—per task?
self-host onlyprice
—output speed?
41Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterClaude Opus 4.5unstated×3.5—$5 / $25
OpenKimi K2 0711unstated×2.7—$0.50 / $2No strict JSONBetterClaude Sonnet 4.5unstated×3.3—$3 / $15BetterClaude Haiku 4.5unstated×3.1—$1 / $5
Bettero3 (2025-04-16)unstated×2.8—$2 / $8ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
Claude Opus 4.5unstated×3.5—$5 / $25Claude Sonnet 4.5unstated×3.3—$3 / $15Claude Haiku 4.5unstated×3.1—$1 / $5o3 (2025-04-16)unstated×2.8—$2 / $8Kimi K2 0711unstatedOpen×2.7—$0.50 / $2No strict JSON
Run it yourself
Fits onhardware needs not verified yet
LicenceApache-2.0free for commercial use
Benchmarks
in Agents & Tool UseBFCL v422.3#33
FAQ
How much does RZN T cost?›
There is no per-unit API price: self-host only.
Is RZN T free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is RZN T, and what is it best at?›
#33 of 39 in Agents & Tool Use.
Is RZN T better than Qwen3 0.6B?›
On BFCL v4, RZN T scores 22.3 vs 23.9 — lower.
What is the context window of RZN T?›
41K tokens.
When was RZN T released? Is there a newer version?›
Released 2025-06-03. It is the current version in its line.
Is RZN T open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run RZN T locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can RZN T read images?›
No, it accepts text only.
What is RZN T?›
RZN T is an open-weights language model from phronetic-ai, released Jun 2025.
What are the best alternatives to RZN T?›
Claude Opus 4.5 (better), Kimi K2 0711 (open weights).