Models listed
78
Reviewed and live in this category
Worth weighing up
What goes in and out, licence terms, and whether you can host it yourself
How we treat data
Published specs only — we don't estimate numbers a vendor hasn't stated
Video-text-to-text models are a source-backed task collection in this directory. The current editorial inventory contains 78 mapped model records. Task membership is a discovery signal, not a performance ranking, deployment recommendation, or proof that every checkpoint accepts the same inputs and returns the same outputs.
Start with the model list, then open each record that matches your data, operating constraints, and intended workflow. Check the primary source, documented modalities, license, release information, and implementation notes before using a model in production.
This collection keeps unsupported pricing, availability, and benchmark claims blank. Each page remains outside the public index until an editor approves its content and related model records.
Scan the table below, then open any model for pricing, limits and the full write-up.
| Model | Capability▼ | Context | Input $/1M | Output $/1M | Speed |
|---|---|---|---|---|---|
| Gemini 3.5 Flash Lite Google | 89.4 | 1.0M | $0.30 | $2.50 | — |
| Gemini 3.6 Flash Google | 89.4 | 1.0M | $1.50 | $7.50 | — |
| Gemini 3.1 Flash Lite Google | 89.0 | 1.0M | $0.25 | $1.50 | — |
| Gemini 3.5 Flash Google | 89.0 | 1.0M | $1.50 | $9.00 | — |
| Gemini Flash Latest Google | 89.0 | 1.0M | $1.50 | $9.00 | — |
| Gemini Flash-Lite Latest Google | 89.0 | 1.0M | $0.25 | $1.50 | — |
| Deep Research Max Preview Google | 88.9 | 1.0M | $2.00 | $12.00 | — |
| Gemini Deep Research Preview Google | 88.9 | 1.0M | $2.00 | $12.00 | — |
| Gemini 3.1 Flash Lite Preview Google | 88.6 | 1.0M | $0.25 | $1.50 | — |
| Gemini 3.1 Pro Preview Google | 88.5 | 1.0M | $2.00 | $12.00 | — |
| Gemini 3.1 Pro Preview Custom Tools Google | 88.5 | 1.0M | $2.00 | $12.00 | — |
| Gemini 3 Flash Preview Google | 88.2 | 1.0M | $0.50 | $3.00 | — |
| Gemini 3 Pro Preview Google | 88.0 | 1.0M | $2.00 | $12.00 | — |
| Gemini 2.5 Flash Google | 87.2 | 1.0M | $0.30 | $2.50 | — |
| Gemini 2.5 Flash-Lite Google | 87.2 | 1.0M | $0.10 | $0.40 | — |
| Gemini 2.5 Pro Google | 87.2 | 1.0M | $1.25 | $10.00 | — |
| Muse Spark 1.1 Meta | 82.0 | 1M | $1.25 | $4.25 | — |
| Kimi K3 Moonshot AI | 80.8 | 1.0M | $3.00 | $15.00 | — |
| MiMo-V2.5 Xiaomi | 80.4 | 1.0M | $0.14 | $0.28 | — |
| Qwen3.7 Flash Alibaba | 79.1 | 1M | $0.03 | $0.13 | — |
| Qwen3.6 Flash Alibaba | 78.7 | 1M | $0.19 | $1.13 | — |
| MiMo-V2-Omni Xiaomi | 78.5 | 262.1K | $0.14 | $0.28 | — |
| Qwen3.6 27B Alibaba | 77.2 | 262.1K | $0.60 | $3.60 | — |
| Qwen3.6 35B-A3B Alibaba | 77.2 | 262.1K | $0.25 | $1.49 | — |
| Qwen3.5 122B-A10B Alibaba | 76.9 | 262.1K | $0.40 | $3.20 | — |
| Qwen3.5 27B Alibaba | 76.9 | 262.1K | $0.30 | $2.40 | — |
| Qwen3.5 35B-A3B Alibaba | 76.9 | 262.1K | $0.25 | $2.00 | — |
| Qwen3.5 397B-A17B Alibaba | 76.8 | 262.1K | $0.60 | $3.60 | — |
| Qwen3.8 Max Alibaba | 75.7 | 1M | $2.00 | $6.00 | — |
| Qwen3.8 Max Preview Alibaba | 75.6 | 1M | $1.50 | $5.00 | — |
| Kimi K2.7 Code Moonshot AI | 74.9 | 262.1K | $0.95 | $4.00 | — |
| Kimi K2.7 Code Highspeed Moonshot AI | 74.9 | 262.1K | $1.90 | $8.00 | — |
| Kimi K2.6 Moonshot AI | 74.6 | 262.1K | $0.95 | $4.00 | — |
| Kimi K2.5 Moonshot AI | 74.0 | 262.1K | $0.60 | $3.00 | — |
| Gemini Robotics-ER 1.6 Preview Google | 73.8 | 131.1K | $1.00 | $5.00 | — |
| Qwen3.7 Plus Alibaba | 73.8 | 1M | $0.50 | $3.00 | — |
| Gemini 3.1 Flash Live Preview Google | 73.7 | 131.1K | $0.75 | $4.50 | — |
| Qwen3.6 Plus Alibaba | 73.5 | 1M | $0.50 | $3.00 | — |
| Qwen3.5 Plus Alibaba | 73.3 | 1M | $0.40 | $2.40 | — |
| GLM-5V-Turbo Zhipu AI | 72.3 | 200K | $5.00 | $22.00 | — |
| MiniMax-M3 MiniMax | 72.1 | 512K | $0.30 | $1.20 | — |
| Nemotron 3 Nano Omni 30B A3B Reasoning NVIDIA | 72.1 | 256K | $0.00 | $0.00 | — |
| Qwen3.5 9B Alibaba | 71.9 | 262.1K | $0.04 | $0.15 | — |
| Step 3.7 Flash StepFun | 69.7 | 256K | $0.18 | $1.11 | — |
| Gemini 2.0 Flash Google | 66.6 | 1.0M | $0.10 | $0.40 | — |
| Gemini 2.0 Flash-Lite Google | 66.6 | 1.0M | $0.07 | $0.30 | — |
| Nemotron Nano 12B v2 VL NVIDIA | 64.2 | 128K | $0.20 | $0.60 | — |
| Gemini 1.5 Pro Google | 63.6 | 2M | $1.25 | $5.00 | 65 t/s |
| Nano Banana 2 Google | 62.5 | 131.1K | $0.50 | $60.00 | — |
| GLM-4.6V Zhipu AI | 61.5 | 128K | $0.30 | $0.90 | — |
| GLM-4.5V Zhipu AI | 56.0 | 64K | $0.60 | $1.80 | — |
| Qwen-Omni Turbo Alibaba | 42.1 | 32.8K | $0.07 | $0.27 | — |
| Gemini Embedding 2 Google | 28.8 | 8.2K | $0.20 | $0.00 | — |
| allenai/MolmoPoint-Vid-4B allenai | 5.0 | — | — | — | — |
| chenjoya/videollm-online-8b-v1plus chenjoya | 5.0 | — | — | — | — |
| DAMO-NLP-SG/VideoLLaMA3-2B DAMO-NLP-SG | 5.0 | — | — | — | — |
| DAMO-NLP-SG/VideoLLaMA3-7B DAMO-NLP-SG | 5.0 | — | — | — | — |
| Diankun/Spatial-MLLM-v1.1-Instruct-135K Diankun | 5.0 | — | — | — | — |
| jdopensource/JoyAI-VL-Interaction jdopensource | 5.0 | — | — | — | — |
| jdopensource/JoyAI-VL-Interaction-Preview jdopensource | 5.0 | — | — | — | — |
| Kwai-Keye/Keye-VL-1_5-8B Kwai-Keye | 5.0 | — | — | — | — |
| Kwai-Keye/Keye-VL-8B-Preview Kwai-Keye | 5.0 | — | — | — | — |
| llava-hf/LLaVA-NeXT-Video-7B-hf llava-hf | 5.0 | — | — | — | — |
| lmms-lab/LLaVA-Video-7B-Qwen2 lmms-lab | 5.0 | — | — | — | — |
| MCG-NJU/TimeLens2-8B MCG-NJU | 5.0 | — | — | — | — |
| MCG-NJU/VideoChat3-4B MCG-NJU | 5.0 | — | — | — | — |
| mlx-community/SmolVLM2-500M-Video-Instruct-mlx mlx-community | 5.0 | — | — | — | — |
| NemoStation/Marlin-2B NemoStation | 5.0 | — | — | — | — |
| nvidia/nemotron-labs-audio-visual-flamingo-hf nvidia | 5.0 | — | — | — | — |
| OpenGVLab/InternVideo2_5_Chat_8B OpenGVLab | 5.0 | — | — | — | — |
| OpenGVLab/VideoChat-Flash-Qwen2-7B_res448 OpenGVLab | 5.0 | — | — | — | — |
| OpenMOSS-Team/MOSS-VL-Instruct-0408 OpenMOSS-Team | 5.0 | — | — | — | — |
| OpenMOSS-Team/MOSS-VL-Realtime OpenMOSS-Team | 5.0 | — | — | — | — |
| smdesai/SmolVLM2-2.2B-Instruct-4bit smdesai | 5.0 | — | — | — | — |
| TencentARC/TimeLens-8B TencentARC | 5.0 | — | — | — | — |
| Vision-CAIR/LongVU_Qwen2_7B Vision-CAIR | 5.0 | — | — | — | — |
| yanziang/InternVideo3-8B-Instruct yanziang | 5.0 | — | — | — | — |
| yaolily/TimeChat-Captioner-GRPO-7B yaolily | 5.0 | — | — | — | — |
78 models · click a column to sort
About the capability score: a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.