←Search results

Search “Multimodal”

By relevance · Total 801 results Clear search

Saturday

Sunday

  1. Story2 reports · 1 facts

    OpenRouter launches RespanAI decision model Span-02

    OpenRouter announced the launch of RespanAI's open-weight decision model Span-02. The model accepts text and image inputs and returns options, yes/no/unknown, or scores with probabilities in response to custom questions; pricing is $0.01 per million input tokens with free output, and the context length is 131K. OpenRouter later clarified that Span-02 runs on the OpenRouter Decisions API, uses the same request format as other decision models, and switching requires only changing one line with the model name; images and text are placed in the same state, with a maximum of 4 images per request. Respan previously introduced Span-02 as supporting anytime inference, returning the current best decision once a deadline is given, allowing configurable reasoning duration, and supporting multimodal viewing of images and screens. The model is now live on OpenRouter.

    OpenRouter announced the launch of RespanAI's open-weight decision model Span-02. The model accepts text and image inputs and returns options, yes/no/unknown, or scores with probabilities in response to custom questions; pricing is $0.01 per million input tokens with free output, and the context length is 131K. OpenRouter later clarified that Span-02 runs on the OpenRouter Decisions API, uses the same request format as other decision models, and switching requires only changing one line with the

    Matched fieldsSummary

  2. Story1 reports · 1 facts

    Apertus 1.5 supports native image and audio input

    On October 15, 2026, Swiss AI released Apertus 1.5, adding native image and audio understanding capabilities on top of 1.0. The model converts images and audio into discrete tokens via early fusion and feeds them into the same sequence as text, with the architecture unchanged; it only understands multimodal input and outputs text only. The official announcement also states that Apertus 1.5 adds a thinking mode and a 262,144-token context window, four times larger than 1.0. According to the official statement, the 8B version outperforms open-source models of the same scale on instruction-following and multilingual tasks, its multimodal performance is close to Gemma 4 12B, and the training data mixture, preference data, and intermediate checkpoints for each stage are also released. There are currently no subsequent developments.

    On October 15, 2026, Swiss AI released Apertus 1.5, adding native image and audio understanding capabilities on top of 1.0. The model converts images and audio into discrete tokens via early fusion and feeds them into the same sequence as text, with the architecture unchanged; it only understands multimodal input and outputs text only. The official announcement also states that Apertus 1.5 adds a thinking mode and a 262,144-token context window, four times larger than 1.0. According to the offic

    Matched fieldsSummary

Friday

Wednesday

Thursday

Monday