API host · catalogue checked 27 Oct 2026

Venice: models, prices and uptime

Venice serves 15 of the 78 models we benchmark through OpenRouter. Prices are OpenRouter's list prices per million tokens. We did not measure speed per host.

Models served15of 78 we test

Cheapest host for2of 15 shared models

Median premium+69%over the cheapest host

Uptime97.3%last 30 min, average

Most accurate models on Venice

Verification score of each model this host serves

1DeepSeek V4 Pro 0813DeepSeek71.2%
2GLM 5.3 FlashZ.ai67.5%
3GLM 5.3Z.ai67.5%
4Kimi K2.7 CodeMoonshotAI65.0%
5Qwen3.8 27BQwen63.8%
6MiMo-V2.6-FlashXiaomi62.5%
7Nemotron 3 UltraNVIDIA60.0%
8gpt-oss-120bOpenAI58.8%
9Qwen3.8 2.4T A95BQwen57.5%
10MiniMax M3MiniMax57.5%
11Nemotron 3.5 Super VLNVIDIA40.0%
12Qwen3.6 35B A3BQwen37.5%
13Qwen3.5 397B A17BQwen32.5%
14Gemma 4 31BGoogle30.0%
15Gemma 4 26B A4BGoogle15.0%

Models on Venice

Premium: this host's blended price (3 input : 1 output) against the cheapest host for the same model

Model	Score	Input / 1M	Output / 1M	vs cheapest host	Hosts	Context	Max output	Quantization	Uptime
DeepSeek V4 Pro 0813	71.2%	$1.65	$4.95	+1079%	23	1M	33k	—	—
GLM 5.3 Flash	67.5%	$0.15	$0.5	+406%	34	1M	131k	—	100%
GLM 5.3	67.5%	$1.4	$4.4	+434%	37	1M	131k	—	100%
Kimi K2.7 Code	65.0%	$0.75	$3.5	+20%	11	256k	66k	int4	—
Qwen3.8 27B	63.8%	$0.45	$3.2	+569%	21	262k	66k	fp8	100%
MiMo-V2.6-Flash	62.5%	$0.175	$0.35	+51%	10	1M	131k	fp8	100%
Nemotron 3 Ultra	60.0%	$0.625	$3.125	+69%	3	256k	33k	fp8	75.0%
gpt-oss-120b	58.8%	$0.03	$0.15	Cheapest	23	128k	33k	int4	89.7%
Qwen3.8 2.4T A95B	57.5%	$2	$6	Cheapest	5	262k	66k	—	100%
MiniMax M3	57.5%	$0.3	$1.2	+35%	12	524k	66k	fp8	100%
Nemotron 3.5 Super VL	40.0%	$0.25	$1.25	+277%	9	262k	33k	fp4	100%
Qwen3.6 35B A3B	37.5%	$0.1	$1	+53%	10	256k	66k	fp8	100%
Qwen3.5 397B A17B	32.5%	$0.75	$4.5	+92%	10	128k	33k	—	100%
Gemma 4 31B	30.0%	$0.12	$0.36	+12%	13	256k	8k	fp4	100%
Gemma 4 26B A4B	15.0%	$0.13	$0.4	+128%	15	256k	8k	bf16	100%

All API hosts →

Venice: frequently asked questions

Which AI models does Venice serve?: Of the models we benchmark, Venice serves 15 through OpenRouter: DeepSeek V4 Pro 0813, GLM 5.3 Flash, GLM 5.3, Kimi K2.7 Code, Qwen3.8 27B, MiMo-V2.6-Flash, Nemotron 3 Ultra, gpt-oss-120b, Qwen3.8 2.4T A95B, MiniMax M3, Nemotron 3.5 Super VL, Qwen3.6 35B A3B, Qwen3.5 397B A17B, Gemma 4 31B, Gemma 4 26B A4B.
What is the most accurate model on Venice?: DeepSeek V4 Pro 0813 by DeepSeek, with a verification score of 71.2% (57 of 80 questions correct) in our tests.
Is Venice the cheapest host?: Venice has the lowest list price for 2 of the 15 models it serves that other hosts also serve (gpt-oss-120b, Qwen3.8 2.4T A95B). Its median markup over the cheapest host is +69%.
How reliable is Venice?: Averaged over the models it serves, Venice reported 97.3% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.

Model

Score

Input / 1M

Output / 1M

vs cheapest host

Hosts

Context

Max output

Quantization

Uptime

DeepSeek V4 Pro 0813

71.2%

$1.65

$4.95

+1079%

33k

—

GLM 5.3 Flash

67.5%

$0.15

$0.5

+406%

131k

—

100%

GLM 5.3

67.5%

$1.4

$4.4

+434%

131k

—

100%

Kimi K2.7 Code

65.0%

$0.75

$3.5

+20%

256k

66k

int4

—

Qwen3.8 27B

63.8%

$0.45

$3.2

+569%

262k

66k

fp8

100%

MiMo-V2.6-Flash

62.5%

$0.175

$0.35

+51%

131k

fp8

100%

Nemotron 3 Ultra

60.0%

$0.625

$3.125

+69%

256k

33k

fp8

75.0%

gpt-oss-120b

58.8%

$0.03

$0.15

Cheapest

128k

33k

int4

89.7%

Qwen3.8 2.4T A95B

57.5%

Cheapest

262k

66k

—

100%

MiniMax M3

57.5%

$0.3

$1.2

+35%

524k

66k

fp8

100%

Nemotron 3.5 Super VL

40.0%

$0.25

$1.25

+277%

262k

33k

fp4

100%

Qwen3.6 35B A3B

37.5%

$0.1

+53%

256k

66k

fp8

100%

Qwen3.5 397B A17B

32.5%

$0.75

$4.5

+92%

128k

33k

—

100%

Gemma 4 31B

30.0%

$0.12

$0.36

+12%

256k

fp4

100%

Gemma 4 26B A4B

15.0%

$0.13

$0.4

+128%

256k

bf16

100%

Venice: frequently asked questions

Which AI models does Venice serve?

Of the models we benchmark, Venice serves 15 through OpenRouter: DeepSeek V4 Pro 0813, GLM 5.3 Flash, GLM 5.3, Kimi K2.7 Code, Qwen3.8 27B, MiMo-V2.6-Flash, Nemotron 3 Ultra, gpt-oss-120b, Qwen3.8 2.4T A95B, MiniMax M3, Nemotron 3.5 Super VL, Qwen3.6 35B A3B, Qwen3.5 397B A17B, Gemma 4 31B, Gemma 4 26B A4B.

What is the most accurate model on Venice?

DeepSeek V4 Pro 0813 by DeepSeek, with a verification score of 71.2% (57 of 80 questions correct) in our tests.

Is Venice the cheapest host?

Venice has the lowest list price for 2 of the 15 models it serves that other hosts also serve (gpt-oss-120b, Qwen3.8 2.4T A95B). Its median markup over the cheapest host is +69%.

How reliable is Venice?

Averaged over the models it serves, Venice reported 97.3% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.