Baseten models
Model APIs and dedicated GPU inference with public per-token list rates.
Kimi K3 (Baseten)
$3.00 / $15.00 per 1M tokens
GLM-5.2 (Baseten)
$1.40 / $4.40 per 1M tokens
GLM-5.2 Fast (Baseten)
$2.10 / $6.60 per 1M tokens
GPT OSS 120B (Baseten)
$0.1 / $0.5 per 1M tokens
DeepSeek V4 (Baseten)
$1.74 / $3.48 per 1M tokens
Kimi K2.6 (Baseten)
$0.95 / $4.00 per 1M tokens
Baseten
Model APIs and dedicated GPU inference with public per-token list rates.
There are 6 published models here. On a 70/30 mix, combined list rates run from $0.22 to $6.60 per 1 million tokens, with a median of $2.281. The largest listed context window in this group is 256,000 tokens. The most recent price check in this group is 2026-08-14.
Baseten 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 |
|---|---|---|---|---|---|
| GPT OSS 120B (Baseten) | $0.1 | $0.5 | $0.22 | 128,000 | |
| Kimi K2.6 (Baseten) | $0.95 | $4.00 | $1.865 | 256,000 | |
| DeepSeek V4 (Baseten) | $1.74 | $3.48 | $2.262 | 160,000 | |
| GLM-5.2 (Baseten) | $1.40 | $4.40 | $2.30 | 200,000 | |
| GLM-5.2 Fast (Baseten) | $2.10 | $6.60 | $3.45 | 200,000 | |
| Kimi K3 (Baseten) | $3.00 | $15.00 | $6.60 | 256,000 |
Questions about Baseten rates
Do these Baseten 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 Baseten tier worth the extra?
Kimi K3 (Baseten) sits near $6.60 per 1M tokens on a 70/30 mix, versus $0.22 on GPT OSS 120B (Baseten). Use the high tier when retries or long reasoning actually fail on the cheap one.