Skip to content

Same-model provider benchmark

DekaLLM vs Nebius: LLM provider comparison

Compare DekaLLM and Nebius on 3 exact shared text models. ProviderBench keeps speed, price, and catalog coverage separate so naturally faster model catalogs cannot distort the result.

DekaLLM

7 indexed models

Headquarters
Indonesia
Server regions
Indonesia
Model types
7 text

Nebius

13 indexed models

Headquarters
Netherlands
Server regions
N/a
Model types
12 text, 1 embeddings

At a glance

Metric winners

There is no overall score. Each winner answers one specific question using only directly comparable data.

Fastest on shared models

2.68× typical advantage

3 exact models with complete recent speed data

Lowest token cost

$0.1478 / 1M

3 exact models using a 1K-input/500-output mix

Most models available

13 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

MetricDekaLLMNebius
Typical 500-token response17.74 s6.62 s
Typical response start1.07 s0.67 s
Typical output speed30.0 tok/s84.0 tok/s
Blended token price$0.1478 / 1M$0.3222 / 1M
Typical route uptime98.29%99.41%

Visual comparison

Price and performance charts

DekaLLMNebius
500-token response by shared model

Estimated seconds using recent median response-start and output-speed data. Lower is better.

Nebius has the lower typical same-model response ratio across 3 measured models.

Blended token price by shared model

USD per 1 million tokens using a 1,000-input/500-output mix. Lower is better.

DekaLLM has the lower typical price ratio across 3 priced shared models.

Shared text models

3 exact models · newest first

ModelDekaLLMNebius
Nemotron 3 SuperWinner · Nebius

nvidia/nemotron-3-super-120b-a12b

DekaLLM
Blended price
$0.2033 / 1M
500-token response
194.23 s
Response starts
27.56 s
Output speed
3.0 tok/s
Route uptime
73.86%
Context
262.1K
Route
dekallm/fp8
Nebius
Blended price
$0.5 / 1M
500-token response
7.85 s
Response starts
1.67 s
Output speed
81.0 tok/s
Route uptime
99.41%
Context
262.1K
Route
nebius/fp4
gpt-oss-120bWinner · DekaLLM

openai/gpt-oss-120b

DekaLLM
Blended price
$0.08 / 1M
500-token response
17.74 s
Response starts
1.07 s
Output speed
30.0 tok/s
Route uptime
98.29%
Context
131.1K
Route
dekallm/bf16
Nebius
Blended price
$0.3 / 1M
500-token response
6.62 s
Response starts
0.67 s
Output speed
84.0 tok/s
Route uptime
97.33%
Context
131.1K
Route
nebius/fp4

qwen/qwen3-30b-a3b-instruct-2507

DekaLLM
Blended price
$0.16 / 1M
500-token response
7.16 s
Response starts
0.40 s
Output speed
74.0 tok/s
Route uptime
98.65%
Context
262.1K
Route
dekallm
Nebius
Blended price
$0.1667 / 1M
500-token response
5.30 s
Response starts
0.30 s
Output speed
100.0 tok/s
Route uptime
99.67%
Context
262.1K
Route
nebius/fp8

A per-model winner combines blended price and estimated 500-token response time with equal proportional weight. Ties and rows missing either measurement receive no badge. Comparison data calculated . Values use one deterministic route per provider and model; missing measurements remain visible as N/a.

DekaLLM vs Nebius analysis

How DekaLLM and Nebius compare for AI inference

DekaLLM and Nebius share 3 indexed text models, including Nemotron 3 Super, gpt-oss-120b, Qwen3 30B A3B Instruct 2507. Nebius has the stronger typical response-time result on the directly measured set.

Same-model speed evidence

3 shared models currently have complete response-start and output-speed measurements on both providers. The speed comparison uses per-model ratios before taking the median, so naturally faster model catalogs do not improve the result.

Token pricing on one workload

3 shared models have complete input and output prices on both providers. Prices use the same 1,000-input/500-output-token mix and are normalized to one million tokens for readability.

Catalog and deployment differences

DekaLLM has 7 indexed models and lists 1 published server region; Nebius has 13 models and lists no regions. Verify data residency, privacy terms, limits, and production latency directly before choosing.

Related same-model benchmarks

Compare with other providers

Explore qualified alternatives with the most shared measured models. Recommendations include comparisons for both DekaLLM and Nebius.