Skip to main content

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 priceUp to 18% off
$0.10 / $0.50$0.082 / $0.41 per 1M
Context
1.1M tokens
Released
Sep 22, 2026
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".

Read docs

Providers

8 routes from 7 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
OpenAI18% offopenai/gpt-6-luna
$0.10/M$0.082/M$0.50/M$0.41/M
Azure Foundryazure_foundry/gpt-6-luna
$0.10/M$0.50/M
Azure OpenAIazure_openai/gpt-6-luna
$0.10/M$0.50/M
Bedrockbedrock/global.openai.gpt-6-luna
$0.10/M$0.50/M
Perplexityperplexity/gpt-6-luna
$0.10/M$0.50/M

Is a provider down? ChatGPT status, Azure OpenAI status, AWS Bedrock status, Perplexity status, OpenRouter status

Pricing

Averaged across 8 routes from 7 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.10 per 1M
Average output
$0.49 per 1M
Average cache read
$0.0099 per 1M
Average cache write
$0.12 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.11/MBedrockLowest$0.082/MOpenAI

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

111tokens/sacross providers

Faster than 80% of the other 596 models on the gateway

Time to first token

Lower is better

5.2sacross providers

Faster than 19% of the other 153 models on the gateway

Response latency

Lower is better

5.8sacross providers

Faster than 28% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 25 published scores from 6 sources, each linked to where it was published.

48.6/ 100

Respan Index#46 of 176

176 ranked models. The shaded band is this model's 95% interval, 43.0 to 54.2. DeepSeek V4 Pro and GPT-5.6 Luna fall inside it, so the gap is within the margin of error.
GPT-6 Luna by category: Coding 28.4, Agents 60.0, Reasoning 57.0, Knowledge & language 38.9, Human preference 55.4
  1. 46GPT-6 Luna48.6
  2. 45DeepSeek V4 Pro49.2
  3. 47GPT-5.6 Luna48.4

Published scores

BenchmarkScore
LiveBench CodingLiveBench79%
DeepSWE v1.1OpenAI66.6%
MirrorCodeEpoch AI26.7%
Terminal-Bench 4.0Vals AI13.6%

Compare GPT-6 Luna: GPT-6 Luna vs GPT-5.6 Luna, GPT-6 Luna vs DeepSeek V4 Flash, GPT-6 Luna vs Grok 4.7, GPT-6 Luna vs GPT-4o mini, GPT-6 Luna vs GPT-5, GPT-6 Luna vs Gemini 3.6 Flash

Apps

Use GPT-6 Luna in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

GPT-6 Luna FAQ

Short answers, built from the data on this page.

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.

On the Respan gateway, GPT-6 Luna costs from $0.082 per 1M input tokens and $0.41 per 1M output tokens on OpenAI, after gateway discounts. Averaged across its 8 routes from 7 providers, it costs $0.10 per 1M input tokens and $0.49 per 1M output tokens.

GPT-6 Luna is available through 8 routes from 7 providers: OpenAI, Azure Foundry, Azure OpenAI, Bedrock, Perplexity, Inference.net, and 1 more.

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

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 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.

GPT-6 Luna scores 48.6 out of 100 on the Respan Index v1.1, ranking #46 of 176 models. By category: Coding 28.4, Agents 60.0, Reasoning 57.0, Knowledge & language 38.9, and Human preference 55.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

GPT-6 Luna has 25 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 Respan.

Certified where it counts.

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

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.