Tasks and inputs
Reka Edge is listed for Image-text-to-text, Text generation, Video-text-to-text. It accepts image, text, video and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Reka Edge from rekaai: Multimodal model for analyzing text, images, documents, and rich media.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Multimodal model for analyzing text, images, documents, and rich media. The registry places it in the reka family with a release date of 2026-03-20. This profile describes its documented interface and how to evaluate it for the intended task.
The recorded inputs are image, text and video, with text output. The registry lists a 16,384-token context window and up to 14,745 output tokens. It also declares function calling and structured output. These are specifications, not a measured quality or speed ranking. A host can impose its own request limits and support a different subset of features.
The registry marks Reka Edge as an open-weight model. Check the linked checkpoint’s licence and runtime requirements before downloading or deploying it. Open weights describe availability, while licence terms determine permitted use. Local inference still requires hardware; a hosted route can charge separately.
No independently checked token rate is added from a hosting alias. Use the route’s current price and billing unit when comparing cost, including output, reasoning, cache behavior and retries where applicable.
Test photographs, screenshots and documents with the detail your application needs to read. Include small text, crowded layouts and questions whose answer is absent. Check whether the answer is supported by the image instead of accepting a plausible description.
This is a registry-sourced profile. A model-specific publisher document has not yet been confirmed; access and specifications should be checked before an integration decision. SyncDev has not independently benchmarked Reka Edge.
Browse rekaai models, explore related tasks, or compare two models using the same workload.
The registry lists AI/ML API with model ID rekaai/reka-edge. This identifies that host's route, rather than establishing a first-party publisher API ID. Check its current access, request limits and billing before integration.
Compare the model on the work you need to complete.
Reka Edge is listed for Image-text-to-text, Text generation, Video-text-to-text. It accepts image, text, video and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 16.38K context and 14.75K maximum output. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
The weights are downloadable under the publisher’s model licence. Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Gemini 4 Argon handles coding, reasoning and multimodal work with a shared 1M-token window and background long decode.
Meta
Meta’s Muse Wonder handles coding, computer use and sustained agent tasks through Meta Model API and Muse Code, with a 1M-token context.
Meta
Muse Wonder Full is Meta’s higher-capability Wonder variant for sustained coding and agent work, available through eligible Muse Code subscriptions.
Xiaomi
MiMo-V2.6-Distill-Qwen-9B is Xiaomi’s smaller downloadable checkpoint for agent research and reinforcement-learning experiments.
Sakana AI
Fugu Max from Sakana AI: Multi-agent model for routing expert agents across complex analytical tasks.
Sakana AI
Fugu Ultra v2 from Sakana AI: Quality-first multi-agent model for hard research, analysis, and competitions.