NEAR AI: Models and Prices

Inference API that runs models inside trusted execution environments (Intel TDX with NVIDIA GPU TEEs) to keep prompts private.

Finance your GPUs All inference providers

NEAR AI served 225B tokens of other labs' open-weight models over Nov 2 to Nov 8, 2026 through a large public LLM router, #39 among providers.

Open-weight models

Model	Family	Share of model	Tokens, 7d	Input $/M	Output $/M	Tokens/s	Uptime 3d	Context
GLM 5.3 Flash	GLM	1.0%	126B	$0.08	$0.50	31	100.0%	1.05M
Qwen3.8 27B	Qwen	11.0%	65B	$0.04	$1.35	80	100.0%	262K
gpt-oss-120b	gpt-oss	12.9%	34B	$0.03	$0.15	45	100.0%	131K
DeepSeek V4.1 Flash 1017	DeepSeek	<0.1%	463M	$0.30	$1.20	42	100.0%	1.05M

List prices per million tokens as of November 8, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.

Company

Website: near.ai
Compute: Nodes of eight NVIDIA H200 GPUs; its Confidential GPU Marketplace (February 2026) lets outside providers rent idle GPUs into the network.

Sources: NEAR AI, NEAR AI.

Finance your GPUs

Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.

Prefer email? hello@amcompute.com