Skip to content

Same-model provider benchmark

DeepInfra vs DigitalOcean: LLM provider comparison

Compare DeepInfra and DigitalOcean on 15 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

DigitalOcean

16 indexed models

Headquarters
N/a
Server regions
N/a
Model types
16 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

1.86× typical advantage

15 exact models with complete recent speed data

Lowest token cost

$0.967 / 1M

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

Most models available

87 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

MetricDeepInfraDigitalOcean
Typical 500-token response16.56 s32.65 s
Typical response start0.93 s1.13 s
Typical output speed32.0 tok/s16.0 tok/s
Blended token price$0.967 / 1M$0.989 / 1M
Typical route uptime99.20%98.97%

Visual comparison

Price and performance charts

DeepInfraDigitalOcean
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 15 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 15 priced shared models.

Shared text models

15 exact models · newest first

ModelDeepInfraDigitalOcean
GLM 5.2Winner · DigitalOcean

z-ai/glm-5.2

DeepInfra
Blended price
$1.62 / 1M
500-token response
42.37 s
Response starts
0.70 s
Output speed
12.0 tok/s
Route uptime
N/a
Context
1M
Route
deepinfra/fp4
DigitalOcean
Blended price
$2.1667 / 1M
500-token response
12.22 s
Response starts
1.11 s
Output speed
45.0 tok/s
Route uptime
98.78%
Context
262.1K
Route
digitalocean
DeepSeek V4 ProWinner · DeepInfra

deepseek/deepseek-v4-pro

DeepInfra
Blended price
$1.7333 / 1M
500-token response
18.19 s
Response starts
0.94 s
Output speed
29.0 tok/s
Route uptime
98.79%
Context
1M
Route
deepinfra/fp4
DigitalOcean
Blended price
$1.856 / 1M
500-token response
33.90 s
Response starts
0.57 s
Output speed
15.0 tok/s
Route uptime
99.92%
Context
262.1K
Route
digitalocean
DeepSeek V4 FlashWinner · DeepInfra

deepseek/deepseek-v4-flash

DeepInfra
Blended price
$0.12 / 1M
500-token response
20.36 s
Response starts
1.13 s
Output speed
26.0 tok/s
Route uptime
99.43%
Context
1M
Route
deepinfra/fp4
DigitalOcean
Blended price
$0.1493 / 1M
500-token response
39.59 s
Response starts
1.13 s
Output speed
13.0 tok/s
Route uptime
99.79%
Context
262.1K
Route
digitalocean
MiMo-V2.5-ProWinner · DigitalOcean

xiaomi/mimo-v2.5-pro

DeepInfra
Blended price
$1.6667 / 1M
500-token response
10.84 s
Response starts
0.64 s
Output speed
49.0 tok/s
Route uptime
89.51%
Context
1M
Route
deepinfra/fp8
DigitalOcean
Blended price
$1.4 / 1M
500-token response
11.70 s
Response starts
1.06 s
Output speed
47.0 tok/s
Route uptime
99.79%
Context
262.1K
Route
digitalocean
MiMo-V2.5Winner · DigitalOcean

xiaomi/mimo-v2.5

DeepInfra
Blended price
$0.9333 / 1M
500-token response
10.57 s
Response starts
0.37 s
Output speed
49.0 tok/s
Route uptime
98.97%
Context
262.1K
Route
deepinfra/bf16
DigitalOcean
Blended price
$0.1633 / 1M
500-token response
32.65 s
Response starts
1.40 s
Output speed
16.0 tok/s
Route uptime
97.47%
Context
262.1K
Route
digitalocean
Kimi K2.6Winner · DigitalOcean

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
DigitalOcean
Blended price
$1.5733 / 1M
500-token response
13.08 s
Response starts
0.89 s
Output speed
41.0 tok/s
Route uptime
99.04%
Context
262.1K
Route
digitalocean
GLM 5.1Winner · DeepInfra

z-ai/glm-5.1

DeepInfra
Blended price
$1.8667 / 1M
500-token response
18.81 s
Response starts
1.57 s
Output speed
29.0 tok/s
Route uptime
99.92%
Context
202.8K
Route
deepinfra/fp4
DigitalOcean
Blended price
$2.0833 / 1M
500-token response
29.06 s
Response starts
1.28 s
Output speed
18.0 tok/s
Route uptime
57.53%
Context
163.8K
Route
digitalocean
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
DigitalOcean
Blended price
$0.2917 / 1M
500-token response
92.33 s
Response starts
8.99 s
Output speed
6.0 tok/s
Route uptime
97.62%
Context
1M
Route
digitalocean
Qwen3.5 397B A17BWinner · DeepInfra

qwen/qwen3.5-397b-a17b

DeepInfra
Blended price
$1.3 / 1M
500-token response
14.53 s
Response starts
0.64 s
Output speed
36.0 tok/s
Route uptime
79.03%
Context
262.1K
Route
deepinfra/fp8
DigitalOcean
Blended price
$1.0733 / 1M
500-token response
60.33 s
Response starts
4.77 s
Output speed
9.0 tok/s
Route uptime
81.67%
Context
131.1K
Route
digitalocean
MiniMax M2.5Winner · DigitalOcean

minimax/minimax-m2.5

DeepInfra
Blended price
$0.4833 / 1M
500-token response
11.21 s
Response starts
1.01 s
Output speed
49.0 tok/s
Route uptime
100.00%
Context
196.6K
Route
deepinfra/fp8
DigitalOcean
Blended price
$0.45 / 1M
500-token response
8.35 s
Response starts
0.78 s
Output speed
66.0 tok/s
Route uptime
100.00%
Context
65.5K
Route
digitalocean
GLM 5Winner · DeepInfra

z-ai/glm-5

DeepInfra
Blended price
$1.0933 / 1M
500-token response
21.01 s
Response starts
1.01 s
Output speed
25.0 tok/s
Route uptime
99.79%
Context
202.8K
Route
deepinfra/fp4
DigitalOcean
Blended price
$1.3 / 1M
500-token response
63.85 s
Response starts
1.35 s
Output speed
8.0 tok/s
Route uptime
95.70%
Context
64K
Route
digitalocean
Kimi K2.5Winner · DeepInfra

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
DigitalOcean
Blended price
$0.925 / 1M
500-token response
34.35 s
Response starts
1.01 s
Output speed
15.0 tok/s
Route uptime
99.45%
Context
262.1K
Route
digitalocean
DeepSeek V3.2Winner · DeepInfra

deepseek/deepseek-v3.2

DeepInfra
Blended price
$0.3 / 1M
500-token response
42.39 s
Response starts
0.73 s
Output speed
12.0 tok/s
Route uptime
83.26%
Context
163.8K
Route
deepinfra/fp4
DigitalOcean
Blended price
$0.7367 / 1M
500-token response
57.26 s
Response starts
1.71 s
Output speed
9.0 tok/s
Route uptime
96.84%
Context
163.8K
Route
digitalocean
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
DigitalOcean
Blended price
$0.21 / 1M
500-token response
25.10 s
Response starts
3.36 s
Output speed
23.0 tok/s
Route uptime
98.90%
Context
128K
Route
digitalocean
Llama 4 MaverickWinner · DeepInfra

meta-llama/llama-4-maverick

DeepInfra
Blended price
$0.4 / 1M
500-token response
13.13 s
Response starts
0.31 s
Output speed
39.0 tok/s
Route uptime
99.97%
Context
1M
Route
deepinfra/base
DigitalOcean
Blended price
$0.4567 / 1M
500-token response
13.42 s
Response starts
0.26 s
Output speed
38.0 tok/s
Route uptime
99.94%
Context
128K
Route
digitalocean

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 DigitalOcean analysis

How DeepInfra and DigitalOcean compare for AI inference

DeepInfra and DigitalOcean share 15 indexed text models, including GLM 5.2, DeepSeek V4 Pro, DeepSeek V4 Flash, MiMo-V2.5-Pro, MiMo-V2.5. DeepInfra has the stronger typical response-time result on the directly measured set.

Same-model speed evidence

15 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

15 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; DigitalOcean has 16 models and lists no regions. Verify data residency, privacy terms, limits, and production latency directly before choosing.