What is the cheapest Reka model?

Reka Edge is currently Reka's cheapest paid tracked model at $0.1 per 1M input tokens and $0.1 per 1M output tokens.

How many Reka models are tracked?

2 current Reka models are tracked, each linked to the official pricing page. The dataset is refreshed twice daily.

Does Reka offer cached-input pricing?

Reka does not currently list cached-input (prompt-caching) prices for its tracked models.

Reka

Commercial provider · 2 models tracked · Founded 2022

Multimodal AI lab. Reka sells Reka Edge, a 7B vision-language model for on-device and physical-AI use, and Reka Flash 3, a 21B open-weight reasoning model, from $0.10/1M tokens; its API also serves open models from other labs.

Reka pricing at a glanceNovember 2026 · $ per 1M tokens

Reka API pricing (November 2026): 2 current models range from $0.100 to $0.100 per 1M input tokens and $0.100 to $0.200 per 1M output tokens. The cheapest paid model is Reka Edge at $0.100/1M input; the priciest is Reka Flash 3 at $0.100/1M input / $0.200 output. Every price links to Reka's official pricing page and refreshes twice daily.

Models2

Input range$0.100–$0.100

Output range$0.100–$0.200

Cached-input tiers0

Today's Reka prices

2 models · cheapest blended first

Sorted by blended cost (cheapest first). Prices per 1M tokens, November 2026 — every price links to Reka's official pricing page.

Current Reka model prices per 1M tokens, sorted by blended cost
Model	Blended*	Input	Output	Cached in	Relative cost	Context	Status
Reka Edge	$0.100	$0.100	$0.100	—		16K	Current
Reka Flash 3	$0.125	$0.100	$0.200	—		66K	Current

* Blended = (3×input + 1×output) ÷ 4 $/1M tokens · cheap · mid · expensive MODELPRICEWATCH.COM · 2026-11-07

Quick stats

Models tracked: 2
Type: commercial
Founded: 2022
Cheapest model: Reka Edge
Cheapest blended: $0.100/M

Open-weight models

2 open-weight models available from this provider.

Reka Edge

$0.100/M in · 16K ctx

Reka Flash 3

$0.100/M in · 66K ctx

Try Reka

Get started

Run it yourself

Self-host Reka's open-weight models

These models ship with open weights, so you can serve them yourself on rented GPUs instead of paying per-token API prices — often cheaper at scale.

RunPod →

Rent GPUs by the second and serve any open-weight model yourself.

Novita AI →

Serverless open-model inference billed per token — no GPU ops.

Vast.ai →

GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.