Reka
Reka Flash 3
Efficient model for low-latency assistance, extraction, and routine automation
Model facts
- Context window
- 66K tokens
- Maximum output
- 59K tokens
- Cheapest paid input
- $0.1 per 1M tokens
- Cheapest paid output
- $0.2 per 1M tokens
- Open weights
- yes
- Providers
- 2
Capabilities and modalities
reasoning, structured output, temperature control, open weights, text.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 3.7 | not measured | 33.7 | 90.2 |
Observed price history
- 2026-08-24: $0.1 input / $0.2 output per 1M tokens
API providers
- OpenRouter — model id rekaai/reka-flash-3; $0.1 input / $0.2 output per 1M tokens; provider documentation
- Kilo Gateway — model id rekaai/reka-flash-3; $0.1 input / $0.2 output per 1M tokens; provider documentation