Vision APIs are useful for screenshots, receipts, product photos, and ticket attachments. What matters is whether the model accepts the image type you have, whether you need JSON out, and how wrong answers look on your own samples. Price second. The shortlist below is deliberately small — A/B a few vision-capable candidates instead of the whole catalog.
來源依據: NextModel capability mapping and OpenRouter input-modality metadata when available. · 更新日期 2026-07-01
如何使用这份名单
匹配分
先從候選名單開始，再以真實提示詞測試，並在接入正式環境路由前比較月度成本。
Gemini 4 Argon via NextModel: 1M-token context; $2 / 1M tokens in / $10 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Claude Haiku 5.5 via NextModel: 1M-token context; Starting at $0.1 / 1M tokens in / $0.5 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Doubao Seedance 2.5 via NextModel: context unpublished; $0.225 / s in / — out per 1M tokens. Capabilities: streaming, vision.
Dreamina-Seedance 2.0 Fast via NextModel: context unpublished; $0.122 / s in / — out per 1M tokens. Capabilities: streaming, vision.
比較表
當你在縮小正式環境候選名單、建立備援策略或比較模型經濟性時，可使用此視圖。
| Model | Provider | Input | Output | Context | Capabilities | Best for | Latency | Status | Source |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argongoogle/gemini-4-argon | $2 / 1M tokens | $10 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 2974-10589ms | Catalog | Platform curated | |
| Claude Haiku 5.5anthropic/claude-haiku-5.5 | Anthropic | Starting at $0.1 / 1M tokens | $0.5 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1321-2017ms | Catalog | Platform curated |
| Doubao Seedance 2.5doubao/doubao-seedance-2-5-260628 | Doubao | $0.225 / s | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
| Dreamina-Seedance 2.0 Fastdreamina/dreamina-seedance-2-0-fast-260128 | Dreamina | $0.122 / s | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
| Dreamina Seedance 2.5dreamina/dreamina-seedance-2-5-260628 | Dreamina | $0.234 / s | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
| Gemini 3 Pro Image (Nano Banana Pro) gemini/gemini-3-pro-image | Gemini | $0.314 / image | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
| Gemini 3.1 Flash Image (Nano Banana 2)gemini/gemini-3.1-flash-image | Gemini | $0.151 / image | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
| Qwen-Image-2.0 CNqwen/qwen-image-2.0-cn | Qwen | $0.0287 / image | — | — | StreamingVision | image understanding, multimodal chat | 0-0ms | Catalog | Platform curated |
常見問題
Image input support, JSON mode if you need it, latency, output cost, and quality on your real images. Synthetic benchmarks lie more often than people admit.
Sometimes, for light work. Dense documents and high-accuracy extraction usually need a stronger model and a real eval set.
相关排行榜