Reka Flash 3 is Reka AI's language model with a 66K context window and up to 59K output tokens, starting at $0.1 / 1M input and $0.2 / 1M output. A 21-billion-parameter general-purpose instruction-tuned LLM from Reka excelling at chat, coding, instruction-following, and function calling.
Specifications
Canonical IDreka-flash-3
TypeLanguage
StatusActive
CreatorReka AIReka AI
Providers
Context Window66K tokens
Max Output59K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Release Date · 2 years ago
Knowledge Cutoff · 2 years ago
Benchmarks
Intelligence Index
#501
Math Index
#194
MMLU-Pro
#246
GPQA
#387
HLE
#446
LiveCodeBench
#178
AIME
#65
IFBench
#364
Time to First Token
#458
SciCode
#376
MATH-500
#80
AIME 2025
#194
LCR
#483
TerminalBench Hard
#411
TAU2
#416
Output TPS
#139

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
OpenRouter logo
OpenRouter
rekaai/reka-flash-3
$0.1$0.2

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Reka Flash 366K$0.100$0.200Current
Reka Edge16K$0.100$0.100Available
Reka Flash—100K——Available
Reka Core—32K——Available

Model IDs

openrouter/rekaai/reka-flash-3
reka-flash-3
rekaai/reka-flash-3