Reka AI

Reka Flash 3 — Benchmark Scores, Pricing & Performance Analysis

Output Speed
136 tok/s
Input Cost
$0.10/1M
Output Cost
$0.20/1M
Context Window
66K

Reka Flash 3 by Reka AI demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

Speed Benchmarks

Output Speed
136 tok/s24th of 94

Tokens generated per second

Aggregated
Time to First Token
500 ms59th of 92

Latency before first token arrives

Aggregated

Cost Benchmarks

Input Cost
$0.10114th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$0.20110th of 413

Cost per 1M output tokens

OpenRouter API

Context Benchmarks

Context Length
66K352nd of 451

Maximum context window size

OpenRouter API

Available from 2 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 1 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Kilo Gateway$0.1$0.2—66K—
OpenRouter$0.1$0.2—66KSupported

Reka Flash 3 — Frequently Asked Questions

How much does Reka Flash 3 cost?

Reka Flash 3 costs $0.10 per 1M input tokens and $0.20 per 1M output tokens. This makes it one of the more affordable models.

How fast is Reka Flash 3?

Reka Flash 3 generates output at 136 tokens per second, which is moderate compared to other models. The time to first token is 500 ms.

What is the context window of Reka Flash 3?

Reka Flash 3 has a context window of 66K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Reka Flash 3?

Reka Flash 3 was created by Reka AI. It is classified as a mid model in our catalogue.

Is Reka Flash 3 open source?

No, Reka Flash 3 is a proprietary model. It is available through Reka AI's API and compatible providers.