Reka AI · language model
Reka Edge: pricing, context and benchmarks
Reka Edge is Reka AI's model released on March 20, 2026. It costs $0.1 per million input tokens and $0.1 per million output tokens, with a 16.4K-token context window. No independent score has been published for it so far.
What you need to know about Reka Edge
Reka AI, based in United States, put Reka Edge online on March 20, 2026. It accepts images, text, and video as input and produces text. Its context window reaches 16,384 tokens, larger than 4 % of the models in the registry, and it can write up to 14,745 tokens in one go.
It has been available for about 7 months, long enough for its prices and scores to have settled.
Reka Edge pricing
On OpenRouter, Reka Edge costs $0.1 per million input tokens and $0.1 per million output tokens. Counting three tokens read for every token written, its average price is $0.1 per million, more expensive than 8 % of paid models (7.6 times cheaper than the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0003. At 1,000 tasks a day, budget $8 a month. The price calculator redoes this with your own volumes.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for Reka Edge. We therefore show no made-up performance rating: only price, context and features count towards its score.
Features, privacy and local use
- It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
- It can answer in an enforced JSON format (structured outputs).
Its weights are open and downloadable from Hugging Face: you can run it on your own machines without sending your data to a third party.
Other Reka AI models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| Reka Flash 3 | Mar 12, 2025 | $0.13 | — |
Verdict
Computed score: 68/100, from public data (performance, price, context, features).
Strengths
- Low price: cheaper than 92 % of paid models.
- Open weights: self-hostable, your data stays with you.
- Agent-ready: tool calling and structured JSON output.
Limitations
- Short context (16.4K tokens): long documents must be split.
- No independent score published: performance cannot be verified.
Avoid if…
- you analyse long documents in one go.
Alternatives
- Phi 4$0.09
- MythoMax 13B$0.09
- Hy-MT2-1.8B$0.08
- Hy-MT2-30B-A3B$0.13
- Hy-MT2-7B$0.13
- Llama 3.2 1B Instruct$0.07
Comparisons and tools
Learn more
Frequently asked questions
How much does Reka Edge cost?
$0.1 per million input tokens and $0.1 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0003.
How big is Reka Edge's context window?
16,384 tokens, roughly 12,000 words, with a maximum of 14,745 output tokens.
Can Reka Edge run locally?
Yes, its weights are published.
Is Reka Edge suitable for an AI agent?
Technically yes: it supports tool calling and structured outputs. Then check its cost for your volume.
What are the alternatives to Reka Edge?
The closest models on price and performance are Phi 4, MythoMax 13B, and Hy-MT2-1.8B.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score