Question 1

How many Novita AI models are available through Requesty?

Accepted Answer

Requesty routes to 43 Novita AI models including regional variants, with pricing synced in real time to the upstream provider.

Question 2

What is the cheapest Novita AI model?

Accepted Answer

The cheapest Novita AI model starts at $0.03 per million input tokens. See the pricing column in the table below for full per-model rates.

Question 3

Does Requesty add markup on Novita AI pricing?

Accepted Answer

No. Requesty passes through exactly what Novita AI charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.

Question 4

Is my data used to train Novita AI models?

Accepted Answer

Novita AI's training policy varies by product and tier. See their privacy policy for specifics, and contact Requesty for enterprise-grade data controls.

Question 5

Where are Novita AI models hosted?

Accepted Answer

Novita AI models are hosted in 🇺🇸 US. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Novita AI rows in the models explorer.

Model	Context	Max Output	Input/1M	Output/1M	Capabilities	Coding
zai-org/glm-5.1	205K	—	$1.38	$4.40	🧠🔧	43
xiaomimimo/mimo-v2-pro	1.0M	—	$2.00	$6.00	🧠🔧	41
xiaomimimo/mimo-v2-flash	262K	—	$0.10	$0.30	🧠🔧	32
minimax/minimax-m2.7-highspeed	205K	—	$0.60	$2.40	🧠🔧	—
kwaipilot/kat-coder-pro	256K	—	$0.30	$1.20	🔧	—
inclusionai/ring-2.6-1t	262K	—	$0.30	$2.50	🧠🔧	33
inclusionai/ling-2.6-flash	262K	—	$0.10	$0.30	🔧	23
inclusionai/ling-2.6-1t	262K	—	$0.30	$2.50	🔧	33
deepseek-v4-flash	1.0M	—	$0.14	$0.28	🧠🔧	39
baidu/ernie-4.5-300b-a47b-paddle	123K	—	$0.28	$1.10		—
baichuan/baichuan-m2-32b	131K	—	$0.07	$0.07		—
gemma-4-26b-a4b-it	262K	131K	$0.13	$0.40	👁🧠🔧	—
GLM-5	203K	131K	$1.00	$3.20	🧠🔧⚡	44
minimax/minimax-m2.7	200K	128K	$0.30	$1.20	👁🧠🔧⚡	42
deepseek-v3.2	164K	66K	$0.27	$0.40	🧠🔧⚡	37
qwen/qwen3.5-397b-a17b	262K	66K	$0.60	$3.60	👁🧠🔧	41
zai-org/glm-4.5	131K	—	$0.60	$2.20	🔧	—
zai-org/glm-4.6	205K	131K	$0.60	$2.20	🔧	30
moonshotai/kimi-k2-instruct	131K	—	$0.57	$2.30	🔧	35
deepseek-v3-0324	128K	—	$0.40	$1.30	🔧	22
deepseek_v3	64K	—	$0.89	$0.89	🔧	—
deepseek-v3-turbo	128K	—	$0.40	$1.30	🔧	16
qwen/qwen-2.5-72b-instruct	32K	—	$0.38	$0.40	🔧	—
qwen/qwen2.5-vl-72b-instruct	96K	—	$0.80	$0.80		—
qwen/qwen3-235b-a22b-fp8	128K	—	$0.20	$0.80		—
meta-llama/llama-3-8b-instruct	8K	—	$0.04	$0.04		—
meta-llama/llama-3-70b-instruct	8K	—	$0.51	$0.74		—
wizardlm-2-8x22b	66K	—	$0.62	$0.62		—
meta-llama/llama-3.3-70b-instruct	131K	—	$0.39	$0.39	🔧	—
meta-llama/llama-3.2-3b-instruct	33K	—	$0.03	$0.05	🔧	—
meta-llama/llama-3.1-8b-instruct	16K	—	$0.05	$0.05		—
deepseek-r1	64K	—	$4.00	$4.00	🔧	24
meta-llama/llama-4-maverick-17b-128e-instruct-fp8	1.0M	1.0M	$0.20	$0.85		—
deepseek-r1-distill-qwen-14b	128K	—	$0.15	$0.15	🔧	—
deepseek-prover-v2-671b	160K	—	$0.70	$2.50		—
deepseek-r1-turbo	64K	—	$0.70	$2.50	🔧	24
deepseek-r1-distill-llama-70b	32K	—	$0.80	$0.80		11
deepseek-r1-distill-qwen-32b	13K	—	$0.30	$0.30	🔧	—
sao10k/l3-8b-lunaris	8K	—	$0.05	$0.05		—
sao10k/l31-70b-euryale-v2.2	16K	—	$1.48	$1.48		—
Sao10K/L3-8B-Stheno-v3.2	8K	—	$0.05	$0.05		—
mistralai/mistral-nemo	131K	—	$0.17	$0.17		—
gryphe/mythomax-l2-13b	4K	—	$0.09	$0.09	🔧	—

Novita AI

All Novita AI models

About Novita AI on Requesty