Reka AI
Reka AI
Efficient

Reka Edge

Micro

Smallest Reka, 7B parameters, designed for on-device multimodal deployment.

Reka Edge is a efficient AI model from Reka AI. It costs $0.400 per million input tokens and $2.000 per million output tokens (blended $0.880/M), with a 128,000-token context window.

INPUT
$0.400/M
per million input tokens
OUTPUT
$2.000/M
per million output tokens
BLENDED 70/30
$0.880/M
unchanged since 3 May
CONTEXT
128,000
tokens
What it is good at
  • Edge / on-device
  • Multimodal
  • Open weights
Typical use cases
  • On-device multimodal assistants
  • Edge inference

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Reka AI

See all 3 →

Frequently asked questions

How much does Reka Edge cost?

Reka Edge costs $0.400 per million input tokens and $2.000 per million output tokens, for a blended reference rate of $0.880 per million tokens.

What is Reka Edge's context window?

Reka Edge supports up to 128,000 tokens of context in a single request.

What is Reka Edge best for?

Reka Edge is well suited to Edge / on-device, Multimodal and Open weights.

Who makes Reka Edge?

Reka Edge is developed and served by Reka AI.

Terms used on this page