← Model list
GPT-5.6 Luna
openai·openai/gpt-5.6-luna·BETA·Closed·gpt-luna series·NEW
Cost-efficient GPT-5.6 model for fast, high-volume workloads
At a glance
Official price$0.20 / $1.20 per 1M
Cache read $0.02 · OpenAI
Lowest paid$0.10 / $0.60
NanoGPT Gateway · 10× spread
1 more $0 channels
Context1,050,000
⚠ Providers report 400,000–1,050,000; the table below is authoritative
Output limit128,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
Modalities
TextImagePDF
Knowledge cutoff2026-02-16
Released / updated2026-07-09 / 2026-07-09
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier max
Intelligence52.3
Value232
Coding71.4
Agentic46.9
Output speed159 tok/s
TTFT159.4 s
Cost per task$0.0471
Value formulaIQ 52.3 ÷ min blended $0.225 = 232
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 26.8 · 145 tok/s
lowIQ 33.9 · 138 tok/s
mediumIQ 38.9 · 144 tok/s
highIQ 47 · 144 tok/s
xhighIQ 50.1 · 158 tok/s
maxIQ 52.3 · 159 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 34 providers32 with public prices · 1 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kenari gpt-5-6-luna | Gateway | Free | — | — | 1,050,000 | 128,000 | ||
| NanoGPT | Gateway | $0.10 | $0.60 | $0.01 | $0.125 | 1,050,000 | 128,000 | |
| Requesty | Gateway | $0.18 tiered >272K: $0.36 | $1.08 | $0.018 | — | 1,050,000 | 128,000 | |
| Impossibl | Gateway | $0.20 tiered >272K: $0.40 | $1.20 | $0.02 | $0.25 | 1,050,000 | 128,000 | |
| OpenRouter | Gateway | $0.20 tiered >272K: $0.40 | $1.20 | $0.02 | $0.25 | 1,050,000 | 128,000 | |
| CrossModel | Gateway | $0.20 tiered >272K: $0.40 | $1.20 | $0.02 | $0.25 | 1,050,000 | 128,000 | |
| OpenAIOfficial | First-party | $0.20 tiered >272K: $0.40 | $1.20 | $0.02 | $0.25 | 1,050,000 | 128,000 | |
| OpenCode Go | Gateway | $0.20 tiered >272K: $0.40 | $1.20 | $0.02 | $0.25 | 1,050,000 | 128,000 | |
| Merge Gateway | Gateway | $0.20 | $1.20 | $0.02 | — | 1,050,000 | 128,000 | |
| Cloudflare AI Gateway | Cloud | $0.20 tiered >272K: $0.40 | $1.20 | $0.02 | $0.25 | 1,050,000 | 128,000 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1NanoGPT$39.20
2Requesty$70.56
3Impossibl$78.40
4OpenRouter$78.40
5CrossModel$78.40
6OpenAI · Official$78.40
1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to NanoGPT to save $39.20/mo (50%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark12 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | — | 62.7 | resolve rate | Source ↗ |
| Terminal-Bench | v2.1 | 84.7 | success rate | Source ↗ |
| DeepSWE | v1.1 | 67.2 | resolve rate | Source ↗ |
| GPQA Diamond | — | 92.3 | accuracy | Source ↗ |
| FrontierMath | dataset: Tier 1-3 · vv2 | 78.6 | accuracy | Source ↗ |
| BrowseComp | — | 83.3 | accuracy | Source ↗ |
| OSWorld | v2.0 | 45.6 | success rate | Source ↗ |
| MMMU Pro | variant: no tools | 78.4 | accuracy | Source ↗ |
| Agents' Last Exam | — | 50.3 | — | Source ↗ |
| Toolathlon | — | 53.4 | success rate | Source ↗ |
| Artificial Analysis Intelligence Index | variant: max · v4.1 | 51.2 | index score | Source ↗ |
| Artificial Analysis Coding Agent Index | harness: Codex · variant: max · v1.1 | 74.6 | index score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = noneeffort = loweffort = mediumeffort = higheffort = xhigheffort = maxbudget_tokenseffort = minimal
2 / 34 providers expose no reasoning control (reasoning_options: []).
Experimental modes2 items
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | OpenAI | $0.40 | $2.40 | $0.04 | $0.50 |
| pro | OpenAI | — | — | — | — |
Related models
GPT-5.6 Luna Prosame series$1.25 / $7.50GPT-5.6 Luna (Global)same series$0.22 / $1.32GPT-5.6 Luna (OpenAI)same series$0.20 / $1.20DeepSeek V4 Flashcheaper alternative$0.14 / $0.28MiMo-V2.5cheaper alternative$0.14 / $0.28Gemini 2.5 Flash-Litecheaper alternative$0.10 / $0.40Qwen Pluscheaper alternative$0.115 / $0.287
Price historyone sample accumulated per data sync
Input listOutput listMin blended