Reka Edge
Reka AI · released Mar 11, 2026 · RekaAI/reka-edge-2603
- Type
- Open weightsCustom licence
- Params
- 7.1B
- Context
- 16K
about 12K words of context · download allowed, licence restricts use
Our take
Written Sep 2, 2026Reka Edge is a compact multimodal model that accepts text, images and video, returning text. At 7.1 billion parameters it is positioned as a lightweight hosted option with low per-token pricing, though no benchmark scores are available to confirm its quality.
Pick this for low-cost multimodal inference when you need basic text, image and video understanding and frontier quality is not required. Use it when the same rate in both directions keeps billing simple. Skip it if you need measured quality data, a permissive licence, or a longer context window for rich video sequences.
The case for it
- Very low per-token pricing for multimodal capability, with the same rate in both directions.
- Native video understanding in a 7-billion-parameter model, which is uncommon at this size.
The case against it
- No measured quality scores to validate performance claims.
- Custom restricted licence, not a permissive open licence, which limits deployment flexibility.
- 16,384-token request limit is modest for multimodal work, where video and image sequences consume tokens rapidly.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 16.7 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 24.7 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU) · 16 GB
Room to spare. 5.9 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.10 in / $0.10 out
- Context served
- 16K
- Throughput
- ~9 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.10 / $0.10checked 4 hours ago | 16K | not measured | Unknown | Unknown | Unknown |
| RekaThrough OpenRouter | $0.10 / $0.10checked 4 hours ago | 16K15K max reply | 9 tok/s | No | No | Confirmed |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✗ | ✓ |
| RekaThrough OpenRouter | ✓ | ✗ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- RekaAI/reka-edge-2603
- Architecture
- Dense
- Takes in, gives back
- Text, images and video in, text out
- Catalogue slug
- rekaai-reka-edge