Reka Flash 3

Fast and light

Reka · Released March 2025 · Knowledge cutoff January 2025

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...

Facts and pricing

Provider
Reka
Context window
66K tokens
Input price
1.1 credits / 1M tokens ($0.10 raw)
Output price
2.2 credits / 1M tokens ($0.20 raw)
Vision (image input)
No
Tool calling
No
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Reka Flash 3 now

Ask Reka Flash 3 anything. Your prompt opens in the Zeplik app with this model selected.

Reka Flash 3

What Reka Flash 3 is best for

Reka family

ModelContextInput cr/MOutput cr/MReleased
Reka Edge16K1.11.1March 2026
Reka Flash 366K1.12.2March 2025

Frequently asked questions

What is Reka Flash 3?
Reka Flash 3 is an AI model by Reka. 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...
How much does Reka Flash 3 cost on Zeplik?
Input tokens cost 1.1 credits per million and output tokens 2.2 credits per million (1 credit = $0.10; the raw provider rates are $0.10 and $0.20 per million). New accounts start with free credits.
How long can a conversation with Reka Flash 3 be?
Reka Flash 3 has a 66K-token context window (65,536 tokens), which covers the conversation plus any documents you attach.
Does Reka Flash 3 support images and tools?
Reka Flash 3 is text-only and does not support tool calling.

Related models

Reka EdgeGeneral purpose

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...

16K ctx1.1 cr/M outMarch 2026
GPT-5.6 Luna ProFrontier

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 LunaFrontier

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 Terra ProFrontier

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx165 cr/M outJuly 2026
GPT-5.6 TerraFrontier

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...

1.1M ctx165 cr/M outJuly 2026
GPT-5.6 Sol ProFrontier

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx330 cr/M outJuly 2026
Reka Flash 3 - Reka AI Model | Zeplik Chat