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 nameGPT-6 Luna
API IDgpt-6-luna
Model vendorOpenAI
TypeText model (chat / completions)
Context window1.05M tokens
Max output128K tokens
Image inputyes
Tokenator usage multiplier0.4×
Input modalitiestext, image, file
Aliasescursor-gpt-6-luna
Supported API formats/v1/chat/completions /v1/responses /v1/messages
Upstream providers1
Current statusavailable
Data updated2026-11-11

Benchmarks

Intelligence index23.5
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

ProviderMultiplier
AiPartners Ltd0.4×

A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.

Example request

curl
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.

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.