Favicon for rekaai

Reka Flash 3

rekaai/reka-flash-3

Model weights

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 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient quantization (down to 11GB at 4-bit precision), and employs explicit reasoning tags ("<reasoning>") to indicate its internal thought process.

Reka Flash 3 is primarily an English model with limited multilingual understanding capabilities. The model weights are released under the Apache 2.0 license.

Modalities
In / out price
$0.10 / $0.20per 1M
Context
66K
Released
Mar 12, 2025
Knowledge cutoff
Jan 2025

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input
$0.09899/M tokens
Output
$0.1995/M tokens
Price history
No effective price data for this selection

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput
78tok/s

P50, best across providers

Latency
0.51s

P50, best provider

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
98.88%

Availability over the last 3 days

Last 72 hours
Availability 98.88%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
98.11%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Reka Flash 3 (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisReka Flash (Sep '24) MATH-50052.9%
Artificial AnalysisReka Flash 3 GPQA Diamond52.9%
Artificial AnalysisReka Flash 3 HLE4.4%
Artificial AnalysisReka Flash 3 IFBench30.4%
Artificial AnalysisReka Flash 3 τ²-Bench Telecom0.0%
Artificial AnalysisReka Flash 3 AA-LCR0.0%
Artificial AnalysisReka Flash 3 CritPt0.0%
Artificial AnalysisReka Flash 3 LiveCodeBench43.5%
Artificial AnalysisReka Flash 3 Terminal-Bench Hard0.0%
Artificial AnalysisReka Flash 3 MMLU-Pro66.9%
Artificial AnalysisReka Flash 3 AIME 202533.7%
Artificial AnalysisReka Flash 3 AIME51.0%
Artificial AnalysisReka Flash 3 MATH-50089.3%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.
Favicon for https://github.com/neilshah/metasafetybench
metasafetybench
new
11Mtokens
2.
Favicon for https://github.com/s0ld13rr/pentestcode
pentestcode
new
9.07Mtokens
3.
Favicon for https://hellohaven.ai/
Hello Haven
new
3.25Mtokens
4.
Favicon for https://github.com/OlympiaAI/open_router
OpenRouter Ruby Client
new
2.06Mtokens
5.
Favicon for https://api.dailyiq.ai/
DailyIQ Evaluation
new
780Ktokens
Rest of OpenRouter
579K
Top 5 Apps
161K

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions

Explore more models