GPT-5.6 Luna via the Tokenator API
What the model is for
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.
Specification
| Full name | GPT-5.6 Luna |
| API ID | gpt-5.6-luna |
| Model vendor | OpenAI |
| Type | Text model (chat / completions) |
| Context window | 1M tokens |
| Max output | 128K tokens |
| Image input | yes |
| Tokenator usage multiplier | 0.7× |
| Input modalities | text, image, file |
| Aliases | cursor-gpt5.6-luna |
| Supported API formats | /v1/chat/completions /v1/responses /v1/messages |
| Upstream providers | 1 |
| Current status | available |
| Data updated | 2026-11-11 |
Benchmarks
| Intelligence index | 23.8 |
| Coding index | 71.4 |
| Agentic index | 42.1 |
| Vals Index (Vals AI) | 51.7% |
| Vals Multimodal Index (Vals AI) | 69.1% |
| Vals Science Index (Vals AI) | 25.3% |
| Code Migration (Vals AI) | 44.6% |
| IOI (Vals AI) | 61.8% |
| ProgramBench (Vals AI) | 0% |
| SkillsBench (Vals AI) | 60.4% |
| SWE-bench (Vals AI) | 93% |
| Terminal-Bench 4.0 (Vals AI) | 11.6% |
| Vibe Code Bench 1-100 (Vals AI) | 22.6% |
| Vibe Code Bench v1.1 (Vals AI) | 77.1% |
| GPQA Diamond (Vals AI) | 91.7% |
| MMLU Pro (Vals AI) | 86% |
| MMMU Pro (Vals AI) | 85% |
| ProofBench v1.1 (Vals AI) | 60% |
| BioMysteryBench (Vals AI) | 61.5% |
| MysteryMechanism (Vals AI) | 14.4% |
| Terminal-Bench-Science (Vals AI) | 0% |
| CorpFin v2 (Vals AI) | 64.2% |
| EMB (Vals AI) | 67.1% |
| Finance Agent (v2) (Vals AI) | 55% |
| MortgageTax (Vals AI) | 67.3% |
| Tax Agent Bench (Vals AI) | 24.8% |
| TaxEval v2 (Vals AI) | 76.2% |
| Harvey's Legal Agent Benchmark v1 (Vals AI) | 1.3% |
| Legal Research Bench (Vals AI) | 36.5% |
| LegalBench (Vals AI) | 84% |
| MedCode (Vals AI) | 42.4% |
| MedScribe (Vals AI) | 84.4% |
| CyberBench v1.1 (Vals AI) | 73.6% |
| SRE Bench (Vals AI) | 1.5% |
| SAGE v1 (Vals AI) | 44.2% |
| Access to Justice Benchmark (Vals AI) | 65.6% |
| Public Benefits Bench v1.1 (Vals AI) | 61.2% |
Artificial Analysis and Vals AI data loaded into the catalog for this model.
Upstream providers
| Provider | Multiplier |
|---|---|
| AiPartners Ltd | 0.7× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
curl https://api.tokenator.top/v1/chat/completions \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5.6-luna", "messages": [{"role": "user", "content": "Hello"}] }'
Compatible tools
The model can be used in any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code, Cherry Studio, DeepSeek Harness, Hermes, Pi, OpenClaw.
See also
FAQ about GPT-5.6 Luna
What is the API ID of GPT-5.6 Luna?
gpt-5.6-luna — put this into the model field of your request.
What context window does GPT-5.6 Luna have?
1M tokens; max output is 128K tokens.
How many tokens will a request cost?
(input × 0.7×) + (output × 0.7×). See the documentation for details.
Which tools support this model?
Any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code. Setup guides are in the integrations section.