All models
Rekaai
Reka Flash 3 fastruns locally
rekaai/reka-flash-3
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...
Input / 1M
$0.10
USD per million tokens
Output / 1M
$0.20
USD per million tokens
Est. cost / token
$0.000000125
$0.13 per 1M, 3:1 mix
Context window
66K
max output 59K
Major features
Open weightsReasoningJSON schema
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context2
- agentic1
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 11.4 GB |
| Q3_K_M | fair | 12.9 GB |
| Q4_K_Mrecommended | good | 15.6 GB |
| Q5_K_M | very good | 17.8 GB |
| Q6_K | excellent | 20.2 GB |
| Q8_0 | near-lossless | 25.5 GB |
| F16 | lossless | 46.1 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.10 | $0.20 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.10
- Output
- $0.20
- Blended (3:1)
- $0.13
Details
- Company
- Rekaai
- Version
- 3
- Family
- Reka
- Released
- 2025-03-12
- Parameters
- 20.9B
- Max output
- 59K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 46 min ago