AI Gateway · 352

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.

openai

gpt-oss-120b

Available Text chat

Configured context limit: 131,072 tokens

Input10,393

Output47,749

Toman per million tokens

openai

gpt-oss-120b-Turbo

Available Text chat

Configured context limit: 131,072 tokens

Input42,132

Output168,525

Toman per million tokens

openai

gpt-oss-120b-Ultra

Available Text chat

Configured context limit: 131,072 tokens

Input56,175

Output266,832

Toman per million tokens

openai

gpt-oss-20b

Available Text chat

Configured context limit: 131,072 tokens

Input8,427

Output39,323

Toman per million tokens

ibm-granite

granite-4.2-30b

Available Text chat

Configured context limit: 131,072 tokens

Input44,940

Output182,569

Toman per million tokens

ibm-granite

granite-4.2-3b

Available Text chat

Configured context limit: 131,072 tokens

Input8,427

Output33,705

Toman per million tokens

ibm-granite

granite-4.2-8b

Available Text chat

Configured context limit: 131,072 tokens

Input16,853

Output70,219

Toman per million tokens

XAI

grok-4

Preparing Text chat

Configured context limit: 4,096 tokens

Input842,625

Output4,213,125

Toman per million tokens

XAI

grok-4-0709

Available Text chat

Configured context limit: 4,096 tokens

Input842,625

Output4,213,125

Toman per million tokens

XAI

grok-4.3

Preparing Text chat

Configured context limit: 4,096 tokens

Input351,094

Output702,188

Toman per million tokens

XAI

grok-4.5

Preparing Text chat

Configured context limit: 4,096 tokens

Input561,750

Output1,685,250

Toman per million tokens

XAI

grok-4.6

Preparing Text chat

Configured context limit: 4,096 tokens

Input561,750

Output1,685,250

Toman per million tokens

NousResearch

Hermes-3-Llama-3.1-405B

Available Text chat

Configured context limit: 131,072 tokens

Input280,875

Output280,875

Toman per million tokens

NousResearch

Hermes-3-Llama-3.1-70B

Available Text chat

Configured context limit: 131,072 tokens

Input196,613

Output196,613

Toman per million tokens

tencent

Hy3

Discontinued Text chat

Configured context limit: 262,144 tokens

Sale prices will appear after provider configuration is complete.

tencent

Hy4-preview

Available Text chat

Configured context limit: 1,048,576 tokens

Input234,250

Output702,469

Toman per million tokens

thinkingmachines

Inkling

Available Text chat

Configured context limit: 524,288 tokens

Input266,832

Output1,137,544

Toman per million tokens

thinkingmachines

Inkling-Small

Available Text chat

Configured context limit: 524,288 tokens

Input126,394

Output337,050

Toman per million tokens

Unknown

k3

Preparing Text chat

Configured context limit: 4,096 tokens

Sale prices will appear after provider configuration is complete.

Unknown

kimi-2.7

Preparing Text chat

Configured context limit: 4,096 tokens

Sale prices will appear after provider configuration is complete.

Unknown

kimi-3

Available Text chat

Configured context limit: 4,096 tokens

Input842,625

Output4,213,125

Toman per million tokens

Unknown

kimi-for-coding

Preparing Text chat

Configured context limit: 4,096 tokens

Sale prices will appear after provider configuration is complete.

moonshotai

Kimi-K2-Instruct

Discontinued Text chat

Configured context limit: 131,072 tokens

Sale prices will appear after provider configuration is complete.

moonshotai

Kimi-K2-Instruct-0905

Discontinued Text chat

Configured context limit: 131,072 tokens

Sale prices will appear after provider configuration is complete.