MODEL CATALOG

Models & pricing

Explore 38 models across 8 providers. Discounts vary by provider.

38 models

OpenAI: GPT-6 Astra

openai/gpt-6-astra

-80%

Flagship reasoning for demanding coding, research, and professional work.

visioncache
Input / 1M tokens$2/M$10/M
Output / 1M tokens$10/M$50/M
Upstream context1.05M
View model

OpenAI: GPT-6.1 Sol

openai/gpt-6.1-sol

-80%

Complex coding and professional work with balanced intelligence and cost.

visioncache
Input / 1M tokens$0.4/M$2/M
Output / 1M tokens$2/M$10/M
Upstream context1.05M
View model

OpenAI: GPT-6 Luna

openai/gpt-6-luna

-80%

Efficient reasoning for focused tasks and high-volume applications.

visioncache
Input / 1M tokens$0.02/M$0.1/M
Output / 1M tokens$0.1/M$0.5/M
Upstream context1.05M
View model

Anthropic: Claude Sonnet 5.5

anthropic/claude-sonnet-5-5

-85%

Fast reasoning and coding for everyday development and document workflows.

visioncache
Input / 1M tokens$0.3/M$2/M
Output / 1M tokens$1.5/M$10/M
Upstream context1M
View model

Anthropic: Claude Opus 5.5

anthropic/claude-opus-5-5

-85%

Advanced reasoning for long-running coding and complex knowledge work.

visioncache
Input / 1M tokens$0.6/M$4/M
Output / 1M tokens$3/M$20/M
Upstream context1M
View model

DeepSeek: DeepSeek V4.1 Flash

deepseek/deepseek-flash

-80%

Efficient reasoning with vision, coding, and a large context window.

visioncache
Input / 1M tokens$0.06/M$0.3/M
Output / 1M tokens$0.24/M$1.2/M
Upstream context1M
View model

DeepSeek: DeepSeek V4 Pro

deepseek/deepseek-v4-pro

-80%

Large-context reasoning and coding with separate peak and off-peak pricing.

cache
Input / 1M tokens$0.264/M$1.32/M
Output / 1M tokens$0.792/M$3.96/M
Upstream context1M
View model

Zhipu: GLM-5.3

zhipu/glm-5.3

-80%

Reasoning and coding from Zhipu, available through the shared /v1 API.

cache
Input / 1M tokens$0.28/M$1.4/M
Output / 1M tokens$0.88/M$4.4/M
Upstream context—
View model

Zhipu: GLM-5.3-Flash

zhipu/glm-5.3-flash

-80%

Fast multimodal coding and knowledge work with a one-million-token context.

visioncache
Input / 1M tokens$0.03/M$0.15/M
Output / 1M tokens$0.1/M$0.5/M
Upstream context1M
View model

Moonshot: Kimi K3.1 Pro

moonshot/kimi-k3.1-pro

-80%

Long-horizon coding and knowledge work with native visual understanding and a one-million-token context.

visioncache
Input / 1M tokens$0.4/M$2/M
Output / 1M tokens$2/M$10/M
Upstream context1.05M
View model

Moonshot: Kimi K3

moonshot/kimi-k3

-80%

Long-horizon coding and knowledge work with a one-million-token context.

visioncache
Input / 1M tokens$0.6/M$3/M
Output / 1M tokens$3/M$15/M
Upstream context1.05M
View model

Moonshot: Kimi K2.7 Code

moonshot/kimi-k2.7-code

Deprecated

A coding-focused Kimi model for software development workflows.

visioncache
Input / 1M tokens$0.19/M$0.95/M
Output / 1M tokens$0.8/M$4/M
Upstream context262K
View model

Grok: Grok 4.7

grok/grok-4.7

-90%

Reasoning, coding, and knowledge work with text and image input.

vision
Input / 1M tokens$0.2/M$2/M
Output / 1M tokens$0.6/M$6/M
Upstream context500K
View model

MiniMax: MiniMax M3

minimax/minimax-m3

-90%

Coding and multimodal understanding for large development projects.

visioncache
Input / 1M tokens$0.03/M$0.3/M
Output / 1M tokens$0.12/M$1.2/M
Upstream context1M
View model

Gemini: Gemini 3.8 Flash

gemini/gemini-3.8-flash

-50%

Gemini 3.8 Flash through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.8 Flash High

gemini/gemini-3.8-flash-high

-50%

Gemini 3.8 Flash High through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.8 Flash Low

gemini/gemini-3.8-flash-low

-50%

Gemini 3.8 Flash Low through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.8 Flash Medium

gemini/gemini-3.8-flash-medium

-50%

Gemini 3.8 Flash Medium through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.8 Flash Tiered

gemini/gemini-3.8-flash-tiered

-50%

Gemini 3.8 Flash Tiered through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.7 Flash High

gemini/gemini-3.7-flash-high

-50%

Gemini 3.7 Flash High through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.7 Flash Low

gemini/gemini-3.7-flash-low

-50%

Gemini 3.7 Flash Low through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.7 Flash Medium

gemini/gemini-3.7-flash-medium

-50%

Gemini 3.7 Flash Medium through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.6 Flash High

gemini/gemini-3.6-flash-high

-50%

Gemini 3.6 Flash High through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.6 Flash Low

gemini/gemini-3.6-flash-low

-50%

Gemini 3.6 Flash Low through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.6 Flash Medium

gemini/gemini-3.6-flash-medium

-50%

Gemini 3.6 Flash Medium through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.375/M$0.75/M
Output / 1M tokens$1.875/M$3.75/M
Upstream context1.05M
View model

Gemini: Gemini 3.5 Flash Extra Low

gemini/gemini-3.5-flash-extra-low

-50%

Gemini 3.5 Flash Extra Low through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.75/M$1.5/M
Output / 1M tokens$4.5/M$9/M
Upstream context1.05M
View model

Gemini: Gemini 3.5 Flash Low

gemini/gemini-3.5-flash-low

-50%

Gemini 3.5 Flash Low through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.75/M$1.5/M
Output / 1M tokens$4.5/M$9/M
Upstream context1.05M
View model

Gemini: Gemini 3.5 Flash Lite

gemini/gemini-3.5-flash-lite

-50%

Gemini 3.5 Flash Lite through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.15/M$0.3/M
Output / 1M tokens$1.25/M$2.5/M
Upstream context1.05M
View model

Gemini: Gemini 3.1 Flash Image

gemini/gemini-3.1-flash-image

-50%

Gemini 3.1 Flash Image through the OpenAI-compatible kineticRouter API.

visionimage
Input / 1M tokens$0.25/M$0.5/M
Output / 1M tokens$1.5/M$3/M
Upstream context131K
View model

Gemini: Gemini 3.1 Flash Lite

gemini/gemini-3.1-flash-lite

-50%

Gemini 3.1 Flash Lite through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.125/M$0.25/M
Output / 1M tokens$0.75/M$1.5/M
Upstream context1.05M
View model

Gemini: Gemini 3.1 Pro High

gemini/gemini-3.1-pro-high

-50%

Gemini 3.1 Pro High through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$1/M$2/M
Output / 1M tokens$6/M$12/M
Upstream context1.05M
View model

Gemini: Gemini 3.1 Pro Low

gemini/gemini-3.1-pro-low

-50%

Gemini 3.1 Pro Low through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$1/M$2/M
Output / 1M tokens$6/M$12/M
Upstream context1.05M
View model

Gemini: Gemini 3 Flash

gemini/gemini-3-flash

-50%

Gemini 3 Flash through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.25/M$0.5/M
Output / 1M tokens$1.5/M$3/M
Upstream context1.05M
View model

Gemini: Gemini 3 Flash Agent

gemini/gemini-3-flash-agent

-50%

Gemini 3 Flash Agent through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.25/M$0.5/M
Output / 1M tokens$1.5/M$3/M
Upstream context1.05M
View model

Gemini: Gemini 2.5 Flash

gemini/gemini-2.5-flash

-50%

Gemini 2.5 Flash through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.15/M$0.3/M
Output / 1M tokens$1.25/M$2.5/M
Upstream context1.05M
View model

Gemini: Gemini 2.5 Flash Thinking

gemini/gemini-2.5-flash-thinking

-50%

Gemini 2.5 Flash Thinking through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.15/M$0.3/M
Output / 1M tokens$1.25/M$2.5/M
Upstream context1.05M
View model

Gemini: Gemini 2.5 Flash Lite

gemini/gemini-2.5-flash-lite

-50%

Gemini 2.5 Flash Lite through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.05/M$0.1/M
Output / 1M tokens$0.2/M$0.4/M
Upstream context1.05M
View model

Gemini: Gemini 2.5 Pro

gemini/gemini-2.5-pro

-50%

Gemini 2.5 Pro through the OpenAI-compatible kineticRouter API.

visioncache
Input / 1M tokens$0.625/M$1.25/M
Output / 1M tokens$5/M$10/M
Upstream context1.05M
View model