higher output rate.