ModelPickr

Reka Flash 3 from Reka: — input and — output per 1M tokens, 65,536 context. Efficient model for low-latency assistance, extraction, and routine automation Data last refreshed Oct 16, 2026, 07:15 AM UTC.

Models / Reka / Reka Flash 3

Reka · reka

Reka Flash 3

Efficient model for low-latency assistance, extraction, and routine automation

— in · — out

per 1M tokens · no published price. Models.dev does not list a per-token price for this model yet.

Context
65,536
Max output
58,982
Cache read
—
Cache write
—
Reasoning
Yes
Tool calls
No
Structured output
Yes
Vision
No
Open weights
Yes
License
—
Released
Mar 12, 2025
Updated in source
Mar 12, 2025
Knowledge
2025-01-31
Providers
0

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

Reka Flash 3

—

No published per-token price.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Models.dev has a canonical record for this model and no provider listing.