Reka Flash (Sep ’24)
Intelligence
12
#412/523
Coding
—
Math
—
Speed
85 tok/s
TTFT: 1.25s
Pricing
$0.20 / $0.80
per 1M tokens (in/out)
Reka Flash (Sep ’24) is Reka AI’s latest model designed for efficient processing of data with a focus on speed and cost-effectiveness. It operates at 84.546 tokens per second and is priced at $0.2 per million input tokens, targeting professional users.
When to Use Reka Flash (Sep ’24)
✓ Best For
- Real-time data processing
- Cost-sensitive applications
- Developers needing fast response times
✗ Not Ideal For
- High-complexity mathematical tasks
- Users requiring extensive coding capabilities
How Reka Flash (Sep ’24) Compares
Intelligence Index · Higher is better
PerplexityGoogleReka AIAlibabaMeta
Output Speed · tok/s
MetaTencentReka AINous Research
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (2)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 12 | |
| MATH 500 | 52.9% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Reka Flash (Sep '24) released?
Reka Flash (Sep '24) was released on October 4, 2024.
Who created Reka Flash (Sep '24)?
Reka Flash (Sep '24) was created by Reka AI.
How intelligent is Reka Flash (Sep '24)?
Reka Flash (Sep '24) scores 12 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other non-reasoning models in a similar price tier (median: 15).
How fast is Reka Flash (Sep '24)?
Reka Flash (Sep '24) generates output at 58.2 tokens per second (based on Reka AI's API), which is below average compared to other non-reasoning models in a similar price tier (median: 98.3 t/s).
What is the latency of Reka Flash (Sep '24)?
Reka Flash (Sep '24) has a time to first token (TTFT) of 1.95s (based on Reka AI's API), which is somewhat higher than average compared to other non-reasoning models in a similar price tier (median: 1.56s).
How much does Reka Flash (Sep '24) cost?
Reka Flash (Sep '24) costs $0.20 per 1M input tokens (better than average, median: $0.23) and $0.80 per 1M output tokens (somewhat higher than average, median: $0.70), based on Reka AI's API.
What is Reka Flash (Sep '24) API pricing?
Reka Flash (Sep '24) costs $0.20 per 1M input tokens and $0.80 per 1M output tokens (based on Reka AI's API). For a blended rate (3:1 input to output ratio), this is $0.35 per 1M tokens. Pricing may vary by provider.
Is Reka Flash (Sep '24) a reasoning model?
No, Reka Flash (Sep '24) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Reka Flash (Sep '24) support?
Reka Flash (Sep '24) supports image input.
What output modalities does Reka Flash (Sep '24) support?
Reka Flash (Sep '24) supports text only output.
Can Reka Flash (Sep '24) process images?
Yes, Reka Flash (Sep '24) supports image input and can analyze, describe, and answer questions about images.
Is Reka Flash (Sep '24) multimodal?
No, Reka Flash (Sep '24) is not multimodal. It only supports image input.
What is the context window of Reka Flash (Sep '24)?
Reka Flash (Sep '24) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is Reka Flash (Sep '24) open source?
No, Reka Flash (Sep '24) is proprietary. The model weights are not publicly available.
How many parameters does Reka Flash (Sep '24) have?
Reka Flash (Sep '24) has 21 billion parameters.
