He says OpenRouter routes Batch API requests to the cheapest provider, and that callers can use /chat/completions, /responses, or /messages on all models. Requests can be polled for a full response without a files API, and bring-your-own-key works.
OpenRouter has integrated Perplexity AI's open-weights multimodal decision model, Perplexity Decider v1.1 (pplx-decider-v1.1-27b). The model is priced at $0.02 per million input tokens with 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.
OpenRouter has added Anthropic's Claude Haiku 5.5 to its platform, noting it is the first Haiku model to support reasoning efforts, runs at roughly 75% lower cost than its predecessor, and achieves over 100 tokens per second.