API host · catalogue checked 27 Oct 2026

Parasail: models, prices and uptime

Parasail serves 16 of the 78 models we benchmark through OpenRouter, 1 of them on no other host. Prices are OpenRouter's list prices per million tokens. We did not measure speed per host.

Models served16of 78 we test

Cheapest host for0of 15 shared models

Median premium+87%over the cheapest host

Uptime97.6%last 30 min, average

Most accurate models on Parasail

Verification score of each model this host serves

1DeepSeek V4.1 Flash 1017DeepSeek73.8%
2DeepSeek V4 Pro 0813DeepSeek71.2%
3GLM 5.3 FlashZ.ai67.5%
4GLM 5.3Z.ai67.5%
5MiniMax M3.1 FlashMiniMax66.2%
6Qwen3.8 27BQwen63.8%
7Qwen3 Coder NextQwen62.5%
8Llama 4 MaverickMeta59.0%
9gpt-oss-120bOpenAI58.8%
10MiniMax M3MiniMax57.5%
11gpt-oss-20bOpenAI51.2%
12Llama 3.3 70B InstructMeta42.5%
13Qwen3.6 35B A3BQwen37.5%
14Qwen3.5 397B A17BQwen32.5%
15Gemma 4 31BGoogle30.0%
16Gemma 4 26B A4BGoogle15.0%

Models on Parasail

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 V4.1 Flash 1017	73.8%	$0.3	$1.2	+364%	30	1M	944k	fp8	100%
DeepSeek V4 Pro 0813	71.2%	$1.32	$3.96	+843%	23	1M	944k	fp8	100%
GLM 5.3 Flash	67.5%	$0.15	$0.5	+406%	34	1M	944k	fp4	95.7%
GLM 5.3	67.5%	$1.4	$4.4	+434%	37	1M	944k	fp8	100%
MiniMax M3.1 Flash	66.2%	$0.15	$0.6	+5%	11	1M	524k	fp8	100%
Qwen3.8 27B	63.8%	$0.24	$2.2	+329%	21	262k	236k	fp8	100%
Qwen3 Coder Next	62.5%	$0.12	$0.8	Only host	1	262k	236k	bf16	100%
Llama 4 Maverick	59.0%	$0.35	$1	+69%	3	524k	33k	fp8	100%
gpt-oss-120b	58.8%	$0.1	$0.75	+338%	23	131k	118k	fp4	100%
MiniMax M3	57.5%	$0.3	$1.2	+35%	12	1M	524k	fp8	92.0%
gpt-oss-20b	51.2%	$0.03	$0.15	+67%	10	131k	118k	fp4	73.3%
Llama 3.3 70B Instruct	42.5%	$0.22	$0.5	+87%	9	131k	16k	fp8	100%
Qwen3.6 35B A3B	37.5%	$0.1	$0.95	+47%	10	262k	236k	fp8	100%
Qwen3.5 397B A17B	32.5%	$0.5	$3.6	+45%	10	262k	236k	fp8	100%
Gemma 4 31B	30.0%	$0.15	$0.4	+33%	13	262k	236k	fp8	100%
Gemma 4 26B A4B	15.0%	$0.13	$0.4	+128%	15	262k	236k	bf16	100%

All API hosts →

Parasail: frequently asked questions

Which AI models does Parasail serve?: Of the models we benchmark, Parasail serves 16 through OpenRouter: DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro 0813, GLM 5.3 Flash, GLM 5.3, MiniMax M3.1 Flash, Qwen3.8 27B, Qwen3 Coder Next, Llama 4 Maverick, gpt-oss-120b, MiniMax M3, gpt-oss-20b, Llama 3.3 70B Instruct, Qwen3.6 35B A3B, Qwen3.5 397B A17B, Gemma 4 31B, Gemma 4 26B A4B.
What is the most accurate model on Parasail?: DeepSeek V4.1 Flash 1017 by DeepSeek, with a verification score of 73.8% (59 of 80 questions correct) in our tests.
Is Parasail the cheapest host?: Parasail has the lowest list price for 0 of the 15 models it serves that other hosts also serve. Its median markup over the cheapest host is +87%.
How reliable is Parasail?: Averaged over the models it serves, Parasail reported 97.6% 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 V4.1 Flash 1017

73.8%

$0.3

$1.2

+364%

944k

fp8

100%

DeepSeek V4 Pro 0813

71.2%

$1.32

$3.96

+843%

944k

fp8

100%

GLM 5.3 Flash

67.5%

$0.15

$0.5

+406%

944k

fp4

95.7%

GLM 5.3

67.5%

$1.4

$4.4

+434%

944k

fp8

100%

MiniMax M3.1 Flash

66.2%

$0.15

$0.6

+5%

524k

fp8

100%

Qwen3.8 27B

63.8%

$0.24

$2.2

+329%

262k

236k

fp8

100%

Qwen3 Coder Next

62.5%

$0.12

$0.8

Only host

262k

236k

bf16

100%

Llama 4 Maverick

59.0%

$0.35

+69%

524k

33k

fp8

100%

gpt-oss-120b

58.8%

$0.1

$0.75

+338%

131k

118k

fp4

100%

MiniMax M3

57.5%

$0.3

$1.2

+35%

524k

fp8

92.0%

gpt-oss-20b

51.2%

$0.03

$0.15

+67%

131k

118k

fp4

73.3%

Llama 3.3 70B Instruct

42.5%

$0.22

$0.5

+87%

131k

16k

fp8

100%

Qwen3.6 35B A3B

37.5%

$0.1

$0.95

+47%

262k

236k

fp8

100%

Qwen3.5 397B A17B

32.5%

$0.5

$3.6

+45%

262k

236k

fp8

100%

Gemma 4 31B

30.0%

$0.15

$0.4

+33%

262k

236k

fp8

100%

Gemma 4 26B A4B

15.0%

$0.13

$0.4

+128%

262k

236k

bf16

100%

Parasail: frequently asked questions

Which AI models does Parasail serve?

Of the models we benchmark, Parasail serves 16 through OpenRouter: DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro 0813, GLM 5.3 Flash, GLM 5.3, MiniMax M3.1 Flash, Qwen3.8 27B, Qwen3 Coder Next, Llama 4 Maverick, gpt-oss-120b, MiniMax M3, gpt-oss-20b, Llama 3.3 70B Instruct, Qwen3.6 35B A3B, Qwen3.5 397B A17B, Gemma 4 31B, Gemma 4 26B A4B.

What is the most accurate model on Parasail?

DeepSeek V4.1 Flash 1017 by DeepSeek, with a verification score of 73.8% (59 of 80 questions correct) in our tests.

Is Parasail the cheapest host?

Parasail has the lowest list price for 0 of the 15 models it serves that other hosts also serve. Its median markup over the cheapest host is +87%.

How reliable is Parasail?

Averaged over the models it serves, Parasail reported 97.6% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.