Novita AI pricing & review

Combines a serverless LLM API (DeepSeek, Llama, Qwen at aggressive per-token prices) with GPU instances and template deployments, one of the few providers covering both sides of the hosting equation.

Where Novita AI wins

Novita AI model pricing

List prices refreshed 2026-08-28 ยท cheapest 25 shown
ModelInput $/1MOutput $/1MMarket floor in
Llama 3.1 8B $0.020 $0.050 $0.020at Nebius
Llama 3.2 1B Instruct $0.020 $0.020 $0.020at Novita AI
Llama 3.2 3B $0.030 $0.050 $0.020at DeepInfra
Qwen3-4B $0.030 $0.030 $0.030at Novita AI
Qwen3 8B $0.035 $0.138 $0.035at Novita AI
GPT-OSS 20B $0.040 $0.150 $0.015at Darkbloom
Mistral Nemo $0.040 $0.170 $0.019at DeepInfra
Llama-3-8b $0.040 $0.040 $0.030at DeepInfra
GPT-OSS 120B $0.050 $0.250 $0.030at W&B Inference
Gemma 3 12B $0.050 $0.100 $0.050at DeepInfra
Nemotron 3 Nano $0.050 $0.200 $0.050at Novita AI
Ling-3.0-Flash $0.060 $0.180 $0.021at OpenRouter
GLM-4.7 Flash $0.070 $0.400 $0.060at DeepInfra
Qwen3 Coder 30B A3B Instruct $0.070 $0.270 $0.070at Novita AI
Qwen2.5-7B-Instruct $0.070 $0.070 $0.040at DeepInfra
Qwen3 VL 8B Instruct $0.080 $0.500 $0.080at Novita AI
Qwen3 30B A3B $0.090 $0.450 $0.051at Cloudflare
MythoMax 13B $0.090 $0.090 $0.090at Novita AI
Qwen3 32B $0.100 $0.450 $0.050at Lambda
Mimo-V2-Flash $0.110 $0.330 $0.100at OpenRouter
Gemma 3 27B $0.119 $0.200 $0.060at Nebius
GLM-4.5 Air $0.130 $0.850 $0.125at Pinstripes
Gemma 4 26B A4B $0.130 $0.400 $0.070at DeepInfra
Llama 3.3 70B $0.135 $0.400 $0.120at Hyperbolic
DeepSeek V4 Flash $0.140 $0.280 $0.050at OpenRouter

Novita AI compared

Disclosure: links to Novita AI may be referral links. Rankings on this site are ordered by price alone. How we make money.