Reka Flash 3 Pricing
FastReka AI · 66K tokens context
Reka Flash 3 from Reka AI costs $0.100 per 1 million input tokens and $0.200 per 1 million output tokens as of July 2026 (live OpenRouter data). The model supports a 65,536-token context window (approximately 49,152 words) with a 66K-token maximum output. A typical 1,000-token request costs $0.0001 in input charges; a 10,000-token request costs $0.0010.
| Input price | $0.100 / 1M tokens |
|---|---|
| Output price | $0.200 / 1M tokens |
| Output / input ratio | 2.0× |
| Context window | 65,536 tokens (~49,152 words) |
| Maximum output | 65,536 tokens |
| Cost per 1K tokens (input) | $0.0001 |
| Tier | Fast |
| Last verified |
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.
Input Price
$0.100
per 1 million tokens
Output Price
$0.200
per 1 million tokens
Context Window
66K tokens
max 66K output
Cost Examples
| Request Type | Tokens | Input Cost | Output Cost |
|---|---|---|---|
| 1,000 word article | 1,333 | $0.000133 | $0.00008 |
| 10-page document (2,500 words) | 3,333 | $0.000333 | $0.0002 |
| 1,000 lines of code | 5,000 | $0.0005 | $0.0003 |
| 100K token document | 100,000 | $0.01 | $0.006 |
Output cost estimated at 30% of input token count. Use the calculator for exact figures.
Strengths
- ✓Extremely cheap at $0.100/1M input tokens
- ✓Low latency for high-throughput workloads
- ✓Cost-effective at scale
Limitations
- –Less capable than flagship models on complex reasoning
- –Quality and availability can vary by hosting provider
Best Use Cases
Calculate Reka Flash 3 Costs
Use the TokenRate calculator to convert any budget, token count, or text into exact Reka Flash 3 costs — and compare across all models.
Open Calculator →Reka Flash 3 — FAQ
Related Models
Related Guides