DeepSeek's V4.1-Flash-1017, released on Oct 17, topped OpenRouter's weekly ranking (Oct 19-25) with 33.6 trillion tokens of usage, up 801% week over week. The updated version, based on the Sep 10 V4.1 Flash, optimizes code, agent, and visual tasks, while the older V4.1 Flash saw a 45% weekly decline.
RespanAI announced that its open-weight decision model Span-02 is now available on OpenRouter, supporting text and image inputs and returning a choice, yes/no/unknown, or a score with probabilities. It is priced at $0.01 per million input tokens with free output, a 131K context window, and a Rust inference engine that is 7x faster than vLLM.
Krea AI's new image editing model Krea 3 is now live on OpenRouter, accepting 1–4 reference images plus a prompt to produce native 2K edited images, with most edits finishing in under 8 seconds end to end.
OpenRouter launched OpenRouter Armor in beta. The tool uses typesafeai's Jev model to intercept out-of-policy tool calls before agents execute them, with better performance than Claude Code's auto classifier at a lower cost.
OpenRouter announced the general availability of Private Endpoints, which provide dedicated endpoints for reserved capacity and fine-tuned models. These endpoints are callable like any other model, visible only to the organization, and automatically fall back to shared capacity when needed. The feature is available to Enterprise plan customers.
Perplexity's open-weights multimodal decision model Decider v1.1 is now live on OpenRouter, accepting text, JSON, or image inputs and returning typed answers with probabilities, priced at $0.02 per million input tokens with free output.
ElevenLabs has officially launched on OpenRouter, offering 9 text-to-speech models supporting 90+ languages and 2 speech-to-text models with speaker labels and word-level timestamps. All ElevenLabs models are 50% off on OpenRouter until October 19, 8am PT.
Google AI Developers' Nano Banana 2.1 model is now live on OpenRouter, offering pro-level image generation and editing at Flash speed with significant improvements in visual design, mask-based editing, and subject consistency over previous Nano Banana models.
Black Forest Labs has released its new flagship image model, FLUX 3 Image, now available on OpenRouter. The model supports pixel-level multi-turn editing, bounding box layout, up to 4K generation, and up to 10 reference images, with commercial weights for enterprise and open weights coming in the following weeks.
Microsoft AI's MAI-Voice-2.1 and MAI-Voice-2.1-Flash speech models are now available on OpenRouter, supporting the same voice across 23 languages with native accents, priced at $22 and $15 per million characters respectively, for real-time voice and audio content use cases.