rekaai Open weights Reasoning

Reka Flash 3 pricing & benchmarks

Released Mar 12, 2025 · served by 1 provider

Input / 1M tokens$0.100
Output / 1M tokens$0.200
Context window66K
Cached input
1M in + 300K out$0.16

What Reka Flash 3 is

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...

Providers and prices for Reka Flash 3

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Rekacheapest $0.100 $0.200 66K fp8 100.0%

FAQ

How much does the Reka Flash 3 API cost?

$0.100 per 1M input tokens and $0.200 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.16.

Is Reka Flash 3 free?

No. It is a paid model starting at $0.100 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Reka Flash 3?

Reka at $0.100 input / $0.200 output per 1M tokens (fp8 quantization).

Can I self-host Reka Flash 3?

Yes — weights are published as RekaAI/reka-flash-3 on Hugging Face, so you can run it on your own hardware.