AI Gateway · 386

Compare models

Compare AI models, service types, context windows and availability in the ServerNet gateway. Find a model for your application and budget.

Only available models are exposed by the API. Availability requires a configured provider, valid prices and a supported execution path.
zai-org

GLM-5.3

PreparingText chat

Context window: 1,048,576 tokens

Input252,646
Output1,122,870
Toman per million tokens
zai-org

GLM-5.3-Flash

AvailableText chat

Context window: 1,048,576 tokens

Input42,108
Output140,359
Toman per million tokens
openai

gpt-oss-120b

AvailableText chat

Context window: 131,072 tokens

Input10,387
Output47,722
Toman per million tokens
openai

gpt-oss-120b-Turbo

AvailableText chat

Context window: 131,072 tokens

Input42,108
Output168,431
Toman per million tokens
openai

gpt-oss-120b-Ultra

AvailableText chat

Context window: 131,072 tokens

Input56,144
Output266,682
Toman per million tokens
openai

gpt-oss-20b

AvailableText chat

Context window: 131,072 tokens

Input8,422
Output39,301
Toman per million tokens
ibm-granite

granite-4.2-30b

AvailableText chat

Context window: 131,072 tokens

Input44,915
Output182,467
Toman per million tokens
ibm-granite

granite-4.2-3b

AvailableText chat

Context window: 131,072 tokens

Input8,422
Output33,687
Toman per million tokens
ibm-granite

granite-4.2-8b

AvailableText chat

Context window: 131,072 tokens

Input16,844
Output70,180
Toman per million tokens
thenlper

gte-base

PreparingEmbeddings

Context window: 512 tokens

Sale prices will appear after provider configuration is complete.

thenlper

gte-large

PreparingEmbeddings

Context window: 512 tokens

Sale prices will appear after provider configuration is complete.

NousResearch

Hermes-3-Llama-3.1-405B

AvailableText chat

Context window: 131,072 tokens

Input280,718
Output280,718
Toman per million tokens
NousResearch

Hermes-3-Llama-3.1-70B

AvailableText chat

Context window: 131,072 tokens

Input196,503
Output196,503
Toman per million tokens
bosonai

HiggsAudioV2.5

PreparingAudio

Context window: 4,096 tokens

Sale prices will appear after provider configuration is complete.

tencent

Hy3

DiscontinuedText chat

Context window: 262,144 tokens

Sale prices will appear after provider configuration is complete.

tencent

Hy4-preview

AvailableText chat

Context window: 1,048,576 tokens

Input234,119
Output702,075
Toman per million tokens
thinkingmachines

Inkling

AvailableText chat

Context window: 524,288 tokens

Input266,682
Output1,136,906
Toman per million tokens
thinkingmachines

Inkling-Small

AvailableText chat

Context window: 524,288 tokens

Input126,323
Output336,861
Toman per million tokens
inworld-ai

inworld-tts-1.5-max

DiscontinuedAudio

Context window: 4,096 tokens

Sale prices will appear after provider configuration is complete.

inworld-ai

inworld-tts-1.5-mini

DiscontinuedAudio

Context window: 4,096 tokens

Sale prices will appear after provider configuration is complete.

deepseek-ai

Janus-Pro-1B

DiscontinuedImage

Context window: 4,096 tokens

Sale prices will appear after provider configuration is complete.

deepseek-ai

Janus-Pro-7B

DiscontinuedImage

Context window: 4,096 tokens

Sale prices will appear after provider configuration is complete.

run-diffusion

Juggernaut-Flux

DiscontinuedImage

Context window: 4,096 tokens

Sale prices will appear after provider configuration is complete.

run-diffusion

Juggernaut-Lightning-Flux

DiscontinuedImage

Context window: 4,096 tokens

Sale prices will appear after provider configuration is complete.

10% tax is added to usage charges. Prices are frozen at request admission and settlement uses reported consumption.