OpenAI · Chat
GPT-5.6 Luna
Newer version: GPT-6 Luna. We compared release dates and version names in our catalogue.
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.
- llminfo IQ
- 135.2
- Maker's price
- $0.45 blended / 1M
- Max context
- 1.1M
- Listings
- 121
Evidence and sources
Advantages and trade-offs
Compared with 10 chat models, picked mainly by popularity and IQ
Advantages
Costs less than most peers
Maker's price: $0.45 blended / 1M, cheaper than 7 of 9 priced peers.
More provider options
Trade-offs
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersCapabilities
Supported operations and provider-stated features
Listings
| 922K | $1.00cache read $0.10batch $0.10 | $6.00cache write $1.25batch $0.60 | — | — | |
| 1.1M | $0.0123cache read $0.0012 | $0.0739cache write $0.0154 | — | — | |
| 1.1M | $0.10cache read $0.01 | $0.60 | — | — | |
| 922K | $0.10cache read $0.01 | $0.60cache write $0.125 | 120 | 2,594ms | |
| 1.1M | $0.10cache read $0.01 | $0.60 | — | — | |
| 1.1M | $0.12cache read $0.012 | $0.72 | — | — | |
| 922K | $0.20cache read $0.02 | $1.20cache write $0.25 | — | — | |
| 922K | $0.20cache read $0.02 | $1.20cache write $0.25 | — | — | |
| 922K | $0.20cache read $0.02 | $1.20cache write $0.25 | — | — | |
| 1.1M | $0.20cache read $0.02 | $1.20 | — | — |
Showing 10 of 105: the maker's own listing first, then the cheapest per 1M input tokens from each provider.
Also sold by Abacus, AI Router, Aihubmix, Aimlapi, Aixy, Atlascloud, Bothub, Boundless, Bumo, Cheapest Token, Cloudflare AI Gateway, Commandcode, Core42, Cortecs AI, Crossmodel, Digitalocean, Eden AI, Eurouter, Evolink, Fastrouter, Frogbot, Gisoo, Github Copilot, Gmicloud, Impossibl, Kenari, Kilo, Llmgateway, Llmgateway Providers, Lowrouter, Merge Gateway, Moneo, NanoGPT, Near AI, Neon, Netmind, Ofox, Opencode Go, Opper, Orcarouter, Perplexity, Perplexity Agent, Pioneer, Prime, Redpill, Replicate, Requesty, Routing Run, Sandbase, Sap AI Core, Snowflake Cortex, Standardcompute, Tokenmix, Venice, Vivgrid, Wavespeed, Writer, Zenmux, Zerogpu.
16 listings without a price are hidden.
Included in plans
Benchmarks
Named effort levels run from lowest to highest. Select a result to see its source details.
Agentic
Show 9 more resultsHide 9 results
Show results from 3 providers and OpenRouter's automatic routingHide results from 3 providers and OpenRouter's automatic routing
- OpenAI
- Azure
- OpenRouter's automatic routing
- Amazon Bedrock
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
- OpenAI
- OpenRouter's automatic routing
- Azure
| Benchmark | Score |
|---|---|
| Tax Agent Bench | |
| Finance Agent (v2) | |
| Harvey's Legal Agent Benchmark v1 | |
| Terminal-Bench 2.1 |
Show 2 more benchmarksHide 2 benchmarks
| Benchmark | Score |
|---|---|
| Terminal-Bench 4.0 | |
| Terminal-Bench-Science |
Multilingual
Show 14 more resultsHide 14 results
Show 34 more resultsHide 34 results
Coding
Reasoning
Show 9 more resultsHide 9 results
Show 9 more resultsHide 9 results
Human preference
| Benchmark | xHigh |
|---|---|
| Arena ELO | |
| Chinese | |
| Creative Writing | |
| Document |
Show 55 more benchmarksHide 55 benchmarks
General
Science
Show results from 3 providers and OpenRouter's automatic routingHide results from 3 providers and OpenRouter's automatic routing
- Azure
- Amazon Bedrock
- OpenRouter's automatic routing
- OpenAI
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
- Azure
- OpenAI
- OpenRouter's automatic routing
Math
Long context
Vision
Instruction following
Factuality
Knowledge
OCR
Other
Show 1 more resultHide 1 result
| Benchmark | gpt-5.6-luna: max-effort |
|---|---|
| 4: ALT_환각방지 | |
| 4 subset: haerae_bench_v1_rc | |
| 4 subset: haerae_bench_v1_wo_rc | |
| 4 subset: hrm8k |
Show 32 more benchmarksHide 32 benchmarks
| Benchmark | openai/gpt-5.6-luna: max-effort |
|---|---|
| ALT_バイアス | |
| ALT_倫理・道徳 | |
| ALT_制御性 | |
| ALT_堅牢性 |
Show 24 more benchmarksHide 24 benchmarks
Show 11 more resultsHide 11 results
Show 9 more resultsHide 9 results
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Benchmark Nusantara, ibahasa (M. Khoirul Huda), doi:10.5281/zenodo.21970463. Test results CC BY 4.0, attribution to ibahasa; aggregate results CSV only. (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · BullshitBench by Peter Gostev, MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Deep20Bench edition 1.1, Patrick Heusser. Results CC BY 4.0; native question scores and fraction-to-percent success rates. (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · Arcophos. HealthBench Hard Leaderboard. https://healthbenchhard.ai. CC BY 4.0. Source document linked on each result. (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Outback Yak Research, NepNewsBench v2 research draft. Public numerical aggregates from a candidate preview that the publisher says is not evidence of publication; no release licence assigned and none asserted here. · Hugging Face official benchmark leaderboards; licence varies by benchmark · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.
Around the web
- HN discussion 50536739Discussion
news.ycombinator.com
- HN discussion 50537787Discussion
news.ycombinator.com
- HN discussion 50545803Discussion
news.ycombinator.com
- HN discussion 50553115Discussion
news.ycombinator.com
- HN discussion 50557657Discussion
news.ycombinator.com
Also known as: aihubmix/gpt-5.6-luna, aws-mantle/gpt-5.6-luna, azure/eu/gpt-5.6-luna, azure/gpt-5.6-luna, azure/gpt-5.6-luna-2026-07-09, azure/gpt-5.6-luna@eastus2, azure/gpt-5.6-luna@swedencentral, azure/us-gov/gpt-5.6-luna, azure/us/gpt-5.6-luna, azure_ai/gpt-5.6-luna, azure_ai/gpt-5.6-luna-2026-07-09, bedrock_mantle/openai.gpt-5.6-luna, bedrock_mantle/us-gov-east-1/openai.gpt-5.6-luna, bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna, chatgpt/gpt-5.6-luna, databricks-gpt-5-6-luna, databricks/databricks-gpt-5-6-luna, github_copilot/gpt-5.6-luna, global.openai.gpt-5.6-luna, gmi/openai/gpt-5.6-luna, gpt-5-6-luna, gpt-5.6 luna, gpt-5.6 luna pro, gpt-5.6-luna-2026-07-09, gpt-5.6-luna-pro, gpt-5.6-luna-xhigh, gpt-5.6-luna-xhigh-codex-harness, gpt-5.6-luna:web, gpt-5.6-luna@eu, gpt-56-luna, openai-gpt-5.6-luna, openai-gpt-5.6-luna-pro, openai-gpt-56-luna, openai.gpt-5.6-luna, openai/gpt-5.6-luna, openai/gpt-5.6-luna-batch, openai/gpt-5.6-luna-fast, openai/gpt-5.6-luna-pro, openai/gpt-5.6-luna-pro:batch, openai/gpt-5.6-luna:batch, opencode_go/gpt-5.6-luna, perplexity/openai/gpt-5.6-luna, replicate/openai/gpt-5.6-luna, us-gov.openai.gpt-5.6-luna, us.openai.gpt-5.6-luna
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works