Novita

Novita Pricing

Visit novita.ai →

Per-token pricing for 35 open-source LLMs on Novita AI — a low-cost serverless inference provider with a broad model catalog and per-model quantization options.

Last updated: Nov 21, 2026

Get our weekly newsletter on pricing changes, new releases, and tools.

Novita offers free models

Free models available — see the full Novita free tier guide

35
Models
$0.02
Cheapest Input/1M
$0.06
Cheapest Output/1M
8
Model Authors
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Context
Quant
Input/1M
Output/1M
262k
—
$0.021
$0.063
1000k
—
$0.060
$0.180
200k
bf16
$0.070
$0.400
1049k
fp8
$0.084
$0.280
262k
bf16
$0.130
$0.400
131k
bf16
$0.130
$0.850
262k
bf16
$0.140
$0.400
262k
—
$0.140
$0.580
1049k
fp8
$0.150
$0.600
deepseek/deepseek-v4.1-flash-1017
1049k
fp8
$0.165
$0.660
131k
bf16
$0.200
$0.700
262k
fp8
$0.200
$1.150
262k
bf16
$0.300
$2.400
131k
bf16
$0.300
$0.900
262k
bf16
$0.400
$3.200
deepseek-ai/DeepSeek-V4-Flash-0731
1049k
fp8
$0.418
$1.254
1000k
—
$0.420
$3.000
205k
bf16
$0.495
$1.980
131k
fp8
$0.570
$2.300
262k
—
$0.570
$2.850
262k
fp8
$0.600
$2.500
262k
bf16
$0.600
$2.500
262k
—
$0.600
$3.600
66k
fp8
$0.600
$1.800
205k
fp8
$0.600
$2.200
1049k
fp8
$0.630
$1.980
1049k
fp8
$0.770
$2.420
262k
—
$0.800
$3.400
1000k
fp8
$0.834
$2.501
203k
fp8
$0.900
$2.880
262k
int4
$0.912
$3.840
deepseek/deepseek-v4-pro-0813
1049k
fp8
$1.254
$3.762
1049k
fp8
$1.280
$2.560
205k
fp8
$1.380
$4.400
1000k
—
$2.000
$6.000

Pricing for Novita endpoints aggregated via OpenRouter. Prices per 1M tokens.

About Novita AI

Novita AI is a serverless inference cloud offering cheap, pay-per-token access to a broad catalog of open-source models — Llama, Qwen, DeepSeek, GLM, gpt-oss and more. Many models are offered at multiple quantizations (fp8, fp16, fp4), letting you trade a little quality for lower cost. The API is OpenAI-compatible, so switching is usually a base-URL change.

Beyond LLMs, Novita also runs GPU instances and image/video models. For most teams the serverless per-token tier below is the cheapest way to run open-weight models, and one of the widest catalogs of any single provider.

Novita Pricing FAQ

How much does Novita cost?

Novita charges per token, with input prices starting around $0.01–$0.10 per million tokens for smaller open models. See the live table above for current per-model input and output prices.

What is quantization and why does it matter?

Quantization (fp8, fp4, int4) compresses a model so it runs cheaper and faster with a small quality trade-off. Novita serves many models at multiple quantizations — the table shows which quantization each price applies to.

Is Novita cheaper than other providers?

For open-weight models Novita is among the cheapest serverless options, especially at fp8/fp4 quantizations. Use the comparison links below to see Novita vs other providers on the same model.

Which models does Novita support?

A wide catalog of open-source LLMs plus image and video models. The table above lists the LLMs Novita currently serves with public per-token pricing.

Compare Novita with Other Providers