All models
Rekaai
Reka Edge fastruns locally
rekaai/reka-edge
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...
Input / 1M
$0.10
USD per million tokens
Output / 1M
$0.10
USD per million tokens
Est. cost / token
$0.0000001
$0.10 per 1M, 3:1 mix
Context window
16K
max output 15K
Major features
VisionOpen weightsJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context1
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 4.7 GB |
| Q3_K_M | fair | 5.3 GB |
| Q4_K_Mrecommended | good | 6.2 GB |
| Q5_K_M | very good | 6.9 GB |
| Q6_K | excellent | 7.7 GB |
| Q8_0 | near-lossless | 9.5 GB |
| F16 | lossless | 16.5 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.10 | $0.10 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.10
- Output
- $0.10
- Blended (3:1)
- $0.10
Details
- Company
- Rekaai
- Version
- —
- Family
- Reka
- Released
- 2026-03-20
- Parameters
- 7.1B
- Max output
- 15K
- Open weights
- Yes
- Inputs
- image, text, video
- Last synced
- 46 min ago