Reka Edge
Reka's small on-device-friendly multimodal model. ~7B parameters, 16k context.
Reka Edge is multimodal AI model from Custom, priced at €0.100 per 1M input tokens with a 16.4K tokens context window.
0.7
Pricing
API Integration
Use our OpenAI-compatible API to integrate Reka Edge into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("reka-edge", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("reka-edge", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("reka-edge", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive — Reka AI's Reka Edge
Reka AI was founded in mid-2022 by Dani Yogatama, Yi Tay, Donovan Ong and Qi Liu, all senior researchers from Google DeepMind, Google Brain, Apple and Facebook AI. The company is headquartered in San Francisco with engineering centres in London and Singapore. Reka has raised $58M in Series A funding led by DST Global Partners in 2023 and closed an additional Series B in 2024 at a reported near-unicorn valuation. The Reka model family is multimodal-by-design (text, image, video, audio) and is sized into three tiers: Edge (smallest), Flash (mid), Core (flagship). Reka Edge (7B parameters) was released alongside Flash and Core in early 2024 as the on-device / cost-sensitive sibling, designed to run on a single consumer GPU while preserving the multimodal capabilities that distinguish Reka from text-only competitors.
Visit Reka AI →Reka Edge is a ~7B parameter decoder-only Transformer trained on the same multimodal corpus as the larger Reka Flash and Core, comprising text, code, images, video frames and audio clips. According to the public Reka Core technical report, all three sizes share the architecture (modality encoders projecting into a shared token embedding space) but differ in scale and the proportion of training compute spent on each modality. Edge is optimised for on-device and cost-sensitive deployments, fits on a single 24 GB consumer GPU in FP16 and supports a 128K-token context window. It accepts text, image, video (up to short clips) and audio (with a learned audio encoder). On MMMU, Perception Test and VideoMME, Edge scores below Flash and Core but ahead of similarly sized open-weights multimodal baselines like LLaVA-Next 7B and InternVL 7B at launch. Edge is offered through the Reka API and Reka Playground; weights are not publicly released.
- Parameters
- 7B
- Context
- 128K tokens
- Multimodal input: text, image, short video and audio
- 128K-token context window
- Runs on a single 24 GB consumer GPU in FP16
- JSON output and tool use
- Multilingual coverage across 32+ languages
- Hosted through Reka API and Reka Playground
- Cost-efficient pricing tier in the Reka family
- Best for: cost-sensitive multimodal apps, on-device experiments, edge AI
Multimodal pretraining over a curated corpus of text, code, images, video frames and audio with progressive curriculum, identical mix to Reka Core but smaller compute budget.
License: Proprietary commercial API. Generated outputs may be used commercially under the Reka terms.
Known limitations
- Closed weights, hosted only
- Smaller capacity than Flash and Core gives lower quality on hard reasoning
- Video clips supported only up to short durations
- Smaller ecosystem and tooling than OpenAI / Anthropic
- No public fine-tuning for external customers
Frequently asked questions
Related Models
View all MultimodalClaude Opus 4.7
Anthropic's April 2026 flagship. 87.6% on SWE-bench Verified, 3x higher image resolution, output self-verification, vision + reasoning.
Claude Sonnet 4.6
Anthropic's balanced mid-tier model from February 2026. Best price/performance for production workloads: 5x cheaper than Opus, near-flagship quality.
Depth Anything v2
Monocular depth-estimation model trained on 595k labeled and 62M unlabeled images. Strong zero-shot generalization in indoor and outdoor scenes.
GPT-5.4
OpenAI's unified flagship combining GPT and o-series reasoning into one model. 1M context, multimodal, top SWE-Bench Pro and OSWorld scores.
Start using Reka Edge today
Get started with free credits. No credit card required. Access Reka Edge and 100+ other models through a single API.