Skip to content
ProviderBench home

Same-model provider benchmark

DeepInfra vs ModelRun: LLM provider comparison

Compare DeepInfra and ModelRun on 4 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

ModelRun

4 indexed models

Headquarters
United States
Server regions
United States
Model types
4 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

ModelRun

2.16× typical advantage

4 exact models with complete recent speed data

Lowest token cost

DeepInfra

$1.145 / 1M

4 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

MetricDeepInfraModelRun
Typical 500-token response16.24 s10.42 s
Typical response start0.88 s0.70 s
Typical output speed32.5 tok/s62.0 tok/s
Blended token price$1.145 / 1M$1.1617 / 1M
Typical route uptime99.95%98.72%

Visual comparison

Price and performance charts

DeepInfraModelRun
500-token response by shared model

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

ModelRun has the lower typical same-model response ratio across 4 measured models.

Blended token price by shared model

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

DeepInfra has the lower typical price ratio across 4 priced shared models.

Shared text models

4 exact models · newest first

ModelDeepInfraModelRun
Kimi K2.7 CodeWinner · ModelRun

moonshotai/kimi-k2.7-code

DeepInfra
Blended price
$1.66 / 1M
500-token response
15.92 s
Response starts
0.77 s
Output speed
33.0 tok/s
Route uptime
100.00%
Context
262.1K
Route
deepinfra/fp4
ModelRun
Blended price
$1.8167 / 1M
500-token response
3.35 s
Response starts
0.46 s
Output speed
173.0 tok/s
Route uptime
98.81%
Context
262.1K
Route
modelrun/fp4
Kimi K2.6Winner · DeepInfra

moonshotai/kimi-k2.6

DeepInfra
Blended price
$1.6667 / 1M
500-token response
12.84 s
Response starts
0.93 s
Output speed
42.0 tok/s
Route uptime
99.94%
Context
262.1K
Route
deepinfra/fp4
ModelRun
Blended price
$1.6 / 1M
500-token response
13.99 s
Response starts
1.49 s
Output speed
40.0 tok/s
Route uptime
98.64%
Context
262.1K
Route
modelrun/fp4
Gemma 4 31BWinner · ModelRun

google/gemma-4-31b-it

DeepInfra
Blended price
$0.2033 / 1M
500-token response
22.57 s
Response starts
0.83 s
Output speed
23.0 tok/s
Route uptime
99.06%
Context
262.1K
Route
deepinfra/turbo
ModelRun
Blended price
$0.33 / 1M
500-token response
6.85 s
Response starts
0.90 s
Output speed
84.0 tok/s
Route uptime
97.84%
Context
262.1K
Route
modelrun/fp4
Kimi K2.5Winner · ModelRun

moonshotai/kimi-k2.5

DeepInfra
Blended price
$1.05 / 1M
500-token response
16.56 s
Response starts
0.93 s
Output speed
32.0 tok/s
Route uptime
99.96%
Context
262.1K
Route
deepinfra/fp4
ModelRun
Blended price
$0.9 / 1M
500-token response
16.12 s
Response starts
0.50 s
Output speed
32.0 tok/s
Route uptime
99.76%
Context
262.1K
Route
modelrun/fp4

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 ModelRun analysis

How DeepInfra and ModelRun compare for AI inference

DeepInfra and ModelRun share 4 indexed text models, including Kimi K2.7 Code, Kimi K2.6, Gemma 4 31B, Kimi K2.5. ModelRun has the stronger typical response-time result on the directly measured set.

Same-model speed evidence

4 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

4 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; ModelRun has 4 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 ModelRun.

DeepInfra vs NovitaAI

45 shared model benchmarks

ModelRun vs SiliconFlow

4 shared model benchmarks

DeepInfra vs Venice

26 shared model benchmarks

ModelRun vs AtlasCloud

3 shared model benchmarks

DeepInfra vs Parasail

23 shared model benchmarks

ModelRun vs Chutes

3 shared model benchmarks