OpenAI reports GPT-6 Luna at 66.6% on DeepSWE v1.1

OOpenRouter9/22/2026, 11:32:25

GPT-6 Luna is the fast, low-cost tier. OpenAI reports that it scores 66.6% on DeepSWE v1.1, comparable to Claude Opus 5 and Fable 5 at medium effort for 93-96% less per task.

At higher effort, OpenAI reports that GPT-6 Luna matches GPT-5.6 Sol on factuality at about 1/100th the cost. It is available on OpenRouter.

#gpt-6-luna #openai #openrouter #deepswe #benchmarks

View original post ↗

Previous articleApple may pay up to $95 per eligible iPhone over Siri Next articleGPT-6 Sol and GPT-6 Luna are live on OpenRouter

Related AI news

OpenRouter adds OpenAI's GPT-6 Luna Decisions with 1M context and free output

OpenRouter has made OpenAI's GPT-6 Luna Decisions available on its platform, featuring a 1M context window, pricing of $0.10 per million input tokens, and free output.

OOpenRouter•10/7/2026, 13:33:04•

#openrouter #openai #decisions-api #gpt-6-luna

OpenRouter launches Model Router Benchmarks across seven routers

OpenRouter has released Model Router Benchmarks to compare seven model routers side by side across quality, speed, and cost on six benchmarks, covering routers such as Jev Router, Unbiased Pareto, and NVIDIA Switchyard.

OOpenRouter•10/6/2026, 09:29:21•

#openrouter #model-router #benchmarks

GPT-6.1 Sol Pro is available on OpenRouter

OpenRouter is offering GPT-6.1 Sol Pro, describing it as the same model in pro reasoning mode for hard, high-stakes problems where the extra cost is worth it.

OOpenRouter•9/29/2026, 10:39:51•

#gpt-6.1-sol-pro #openrouter #openai #reasoning

GPT-6.1 Sol is live on OpenRouter at $2 per million input tokens

OpenRouter is offering OpenAI’s GPT-6.1 Sol at $2 per million input tokens, $10 per million output tokens, and $0.10 per million cached input tokens. It says the model nearly matches GPT-6 Astra on agentic coding, computer use, and professional work at one-fifth of Astra’s price.

OOpenRouter•9/29/2026, 10:41:03•

#gpt-6.1-sol #openrouter #openai #model-pricing #gpt-6-astra

GPT-6 Sol and Luna carry Astra's communication style and 90% off cached input reads

OpenRouter says GPT-6 Sol and GPT-6 Luna use Astra's clearer, shorter, lower-jargon answers and OpenAI's improved prompt caching, with 90% off cached input reads.

OOpenRouter•9/22/2026, 11:34:06•

#openai #gpt-6 #openrouter #prompt-caching

Reset history AI News FAQ Usage limits RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.

Data & original project: Did Codex Reset · Licoy