GPT 6 Luna is a model from OpenAI, released on Sep 22, 2026. GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.

How much does GPT 6 Luna cost?

On the Respan gateway, GPT 6 Luna costs $0.10 per 1M input tokens and $0.50 per 1M output tokens on every provider, after gateway discounts.

Which providers serve GPT 6 Luna on Respan?

GPT 6 Luna is available through 5 providers: Azure OpenAI, Inference.net, OpenAI, OpenRouter, and Perplexity. Azure OpenAI and Perplexity require your own provider API key (BYOK).

What is GPT 6 Luna's context window?

GPT 6 Luna accepts up to 1.1M tokens of context on its largest provider route.

How do I use GPT 6 Luna with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "openai/gpt-6-luna". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is GPT 6 Luna?

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenAI at 121 tokens per second, and the lowest response latency was 3.0 seconds on Azure OpenAI. Speed varies with request size and provider.

Where does GPT 6 Luna rank on the Respan Index?

GPT 6 Luna scores 46.8 out of 100 on the Respan Index v1.1, ranking #30 of 138 models. By category: Coding 30.5, Agents 59.8, Reasoning 48.7, Knowledge & language 38.7, and Human preference 54.5. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does GPT 6 Luna score on benchmarks?

GPT 6 Luna has 22 published benchmark scores, including LiveBench Coding 79%, LiveBench Agentic Coding 51.2%, and GPQA Diamond 90.5%. Each score links to where it was published; the data is collected by llmmetric.com.

DemoBook a demo Dashboard

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Copy for agentRead docs

Providers

GPT 6 Luna API: Pricing, Benchmarks & Context Window | Respan

GPT 6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.

Input / output price: $0.10 / $0.50 per 1M
Context: 1.1M tokens
Released: Sep 22, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "openai/gpt-6-luna".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="openai/gpt-6-luna",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "openai/gpt-6-luna",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "openai/gpt-6-luna",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

5 providers, cheapest first, priced per 1M tokens after gateway discounts. BYOK routes use your own key.

Provider	Context	Input	Output	Cache read
Azure OpenAIBYOK only`azure/gpt-6-luna`	1.1M	$0.10/M	$0.50/M	$0.01/M
Inference.net`inference_net/gpt-6-luna`	922K	$0.10/M	$0.50/M	$0.01/M
OpenAI`openai/gpt-6-luna`	1.1M	$0.10/M	$0.50/M	$0.01/M
OpenRouter`openrouter/openai/gpt-6-luna`	1.1M	$0.10/M	$0.50/M	$0.01/M
PerplexityBYOK only`perplexity/openai/gpt-6-luna`	1.1M	$0.10/M	$0.50/M	$0.01/M

Is a provider down? Azure OpenAI status, OpenAI status, OpenRouter status

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

Benchmarks

The Respan Index plus 22 published scores from 6 sources, each linked to where it was published.

46.8/ 100

Respan Index#30 of 138

138 ranked models. The shaded band is this model's 95% interval, 41.3 to 52.5. DeepSeek V4 Pro and Muse Spark 1.2 fall inside it, so the gap is within the margin of error.

Published scores

Benchmark	Score	Source	Published
LiveBench CodingLiveBench	79%	LiveBench	Oct 5, 2026
DeepSWE v1.1OpenAI	66.6%	OpenAI	Sep 22, 2026
Terminal-Bench 4.0Vals AI	13.6%	Vals AI	Oct 5, 2026

Benchmark	Score	Source	Published
LiveBench Agentic CodingLiveBench	51.2%	LiveBench	Oct 5, 2026
APEX-AgentsMercor	44.3%	Mercor	Oct 5, 2026

Benchmark	Score	Source	Published
GPQA DiamondEpoch AI	90.5%	Epoch AI	Oct 5, 2026
LiveBench ReasoningLiveBench	81.8%	LiveBench	Oct 5, 2026
LiveBench Data AnalysisLiveBench	73.4%	LiveBench	Oct 5, 2026
Chess PuzzlesEpoch AI	31%	Epoch AI	Oct 5, 2026
Mystery Game PuzzlesEpoch AI	7%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
OTIS Mock AIME 2024-2025Epoch AI	98.9%	Epoch AI	Oct 5, 2026
LiveBench MathematicsLiveBench	89.1%	LiveBench	Oct 5, 2026
FrontierMath Tiers 1-3 v2Epoch AI	78.9%	Epoch AI	Oct 5, 2026
FrontierMath Tier 4 v2Epoch AI	56.1%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LiveBench LanguageLiveBench	73.8%	LiveBench	Oct 5, 2026
LiveBench Instruction FollowingLiveBench	55.9%	LiveBench	Oct 5, 2026
SimpleQA VerifiedEpoch AI	41.4%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
Furniture AssemblyEpoch AI	44.2%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1579 Elo · #27 of 94	LMArena	Oct 1, 2026
LMArena EloLMArena	1443 Elo · #62 of 141	LMArena	Oct 2, 2026
LMArena AgentLMArena	0.0135 · #23 of 48	LMArena	Oct 2, 2026

Benchmark	Score	Source	Published
SAGEVals AI	48.1%	Vals AI	Oct 5, 2026

How the Respan Index works

How GPT compares: Claude vs GPT, Gemini vs GPT, DeepSeek vs GPT

Providers

Providers

GPT 6 Luna

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Benchmarks

Respan Index#30 of 138

Published scores

Apps

GPT 6 Luna FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Providers

Providers

GPT 6 Luna

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Benchmarks

Respan Index#30 of 138

Published scores

Apps

GPT 6 Luna FAQ

What is GPT 6 Luna?

How much does GPT 6 Luna cost?

Which providers serve GPT 6 Luna on Respan?

What is GPT 6 Luna's context window?

How do I use GPT 6 Luna with the Respan gateway?

How fast is GPT 6 Luna?

Where does GPT 6 Luna rank on the Respan Index?

How does GPT 6 Luna score on benchmarks?

Works with your entire stack

Built for AI agents. Break less. Ship more.

Built for AI agents.
Break less.
Ship more.