Reka Flash 3
Fast and lightReka · 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
What Reka Flash 3 is best for
- High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
Reka family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Reka Edge | 16K | 1.1 | 1.1 | March 2026 |
| Reka Flash 3 | 66K | 1.1 | 2.2 | March 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 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,...
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
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...
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
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...
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