Skip to content
Sovyron

Beam Free

beam-free1.0M context1.0M max outputreleased Oct 5, 2026Open weightsReasoningTool calling1 subscription plan →

As of Nov 22, 2026, the cheapest Beam Free API price is $0.4 per 1M input tokens (DigitalOcean) and $1.2 per 1M output tokens (DigitalOcean). Beam Free is offered by 3 providers in the beam-free family, open weights, reasoning enabled. 2 providers list it as a free-tier offer. It is also included in one flat-rate subscription plan, OpenCode OpenCode Go from $10/mo.

Cheapest input
$0.4
Cheapest output
$1.2
Official
—
output per 1M tokens
Providers
3
offering this model
Spread
—
max / min output
Free offers
2
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

Beam Free API prices by provider in USD per 1M tokens, updated Nov 22, 2026
DigitalOceanreflection-beamCheapest$0.4Cheapest$1.2$0.04—1.0M
OpenCodefreebeam-freefreefreefree—1.0M
OpenCode Gofreebeam-freefreefreefree—1.0M

Beam Free pricing FAQ

What is the cheapest Beam Free API?

As of Nov 22, 2026, DigitalOcean has the lowest Beam Free output price at $1.2 per 1M tokens, and DigitalOcean has the lowest input price at $0.4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer Beam Free?

3 providers list Beam Free on Sovyron; 1 of them sell it at a metered per-token price.

Is Beam Free free?

2 providers list a free-tier offer: OpenCode, OpenCode Go. Free tiers usually have rate limits.

Is Beam Free included in a subscription plan?

Yes. One flat-rate plan includes it; the cheapest is OpenCode OpenCode Go at $10/month.

What is the context window of Beam Free?

Beam Free supports a 1.0M-token context window and up to 1.0M output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—