FriendliAI models
Fast open-model Model APIs with cache-aware per-token pricing.
GLM-5.2 (FriendliAI)
$1.40 / $4.40 per 1M tokens
DeepSeek V3.2 (FriendliAI)
$0.5 / $1.50 per 1M tokens
Gemma 4 31B (FriendliAI)
$0.14 / $0.4 per 1M tokens
MiniMax M2.5 (FriendliAI)
$0.3 / $1.20 per 1M tokens
FriendliAI
Fast open-model Model APIs with cache-aware per-token pricing.
There are 4 published models here. On a 70/30 mix, combined list rates run from $0.218 to $2.30 per 1 million tokens, with a median of $0.685. The largest listed context window in this group is 200,000 tokens. The most recent price check in this group is 2026-08-14.
Official FriendliAI pricing page
FriendliAI list rates
USD per million tokens. The 70/30 mix is a planning default — change it on the model page if your traffic is output-heavy.
| Model | Input / 1M | Output / 1M | Mixed 70/30 | Context | Verified |
|---|---|---|---|---|---|
| Gemma 4 31B (FriendliAI) | $0.14 | $0.4 | $0.218 | 128,000 | |
| MiniMax M2.5 (FriendliAI) | $0.3 | $1.20 | $0.57 | 200,000 | |
| DeepSeek V3.2 (FriendliAI) | $0.5 | $1.50 | $0.8 | 160,000 | |
| GLM-5.2 (FriendliAI) | $1.40 | $4.40 | $2.30 | 200,000 |
Questions about FriendliAI rates
Do these FriendliAI figures include discounts and tax?
No. They are public list rates. Commits, credits, regions, tax, and commercial discounts are not in the number — check the source linked on each model.
When is the more expensive FriendliAI tier worth the extra?
GLM-5.2 (FriendliAI) sits near $2.30 per 1M tokens on a 70/30 mix, versus $0.218 on Gemma 4 31B (FriendliAI). Use the high tier when retries or long reasoning actually fail on the cheap one.