Skip to content
ProviderBench home

Same-model provider benchmark

DeepInfra vs DekaLLM: LLM provider comparison

Compare DeepInfra and DekaLLM on 5 exact shared text models. ProviderBench keeps speed, price, and catalog coverage separate so naturally faster model catalogs cannot distort the result.

DeepInfra

87 indexed models

Headquarters
United States
Server regions
N/a
Model types
67 text, 15 embeddings, 5 speech

DekaLLM

7 indexed models

Headquarters
Indonesia
Server regions
Indonesia
Model types
7 text

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

DeepInfra

1.47× typical advantage

5 exact models with complete recent speed data

Lowest token cost

DekaLLM

$0.1045 / 1M

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

Most models available

DeepInfra

87 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

MetricDeepInfraDekaLLM
Typical 500-token response17.02 s17.74 s
Typical response start0.49 s1.05 s
Typical output speed33.0 tok/s30.0 tok/s
Blended token price$0.1049 / 1M$0.1045 / 1M
Typical route uptime98.93%98.29%

Visual comparison

Price and performance charts

DeepInfraDekaLLM
500-token response by shared model

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

DeepInfra has the lower typical same-model response ratio across 5 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 5 priced shared models.

Shared text models

5 exact models · newest first

ModelDeepInfraDekaLLM
Gemma 4 26B A4BWinner · DekaLLM

google/gemma-4-26b-a4b-it

DeepInfra
Blended price
$0.16 / 1M
500-token response
22.23 s
Response starts
0.49 s
Output speed
23.0 tok/s
Route uptime
99.62%
Context
262.1K
Route
deepinfra/fp8
DekaLLM
Blended price
$0.15 / 1M
500-token response
11.47 s
Response starts
1.05 s
Output speed
48.0 tok/s
Route uptime
96.48%
Context
262.1K
Route
dekallm/bf16
Nemotron 3 SuperWinner · DeepInfra

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

DeepInfra
Blended price
$0.19 / 1M
500-token response
41.88 s
Response starts
6.16 s
Output speed
14.0 tok/s
Route uptime
90.39%
Context
262.1K
Route
deepinfra/bf16
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
gpt-oss-120bWinner · DeepInfra

openai/gpt-oss-120b

DeepInfra
Blended price
$0.0813 / 1M
500-token response
12.10 s
Response starts
0.47 s
Output speed
43.0 tok/s
Route uptime
94.64%
Context
131.1K
Route
deepinfra/bf16
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
gpt-oss-20bWinner · DeepInfra

openai/gpt-oss-20b

DeepInfra
Blended price
$0.0667 / 1M
500-token response
5.15 s
Response starts
0.35 s
Output speed
104.0 tok/s
Route uptime
99.78%
Context
131.1K
Route
deepinfra/bf16
DekaLLM
Blended price
$0.066 / 1M
500-token response
32.15 s
Response starts
0.90 s
Output speed
16.0 tok/s
Route uptime
99.13%
Context
131.1K
Route
dekallm/bf16
Mistral NemoWinner · DekaLLM

mistralai/mistral-nemo

DeepInfra
Blended price
$0.0267 / 1M
500-token response
17.02 s
Response starts
1.87 s
Output speed
33.0 tok/s
Route uptime
98.93%
Context
131.1K
Route
deepinfra/fp8
DekaLLM
Blended price
$0.0233 / 1M
500-token response
14.46 s
Response starts
0.57 s
Output speed
36.0 tok/s
Route uptime
99.48%
Context
131.1K
Route
dekallm/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.

DeepInfra vs DekaLLM analysis

How DeepInfra and DekaLLM compare for AI inference

DeepInfra and DekaLLM share 5 indexed text models, including Gemma 4 26B A4B, Nemotron 3 Super, gpt-oss-120b, gpt-oss-20b, Mistral Nemo. DeepInfra has the stronger typical response-time result on the directly measured set.

Same-model speed evidence

5 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

5 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

DeepInfra has 87 indexed models and lists no published server regions; DekaLLM has 7 models and lists 1 region. 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 DeepInfra and DekaLLM.

DeepInfra vs NovitaAI

45 shared model benchmarks

DekaLLM vs SiliconFlow

5 shared model benchmarks

DeepInfra vs Venice

26 shared model benchmarks

DekaLLM vs Parasail

4 shared model benchmarks

DeepInfra vs AtlasCloud

22 shared model benchmarks

DekaLLM vs Weights & Biases

4 shared model benchmarks