Skip to content
LLMs
Reka AI logo

Reka Flash 3

by Reka AI

Reka Flash 3 is a large language model from Reka AI. It costs $0.100 per million input tokens and $0.200 per million output tokens. Its context window is 66K tokens.

ReasoningStructured outputOpen weights
Input / 1M tokens
$0.100
Output / 1M tokens
$0.200
Cached input / 1M
-

Not supported

Context window
66K

tokens

Who serves it cheapest

1 hosts serve Reka Flash 3. Same weights, same API - the price difference is pure margin and routing.

Providers serving Reka Flash 3, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
RekaCheapestfp8$0.100$0.20066K-100.0%

About Reka Flash 3

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...

Specifications

Reka Flash 3 specifications
Model IDrekaai/reka-flash-3
ProviderReka AI
Context window66K tokens
Max output59K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2025-01-31
Open weightsYes - RekaAI/reka-flash-3
ReleasedMarch 12, 2025

Cheaper alternatives

Models that cost less than Reka Flash 3 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Reka Flash 3 cost?

$0.100 per million input tokens and $0.200 per million output tokens.

What is the context window of Reka Flash 3?

66K tokens, with up to 59K tokens of output per request.

Confirm against the source: Reka AI official pricing.