MODEL CATALOG

Models & reference pricing

Browse the imported model and price snapshot. OpenAI is available on kineticRouter; Anthropic and Grok native routes are planned and planned.

7 models

OpenAI: GPT-5.3 Codex

openai/gpt-5.3-codex

0.15x ref

GPT-5.3 Codex 是 OpenAI 面向代理式编码的高能力模型,结合 GPT-5.2 Codex 的软件工程能力和更广泛的推理、专业知识能力,适合多语言编码、终端任务和真实计算机使用场景。

visionfunctionreasoningsearch
Snapshot input$0.2625/M
Snapshot output$2.1/M
Upstream context400K
View model

OpenAI: GPT-5.4

openai/gpt-5.4

0.15x ref

GPT-5.4 is a flagship GPT model for complex reasoning, coding, multimodal analysis, web research, and long-running agents. It provides a 272K-token context window and up to 128K output tokens. Its current kineticRouter catalog capabilities include vision, function calling, reasoning, web search, prompt caching, code interpreter. Use model ID openai/gpt-5.4 through kineticRouter's OpenAI-compatible API.

visionfunctionreasoningsearch
Snapshot input$0.375/M
Snapshot output$2.25/M
Upstream context1.05M
View model

OpenAI: GPT-5.4 Mini

openai/gpt-5.4-mini

0.15x ref

GPT-5.4 Mini is a balanced GPT-5.4 tier for everyday coding, reasoning, multimodal tasks, and cost-sensitive agent workflows. It provides a 272K-token context window and up to 128K output tokens. Its current kineticRouter catalog capabilities include vision, function calling, reasoning, web search, prompt caching, code interpreter. Use model ID openai/gpt-5.4-mini through kineticRouter's OpenAI-compatible API.

visionfunctionreasoningsearch
Snapshot input$0.1125/M
Snapshot output$0.675/M
Upstream context400K
View model

OpenAI: GPT-5.5

openai/gpt-5.5

0.15x ref

GPT-5.5 is an advanced GPT model for professional reasoning, coding, multimodal analysis, and agent workflows. It provides a 272K-token context window and up to 128K output tokens. Its current kineticRouter catalog capabilities include vision, function calling, reasoning, web search, prompt caching, code interpreter. Use model ID openai/gpt-5.5 through kineticRouter's OpenAI-compatible API.

visionfunctionreasoningsearch
Snapshot input$0.75/M
Snapshot output$4.5/M
Upstream context1.05M
View model

OpenAI: GPT-5.6 Luna

openai/gpt-5.6-luna

0.3x ref

GPT-5.6 Luna is the fast, cost-efficient GPT-5.6 tier for high-volume, latency-sensitive chat, classification, and lightweight agents. It provides a 372K-token context window and up to 128K output tokens. Its current kineticRouter catalog capabilities include vision, function calling, reasoning, web search, prompt caching. Use model ID openai/gpt-5.6-luna through kineticRouter's OpenAI-compatible and Anthropic-compatible APIs.

visionfunctionreasoningcache
Snapshot input$0.06/M
Snapshot output$0.36/M
Upstream context1.05M
View model

OpenAI: GPT-5.6 Sol

openai/gpt-5.6-sol

0.15x ref

GPT-5.6 Sol is the flagship GPT-5.6 tier for complex reasoning, coding, command-line tasks, and long-horizon agent workflows. It provides a 372K-token context window and up to 128K output tokens. Its current kineticRouter catalog capabilities include vision, function calling, reasoning, web search, prompt caching. Use model ID openai/gpt-5.6-sol through kineticRouter's OpenAI-compatible and Anthropic-compatible APIs.

visionfunctionreasoningcache
Snapshot input$0.6/M
Snapshot output$3/M
Upstream context1.05M
View model

OpenAI: GPT-5.6 Terra

openai/gpt-5.6-terra

0.15x ref

GPT-5.6 Terra is the balanced GPT-5.6 tier for everyday coding, reasoning, and agent workflows that need a strong capability-to-cost tradeoff. It provides a 372K-token context window and up to 128K output tokens. Its current kineticRouter catalog capabilities include vision, function calling, reasoning, web search, prompt caching. Use model ID openai/gpt-5.6-terra through kineticRouter's OpenAI-compatible and Anthropic-compatible APIs.

visionfunctionreasoningcache
Snapshot input$0.3/M
Snapshot output$1.8/M
Upstream context1.05M
View model