Skip to content
ProviderBench home

Same-model provider benchmark

CoreWeave vs Friendli: LLM provider comparison

Compare CoreWeave and Friendli on 4 exact shared text models. ProviderBench keeps speed, price, and catalog coverage separate so naturally faster model catalogs cannot distort the result.

CoreWeave

20 indexed models

Headquarters
United States
Server regions
United States
Model types
20 text

Friendli

6 indexed models

Headquarters
United States
Server regions
N/a
Model types
6 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

Friendli

1.56× typical advantage

4 exact models with complete recent speed data

Lowest token cost

CoreWeave

$1.3975 / 1M

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

Most models available

CoreWeave

20 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

MetricCoreWeave(0)Friendli(0)
SpeedCoreWeave13.50 sFriendli8.37 s
TTFTCoreWeave0.95 sFriendli1.06 s
TPSCoreWeave54.0 tok/sFriendli76.0 tok/s
UptimeCoreWeave99.98%Friendli99.99%
BlendedCoreWeave$1.3975 / 1MFriendli$1.4067 / 1M
Green value Better comparable resultRed value Worse comparable result

Visual comparison

Price and performance charts

CoreWeaveFriendli
500-token response by shared model

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

Friendli 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.

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

Shared text models

4 exact models · newest first

ModelCoreWeave(0)Friendli(0)
GLM 5.2Winner · Friendli
CoreWeave
Speed— Worst comparable value
20.46 s
TTFT— Worst comparable value
1.94 s
TPS— Worst comparable value
27.0 tok/s
Uptime— Worst comparable value
99.96%
Context
262.1K
Route
coreweave/fp4
Blended— Best comparable value
$2.3933 / 1M
Friendli
Speed— Best comparable value
11.48 s
TTFT— Best comparable value
1.68 s
TPS— Best comparable value
51.0 tok/s
Uptime— Best comparable value
99.98%
Context
1M
Route
friendli
Blended— Worst comparable value
$2.4 / 1M
GLM 5.1Winner · CoreWeave
CoreWeave
Speed— Best comparable value
4.38 s
TTFT— Worst comparable value
0.50 s
TPS— Best comparable value
129.0 tok/s
Uptime
100.00%
Context
202.8K
Route
coreweave/fp8
Blended
$2.4 / 1M
Friendli
Speed— Worst comparable value
5.26 s
TTFT— Best comparable value
0.31 s
TPS— Worst comparable value
101.0 tok/s
Uptime
100.00%
Context
202.8K
Route
friendli
Blended
$2.4 / 1M
Gemma 4 31BWinner · Friendli
CoreWeave
Speed— Worst comparable value
30.82 s
TTFT— Best comparable value
1.41 s
TPS— Worst comparable value
17.0 tok/s
Uptime— Worst comparable value
77.67%
Context
262.1K
Route
coreweave/bf16
Blended— Best comparable value
$0.1967 / 1M
Friendli
Speed— Best comparable value
16.41 s
TTFT— Worst comparable value
5.30 s
TPS— Best comparable value
45.0 tok/s
Uptime— Best comparable value
99.90%
Context
262.1K
Route
friendli
Blended— Worst comparable value
$0.2267 / 1M
MiniMax M2.5Winner · Friendli
CoreWeave
Speed— Worst comparable value
6.55 s
TTFT— Best comparable value
0.38 s
TPS— Worst comparable value
81.0 tok/s
Uptime
100.00%
Context
196.6K
Route
coreweave/fp8
Blended
$0.6 / 1M
Friendli
Speed— Best comparable value
4.90 s
TTFT— Worst comparable value
0.44 s
TPS— Best comparable value
112.0 tok/s
Uptime
100.00%
Context
196.6K
Route
friendli
Blended
$0.6 / 1M

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.

CoreWeave vs Friendli analysis

How CoreWeave and Friendli compare for AI inference

CoreWeave and Friendli share 4 indexed text models, including GLM 5.2, GLM 5.1, Gemma 4 31B, MiniMax M2.5. Friendli 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

CoreWeave has 20 indexed models and lists 1 published server region; Friendli has 6 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 CoreWeave and Friendli.

CoreWeave vs DeepInfra

16 shared model benchmarks

Friendli vs NovitaAI

6 shared model benchmarks

CoreWeave vs SiliconFlow

15 shared model benchmarks

Friendli vs Venice

6 shared model benchmarks

CoreWeave vs Parasail

13 shared model benchmarks

Friendli vs AtlasCloud

5 shared model benchmarks