vision-language model

Moondream 3 Preview is a vision-language model with 9B total and 2B active parameters (mixture-of-experts), a 32K-token context window and an optional reasoning mode. OpenRouter lists it at $0.30 per 1M input tokens and $2.50 per 1M output tokens, served by Prime Intellect.

Moondream has released Moondream 3.1, a mixture-of-experts vision-language model with 9B total and 2B active parameters and a 32K-token context window. It is listed on OpenRouter at $0.30 per 1M input tokens and $2.50 per 1M output tokens, with an optional reasoning mode.

OpenBMB has released MiniCPM-V 4.7 1B, a 1B-parameter multimodal model for single-image, multi-image and video understanding on phones, tablets and local hardware. OpenBMB claims it substantially outperforms Qwen3.5 0.8B in overall score and inference efficiency in Instruct mode. Benchmark figures, context window and training cutoff are not given in the available model card text.

Perceptron has released Mk1.5, a perception model built for physical agents that accepts text, image, video, and audio input and returns text alongside structured spatial annotations. It succeeds Mk1 and is priced at $0.15 per 1M input tokens and $1.50 per 1M output tokens.

Liquid AI has released LFM2.5-VL-3B-DSpark, a 280M-parameter speculative decoding drafter for its LFM2.5-VL-3B vision-language model. The company claims decode speedups up to 3.13x on Apple silicon and 2.66x on H100 GPUs, with day-one support for llama.cpp, MLX-VLM, and SGLang.

InclusionAI has released Ling 3.0 Flash VL, a vision-language extension of its 124B total-parameter, 5.5B active Mixture-of-Experts model. The model adds native image and video understanding, supports a 131K token context window, and is priced at $0.06 per 1M input tokens and $0.18 per 1M output tokens via OpenRouter.

Alibaba has released Qwen-Drive 1.0, a driving model built on Qwen3.5-4B that handles spatial perception, route planning, and cockpit dialogue in a single system. Reinforcement learning cut the rate of off-road driving errors in simulation from 24 percent to 12 percent, though the model's stated reasoning doesn't always match its actual maneuvers.

Alibaba's Qwen team has released FP8-quantized weights for Qwen3.8-27B, a 27-billion-parameter dense vision-language model with native 262,144-token context extensible to 1 million tokens. The model claims gains over its Qwen3.6 and Qwen3.7 predecessors on coding, agentic, and multimodal benchmarks.

Alibaba's Qwen team has released Qwen3.8-27B, a 27-billion-parameter dense vision-language model with 262,144-token native context extensible to 1 million tokens. The model shows gains over Qwen3.6-27B and Qwen3.7-Plus across coding, agentic, and multimodal benchmarks, according to Alibaba.

Liquid AI has released LFM2.5-VL-3B, a 3.1-billion-parameter vision-language model built for on-device deployment. The model claims leading performance in its size class on grounding, screen understanding, and tool use, while running at 228 tokens/s on an Apple M5 Max.

Microsoft has released Mage-VL, a codec-native multimodal foundation model built on a from-scratch 4B-parameter visual encoder paired with Qwen3-4B-Instruct-2507. The model claims up to 3.5x inference speedup over uniform frame sampling and outperforms Qwen3-VL-4B on video and temporal-grounding benchmarks, according to Microsoft.

Alibaba has released Qwen3.7 Flash, a vision-language reasoning model with a 1 million token context window aimed at multimodal agents, visual coding, and computer-use tasks. The model is priced at $0.03 per 1M input tokens and $0.13 per 1M output tokens and is available through OpenRouter.

NASA's Jet Propulsion Laboratory ran a 4-bit quantized version of Google's Gemma 3 4B on board a Loft Orbital YAM-9 satellite, marking the first in-orbit demonstration of a vision-language model analyzing imagery from a satellite's own sensor. The unmodified open-weights model hit 88 percent accuracy on a 7,960-image benchmark and ran live capture tests over Toulouse, France and coastal Argentina.