Reka Flash 3
Provider：Reka AI
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...
Key specs
- Context：65.5K
- Max output：59K
- Tokenizer：Other
- Released：2025-03-12
Token pricing
- Input price：$0.100 / 1M tokens
- Output price：$0.200 / 1M tokens
- Blended price：$0.125 / 1M tokens
Modalities
Text
Use Cases
- Deep Reasoning & Analysis：Math proofs, logical reasoning, multi-step planning — ideal for research and financial analysis.（≈ $0.0016/call）
- Chat & Support：FAQ auto-response, multi-turn dialogue, emotion detection — e-commerce, finance, gov.（≈ $0.0010/turn）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Low input + output price: solid fit for high-frequency calls and batch processing.
- Low blended price: budget-friendly for fleet-scale deployment.
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
FAQ
- What is the token pricing of Reka Flash 3? Input price $0.100 / 1M tokens, output price $0.200 / 1M tokens, blended about $0.125 / 1M tokens. Refer to Reka AI’s official page for the exact rate.
- What context window does Reka Flash 3 support? Context window is 65.5K, max output about 59K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Reka Flash 3 best for? Based on its capability and pricing, Reka Flash 3 fits best: Deep Reasoning & Analysis, Chat & Support. See the Use Cases section for details and cost estimates.
- What input/output modalities does Reka Flash 3 support? Supports Text modality.
- Is Reka Flash 3 a free model? Reka Flash 3 is billed per token, not a free model.
- Which provider offers Reka Flash 3? Reka Flash 3 is offered by Reka AI.
More models from Reka AI
Full info：Reka Flash 3