Catalog

Every model. One rate card.

One endpoint, one price list, charged at the exact token count on Robinhood Chain.

glm-5.3-prime

Zhipu AI · 1M context

new
Input / 1M$2.80
Output / 1M$8.80

qwen3.8-max-prime

Qwen · 1M context

new
Input / 1M$4.00
Output / 1M$12.00

gpt-6-luna-pro

OpenAI · 1.1M context

new
Input / 1M$0.100
Output / 1M$0.500

gpt-6-luna

OpenAI · 1.1M context

new
Input / 1M$0.100
Output / 1M$0.500

gpt-6-sol-pro

OpenAI · 1.1M context

new
Input / 1M$2.00
Output / 1M$10.00

grok-4.7

xAI · 500K context

new
Input / 1M$1.60
Output / 1M$4.80

qwen3.8-omni-flash

Qwen · 1M context

new
Input / 1M$0.150
Output / 1M$0.470

glm-5.3-flashx

Zhipu AI · 1M context

new
Input / 1M$0.370
Output / 1M$1.25

deepseek-v4.1-flash

DeepSeek · 1M context

new
Input / 1M$0.150
Output / 1M$0.600

qwen3.8-max-0902

Qwen · 1M context

new
Input / 1M$2.00
Output / 1M$6.00

gemini-3.8-flash

Google · 1M context

new
Input / 1M$0.750
Output / 1M$3.75

glm-5.3-flash

Zhipu AI · 1.3M context

vision
Input / 1M$0.045
Output / 1M$0.140

deepseek-v4-flash-vision-exp

DeepSeek · 1M context

vision
Input / 1M$0.220
Output / 1M$0.660

gemini-3.7-flash

Google · 1M context

vision
Input / 1M$0.750
Output / 1M$3.75

deepseek-v4-pro-0813

DeepSeek · 1M context

Input / 1M$0.346
Output / 1M$1.04

grok-4.6

xAI · 500K context

vision
Input / 1M$2.00
Output / 1M$6.00

gemini-3.6-flash

Google · 1M context

vision
Input / 1M$0.750
Output / 1M$3.75

kimi-k3

Moonshot AI · 1M context

vision
Input / 1M$3.00
Output / 1M$15.00

grok-4.5

xAI · 500K context

vision
Input / 1M$2.00
Output / 1M$6.00

kimi-k2.7-code

Moonshot AI · 262K context

vision
Input / 1M$0.656
Output / 1M$3.30

minimax-m3

MiniMax · 1M context

vision
Input / 1M$0.300
Output / 1M$1.20

mistral-medium-3-5

Mistral · 262K context

vision
Input / 1M$1.50
Output / 1M$7.50

kimi-k2.6

Moonshot AI · 262K context

vision
Input / 1M$0.950
Output / 1M$4.00

minimax-m2.7

MiniMax · 205K context

Input / 1M$0.300
Output / 1M$1.20

mistral-small-2603

Mistral · 262K context

vision
Input / 1M$0.150
Output / 1M$0.600

minimax-m2.5

MiniMax · 205K context

Input / 1M$0.270
Output / 1M$1.08

devstral-2512

Mistral · 262K context

Input / 1M$0.400
Output / 1M$2.00

llama-4-maverick

Meta · 1M context

vision
Input / 1M$0.188
Output / 1M$0.652

llama-4-scout

Meta · 1.3M context

vision
Input / 1M$0.100
Output / 1M$0.300

llama-3.3-70b-instruct

Meta · 131K context

Input / 1M$0.100
Output / 1M$0.320
How pricing works

You pay for tokens. That is the whole bill.

With a prepaid key, each call is charged its exact token count at the posted rate. With pay-per-call you sign a ceiling (the full input plus max_tokens of output) and the unused part returns to your wallet. Repeated deterministic requests are answered from cache at half the charge.

Rates shown are indicative public list prices while the lane is in preview. The OpenAI-shaped listing will be served at GET /v1/models; see the models reference.