GPT-6 Luna
OpenAI · Sep 22, 2026
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…
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
openai/gpt-oss-20b:batchgpt-oss-20b (batch) is an API model from OpenAI, released on Aug 5, 2025, with a context window of 131,072 tokens, pricing of $0.024 per million input tokens and $0.112 per million output tokens. It accepts text input and produces text output.
At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.00035.
Specs are sourced from OpenRouter and were last checked on Nov 20, 2026. Always confirm current pricing and limits with the provider before production use.
gpt-oss-20b (batch) supports a context window of 131,072 tokens.
gpt-oss-20b (batch) is listed at $0.024 per million input tokens and $0.112 per million output tokens on OpenRouter.
gpt-oss-20b (batch) was published on Aug 5, 2025.
gpt-oss-20b (batch) accepts text input and produces text output.