Reka Flash 21B
Efficient
Faster, cheaper Reka Flash. 21B parameters, multimodal, deployable on a single high-end GPU.
Reka Flash 21B is a efficient AI model from Reka AI. It costs $0.800 per million input tokens and $4.000 per million output tokens (blended $1.760/M), with a 128K-token context window.
INPUT
$0.800/M
per million input tokens
OUTPUT
$4.000/M
per million output tokens
CONTEXT
128K
128,000 tokens
What it's good at
- Single-GPU multimodal
- Native vision + audio
- Cheaper than Reka Core
Typical use cases
- Self-hosted multimodal chat
- Cost-sensitive video QA
Benchmarks
vs. best public score
MMLU75%
Multitask academic knowledge across 57 subjects.
HumanEval65%
Python function synthesis from docstrings.
LMArena Elo1184 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
Frequently asked questions
How much does Reka Flash 21B cost?
Reka Flash 21B costs $0.800 per million input tokens and $4.000 per million output tokens, for a blended reference rate of $1.760 per million tokens.
What is Reka Flash 21B's context window?
Reka Flash 21B supports up to 128K tokens of context (128,000 tokens).
What is Reka Flash 21B best for?
Reka Flash 21B is well suited to Single-GPU multimodal, Native vision + audio and Cheaper than Reka Core.
Who makes Reka Flash 21B?
Reka Flash 21B is developed and served by Reka AI.
