MODEL PROFILE

Reka Edge

rekaai · reka-edge

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...

Text generationstructured_outputstools
Context window16,384 Token
Input → OutputImage、Text、Video → Text
Model weightsOpen weights
Profile updated2026/11/8 19:27:55
OVERVIEW

Model overview

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...

The summary below is compiled from sources by an AI model, not our own testing. Verify selection decisions against original sources and your workload.

Key features

  • 7B parameter multimodal vision-language model supporting image, video, and text inputs
  • Optimized for efficient image understanding with industry-leading performance in that domain
  • Supports structured outputs and tool integration

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
OpenRouter · rekaai/reka-edge ↗USD 0.1USD 0.1Per million tokens2026/11/2 06:25:23

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

What modalities does Reka Edge accept as input?

Reka Edge accepts image, video, and text inputs.

What is the context length of Reka Edge?

The context length is 16,384 tokens.

Where can I access Reka Edge?

It is available via OpenRouter (https://openrouter.ai/rekaai/reka-edge) and Hugging Face (https://huggingface.co/RekaAI/reka-edge-2603).

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:other。模型介绍与第三方评测均以原来源的具体版本和方法为准。