What is Reka Edge API?
Reka Edge is available through AIMLAPI.
Technical Specifications
- Supported inputs: Image, Text
- Output: Text
- Context window: 16,384 tokens / Max output: 16,384 tokens
- Endpoint: /chat/completions
Performance Benchmarks
[embed]
Reka Edge API Pricing
- Input: $0.13 / 1M tokens
- Output: $0.13 / 1M tokens
Where to Use Reka Edge
Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.
Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.
Complex reasoning
Extended reasoning improves reliability on multi-step math, logic, and technical analysis.
Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.
Code Sample
[embed]
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Real-time video analysis, including live video processing for production and latency-sensitive environments. Object detection and scene understanding for robotics and drones, with localized visual intelligence at the edge. Media and content highlight generation, including automatic highlight creation and content metadata tagging for live or archived media. Multimodal agent orchestration and agentic tool-use for physical AI systems and other edge-deployed workflows.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "rekaai/reka-edge", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "rekaai/reka-edge", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"rekaai/reka-edge","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| MMLU | 65.7 | Multi-discipline knowledge across 57 school and professional subjects | Source | September 21, 2026 |
| GSM8K | 66.2 | Grade-school maths word problems requiring multi-step arithmetic | Source | September 21, 2026 |
| MATH | 23.2 | Competition mathematics problems across five difficulty levels | Source | September 21, 2026 |
| HumanEval | 54.3 | Python function synthesis from a docstring, scored by unit tests (pass@1) | Source | September 21, 2026 |
| MMMU | 53.6 | College-level multimodal understanding + reasoning | Source | September 21, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Reka Edge This page | Reasoning + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Reka Edge has a 16,384 tokens context window and can return up to 16,384 tokens.
Reka Edge takes image, text as input and returns text.
Use rekaai/reka-edge as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Reka Edge is priced at input $0.13754 / 1M tokens, output $0.13754 / 1M tokens.
Yes, Reka Edge can stream responses as they are generated.
Yes, Reka Edge accepts image input alongside text.
Yes, Reka Edge supports function calling, parallel tool calls, and tool use.
