RentGPU RentGPU
Trouver un GPU →
by Rekaai

Reka Flash 3.

text open weights 66K ctx
Cheapest input
$0.1/M
on OpenRouter
Cheapest output
$0.2/M
on OpenRouter
Fastest
5 tok/s
on OpenRouter
Hosted equiv.
~$0.07/hr
@ 100 tok/s on OpenRouter

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..

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.1 $0.2 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 4.7 100812 ms 105795 ms
FAQ

Frequently asked.

How do I run Reka Flash 3?
Reka Flash 3 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Reka Flash 3?
Reka Flash 3 is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Reka Flash 3?
API pricing starts at $0.1/M input tokens and $0.2/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Reka Flash 3 open-source or proprietary?
Reka Flash 3 is open-weight under the license. You can download and self-host it.