GPT-6 Luna via the Tokenator API
What the model is for
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.
Specification
| Full name | GPT-6 Luna |
| API ID | gpt-6-luna |
| Model vendor | OpenAI |
| Type | Text model (chat / completions) |
| Context window | 1.05M tokens |
| Max output | 128K tokens |
| Image input | yes |
| Tokenator usage multiplier | 0.4× |
| Input modalities | text, image, file |
| Aliases | cursor-gpt-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 | 23.5 |
| Vals Finance Index (Vals AI) | 53.1% |
| Vals Index (Vals AI) | 52.3% |
| Vals Legal Index (Vals AI) | 62.2% |
| Vals Science Index (Vals AI) | 28.4% |
| Code Migration v1.1 (Vals AI) | 46.7% |
| IOI (Vals AI) | 55.6% |
| ProgramBench (Vals AI) | 0.5% |
| SWE-bench Multimodal (Vals AI) | 37.5% |
| Terminal-Bench 4.0 (Vals AI) | 13.6% |
| Vibe Code Bench v1.1 (Vals AI) | 81.6% |
| ProofBench v1.1 (Vals AI) | 64% |
| BioMysteryBench (Vals AI) | 61.5% |
| MysteryMechanism (Vals AI) | 19.4% |
| Terminal-Bench-Science (Vals AI) | 4.3% |
| ClaimBench (Vals AI) | 99.2% |
| EMB v1.1 (Vals AI) | 70% |
| Finance Agent v2.1 (Vals AI) | 56.8% |
| Tax Agent Bench (Vals AI) | 19.9% |
| HLAB-Vals-1.1 (Vals AI) | 4.2% |
| Immigration (Vals AI) | 62.5% |
| Legal Research Bench (Vals AI) | 30.3% |
| MedCode (Vals AI) | 44.7% |
| MedScribe (Vals AI) | 83.7% |
| CyberBench v1.1 (Vals AI) | 76.3% |
| SRE Bench (Vals AI) | 2.7% |
| SAGE (Vals AI) | 83.4% |
| Public Benefits Bench v1.1 (Vals AI) | 57.6% |
Artificial Analysis and Vals AI data loaded into the catalog for this model.
Upstream providers
| Provider | Multiplier |
|---|---|
| AiPartners Ltd | 0.4× |
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-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-6 Luna
What is the API ID of GPT-6 Luna?
gpt-6-luna — put this into the model field of your request.
What context window does GPT-6 Luna have?
1.05M tokens; max output is 128K tokens.
How many tokens will a request cost?
(input × 0.4×) + (output × 0.4×). 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.