Novita: Models Intelligence, Performance & Price

Novita
Novita

This analysis is intended to support you in choosing the best model provided by Novita for your use-case.

Most Intelligent

#1
DeepSeek V4.1 Flash 1017 (max)DeepSeek V4.1 Flash 1017 (max)
33
#2
GLM-5.3 (max)GLM-5.3 (max)
32
#3
MiniMax-M3.1-FlashMiniMax-M3.1-Flash
29
#4
GLM-5.3-FlashGLM-5.3-Flash
28
#5
DeepSeek V4 Pro 0813 (max)DeepSeek V4 Pro 0813 (max)
23

Intelligence Index

Total 61 models

Lowest Time per Task

#1
gpt-oss-120b (high)gpt-oss-120b (high)
7.2 min
#2
MiniMax-M3MiniMax-M3
15.4 min
#3
DeepSeek V4.1 Flash 1017 (max)DeepSeek V4.1 Flash 1017 (max)
15.8 min
#4
GLM-5.3 (max)GLM-5.3 (max)
19.1 min
#5
MiniMax-M3.1-FlashMiniMax-M3.1-Flash
19.3 min

Time per Intelligence Index task (minutes)

Total 61 models

Lowest Price

#1
Llama 3.1 8BLlama 3.1 8B
$0.02
#2
GLM-4.7-FlashGLM-4.7-Flash
$0.06
#3
GLM-4.7-Flash (non-reasoning)GLM-4.7-Flash (non-reasoning)
$0.06
#4
Nemotron 3 Nano (non-reasoning) (FP4)Nemotron 3 Nano (non-reasoning) (FP4)
$0.07
#5
Nemotron 3 Nano (FP4)Nemotron 3 Nano (FP4)
$0.07

Blended price (per 1M tokens)

Total 61 models

Novita offers 61 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.

  • For intelligence, the top models on Novita are DeepSeek V4.1 Flash 1017 (max) (33), GLM-5.3 (max) (32), and MiniMax-M3.1-Flash (29).
  • For time per task, gpt-oss-120b (high) (7.2 min), MiniMax-M3 (15.4 min), and DeepSeek V4.1 Flash 1017 (max) (15.8 min) finish an Intelligence Index task fastest on Novita. Time per task varies significantly across models, with the slowest taking 2.7x longer than the quickest.
  • For latency, Llama 3.1 8B (0.66s), Gemma 3 27B (1.02s), and DeepSeek V3 (Dec) (1.25s) offer the lowest time to first answer token.
  • For pricing, Llama 3.1 8B ($0.02), GLM-4.7-Flash ($0.06), and GLM-4.7-Flash (non-reasoning) ($0.06) offer the lowest blended prices per 1M tokens. Prices vary up to 2.8x across models.
  • For context window size, DeepSeek V4.1 Flash 1017 (max) (1M), GLM-5.3-Flash (1M), and DeepSeek V4 Pro 0813 (max) (1M) support the largest context windows on Novita.
Artificial Analysis Intelligence Index · Higher is better
Inference time (minutes) per Intelligence Index task · Lower is better
USD per 1M tokens (blended) · Lower is better

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Evaluations

Evaluations measured independently by Artificial Analysis · AA-PersonalityBench scores are percentile ranks from 1 to 100
See more

Agentic knowledge work, Elo

Agentic SaaS workflows

Agentic scientific research workflows in a terminal

Agentic software engineering in open-source repositories

Reasoning & knowledge

Professional document reasoning, All-pass

Agentic coding & terminal use

Physics reasoning

Quantitative analysis on spreadsheets & documents

Legal agentic work, Hallucination-Gated All-Pass Rate

Agentic business operations

Agentic real-world work tasks, Elo

Agentic interactive 3D experiences, Elo

Product and brand videos designed in code, Elo

Kubernetes incident root-cause analysis

Medical long context reasoning

Visual reasoning

Rich, varied, well-crafted language

Well-structured, scannable, answer-first

Truthful, acknowledges uncertainty, non-sycophantic

Use of filler and generic language

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Pricing

Cost per Intelligence Index Task

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Speed

Average of the single-request and multi-turn agentic workloads measured

Time per Intelligence Index Task

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Lower is better

Quality

Endpoint Accuracy Index

Each endpoint's accuracy as a % of its model's reference endpoint · Color shows whether the gap is statistically significant

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

Caching

Cache Hit Rate

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

Cost per Task vs. Cache Hit Rate

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026
Most attractive quadrant
Pareto line

Further Analysis
DeepSeek logo
DeepSeek V4.1 Flash 1017 (max)
33
$0.52
18.1
62.85
0.8%
1M
Open
Z AI logo
GLM-5.3 (max)
32
$5.00
18.3
61.74
0.0%
1M
Open
MiniMax logo
MiniMax-M3.1-Flash
29
$0.43
18.9
71.06
0.9%
1M
Open
Z AI logo
GLM-5.3-Flash
28
$0.80
33.0
62.67
1.7%
1M
Open
DeepSeek logo
DeepSeek V4 Pro 0813 (max)
23
$1.86
23.6
67.46
0.0%
1M
Open
MiniMax logo
MiniMax-M3
19
$1.16
14.9
79.79
0.8%
1M
Open
Google logo
Gemma 4 31B
4
--
--
76.21
0.6%
262k
Open
OpenAI logo
gpt-oss-120b (high)
4
$0.12
7.9
13.23
2.6%
131k
Open
Z AI logo
GLM-4.5V (non-reasoning)
--
--
--
8.07
0.0%
66k
Open
DeepSeek logo
DeepSeek V3.1 Terminus (FP8)
--
--
--
--
--
131k
Open
Kimi logo
Kimi K2.6
--
--
--
76.44
0.0%
262k
Open
DeepSeek logo
DeepSeek R1 (Jan) Turbo
--
--
--
--
--
64k
Open
DeepSeek logo
DeepSeek R1 (Jan)
--
--
--
--
--
64k
Open
Alibaba logo
Qwen3.5 397B A17B
--
--
--
38.88
2.8%
262k
Open
Kimi logo
Kimi K2.6 (non-reasoning)
--
--
--
9.53
0.0%
262k
Open
MiniMax logo
MiniMax-M2.5
--
--
--
22.07
0.0%
205k
Open
Alibaba logo
Qwen3.5 27B
--
--
--
37.17
10.2%
262k
Open
DeepSeek logo
DeepSeek V3.1
--
--
--
--
--
131k
Open
Alibaba logo
Qwen3.5 122B A10B
--
--
--
34.97
0.8%
262k
Open
NVIDIA logo
Nemotron 3 Nano (non-reasoning) (FP4)
--
--
--
1.80
0.0%
262k
Open
Google logo
Gemma 3 27B
--
--
--
0.87
0.0%
98k
Open
Z AI logo
GLM-4.7-Flash
--
--
--
37.48
0.0%
200k
Open
Z AI logo
GLM-4.5V
--
--
--
17.77
0.0%
66k
Open
Alibaba logo
Qwen3.5 397B A17B (non-reasoning)
--
--
--
2.62
0.0%
262k
Open
Alibaba logo
Qwen3.6 27B (non-reasoning)
--
--
--
44.16
4.7%
262k
Open
Z AI logo
GLM-5 FP8
--
--
--
24.42
0.0%
203k
Open
Z AI logo
GLM-4.6V (non-reasoning)
--
--
--
7.58
18.9%
131k
Open
DeepSeek logo
DeepSeek V3 (Dec)
--
--
--
1.53
0.0%
64k
Open
Kimi logo
Kimi K2
--
--
--
7.00
2.3%
131k
Open
Alibaba logo
Qwen3.5 35B A3B
--
--
--
32.40
0.0%
262k
Open
MiniMax logo
MiniMax-M2.7 (FP8)
--
--
--
17.52
0.0%
205k
Open
Alibaba logo
Qwen3 VL 30B A3B
--
--
--
2.56
20.0%
131k
Open
Z AI logo
GLM-5.1 (FP8)
--
--
--
51.92
0.0%
205k
Open
DeepSeek logo
DeepSeek V4 Pro (high)
--
--
--
--
--
1M
Open
Kimi logo
Kimi K2 0905
--
--
--
2.37
0.0%
262k
Open
Alibaba logo
Qwen3.6 35B A3B (non-reasoning)
--
--
--
3.27
2.2%
205k
Open
Z AI logo
GLM-4.6
--
--
--
51.62
0.0%
205k
Open
Google logo
Gemma 4 26B A4B
--
--
--
29.66
1.3%
262k
Open
Z AI logo
GLM-4.7
--
--
--
53.69
0.0%
205k
Open
Google logo
Gemma 4 26B A4B (non-reasoning)
--
--
--
2.10
0.7%
262k
Open
Meta logo
Llama 3.1 8B
--
--
--
1.45
0.0%
16k
Open
NVIDIA logo
Nemotron 3 Nano (FP4)
--
--
--
7.23
0.6%
262k
Open
Z AI logo
GLM-4.7 (non-reasoning)
--
--
--
8.13
0.0%
205k
Open
Meta logo
Llama 3 8B
--
--
--
--
--
8k
Open
Alibaba logo
Qwen3.6 35B A3B
--
--
--
26.16
3.2%
205k
Open
Alibaba logo
Qwen3.6 27B
--
--
--
44.04
2.2%
262k
Open
Kimi logo
Kimi K2.7 Code
--
--
--
53.38
0.0%
262k
Open
Meta logo
Llama 4 Maverick (FP8)
--
--
--
2.31
1.0%
1M
Open
Z AI logo
GLM-5.1 (non-reasoning) (FP8)
--
--
--
7.99
0.0%
205k
Open
Z AI logo
GLM-4.6 (non-reasoning)
--
--
--
11.59
0.0%
205k
Open
Meta logo
Llama 3.3 70B
--
--
--
4.58
0.8%
131k
Open
MiniMax logo
MiniMax M1 80k
--
--
--
4.27
2.2%
1M
Open
Kimi logo
Kimi K2.5
--
--
--
33.07
0.0%
262k
Open
DeepSeek logo
DeepSeek R1 0528
--
--
--
60.07
1.9%
164k
Open
Meta logo
Llama 3 70B
--
--
--
--
--
8k
Open
Meta logo
Llama 4 Scout
--
--
--
1.60
7.5%
131k
Open
Tencent logo
Hy3
--
--
--
45.05
0.0%
262k
Open
Kimi logo
Kimi K2.5 (non-reasoning)
--
--
--
9.73
0.0%
262k
Open
Kimi logo
Kimi K2 Thinking
--
--
--
30.95
0.0%
262k
Open
DeepSeek logo
DeepSeek V4 Pro (max)
--
--
--
64.86
0.0%
1M
Open
Z AI logo
GLM-4.7-Flash (non-reasoning)
--
--
--
32.47
5.4%
200k
Open
OpenAI logo
gpt-oss-120b (low)
--
--
--
3.30
6.0%
131k
Open
Google logo
Gemma 4 31B (non-reasoning)
--
--
--
4.31
0.7%
262k
Open
Z AI logo
GLM-4.6V
--
--
--
27.99
23.2%
131k
Open
DeepSeek logo
DeepSeek V4.1 Flash (max)
--
--
--
60.83
0.0%
524k
Open
DeepSeek logo
DeepSeek V3.1 Terminus (non-reasoning) (FP8)
--
--
--
--
--
131k
Open
Z AI logo
GLM-5 (non-reasoning) (FP8)
--
--
--
2.54
0.0%
203k
Open
Z AI logo
GLM-5.2 (max) (FP8)
--
--
--
35.40
0.0%
1M
Open
DeepSeek logo
DeepSeek V3.1 (non-reasoning)
--
--
--
--
--
164k
Open
DeepSeek logo
DeepSeek V4 Flash 0731 (max)
--
--
--
55.46
0.0%
1M
Open

Key definitions

Frequently Asked Questions

Common questions about Novita