The full model stack, one key
From frontier GPT and Claude to Gemini, DeepSeek, GLM, Kimi, Qwen and more — every model below is live and reachable from a single OpenAI-compatible account and key.
GPT
OpenAI-compatible GPT models for demanding coding, research, and image generation.
GPT-5.5
gpt-5.5
Frontier GPT model for demanding coding, research, and long problem-solving.
GPT-5.4
gpt-5.4
Strong all-around GPT model with wide headroom for heavy coding sessions.
GPT-5.4 Mini
gpt-5.4-mini
Smaller, faster GPT model for quick iterations and lighter tasks.
GPT Image 2
gpt-image-2
Image generation for OpenAI-compatible image routes, editors, and automations.
Claude
Anthropic Claude models for writing, analysis, and long structured work.
Claude Opus 4.8
claude-opus-4-8
Top-tier Claude model for demanding writing, analysis, and long structured tasks.
Claude Opus 4.7
claude-opus-4-7
High-capability Claude Opus model for complex reasoning and long-form work.
Claude Opus 4.6
claude-opus-4-6
Capable Claude Opus model for deep analysis and structured generation.
Claude Sonnet 4.6
claude-sonnet-4-6
Balanced Claude model for fast, high-quality everyday work.
Claude Haiku 4.5
claude-haiku-4-5
Fast, lightweight Claude model for quick responses at high volume.
Gemini
Google-family models tuned for fast multimodal and agentic workflows.
Gemini 2.5 Pro
gemini-2.5-pro
Flagship Gemini model for multimodal coding and reasoning.
Gemini 2.5 Flash
gemini-2.5-flash
Balanced Gemini model for fast multimodal and agentic work.
Gemini 2.5 Flash Lite
gemini-2.5-flash-lite
Lowest-cost Gemini model for lightweight loops and tooling.
Gemini 3 Pro Preview
gemini-3-pro-preview
Preview Gemini model for heavier multimodal and coding sessions.
Gemini 3.1 Pro Preview
gemini-3.1-pro-preview
Newer Gemini Pro preview with stronger agentic coding.
Gemini 3 Flash Preview
gemini-3-flash-preview
Faster Gemini preview for responsive, high-volume tasks.
Gemini 3.5 Flash
gemini-3.5-flash
Fast Gemini 3.5 lane for low-latency multimodal requests.
DeepSeek
Large-context DeepSeek models for heavier reasoning at low cost.
DeepSeek V4 Flash
deepseek-v4-flash
Lowest-cost, large-context DeepSeek model for fast iterations.
DeepSeek V4 Pro
deepseek-v4-pro
Flagship large-context DeepSeek model for heavier reasoning.
DeepSeek V4 Pro Lightning
deepseek-v4-pro-lightning
High-speed DeepSeek V4 Pro variant for heavy agent loops.
DeepSeek V3.2
deepseek-v3.2
Balanced DeepSeek reasoning model with a wide context window.
GLM
GLM models with wide context windows for long agent sessions.
GLM 5.2
glm-5.2
Latest GLM flagship with a million-token context for long sessions.
GLM 5.1
glm-5.1
Strong GLM reasoning model for complex work with broad context.
GLM 5
glm-5
Strong GLM model for general coding and agent workflows.
GLM 4.7
glm-4.7
Balanced GLM model with solid context at lower cost.
GLM 4.7 Flash
glm-4.7-flash
Fast, low-cost GLM model for high-volume agent tasks.
Kimi
Kimi models for large-context multimodal coding and research.
Kimi K2.7 Code
kimi-k2.7-code
Kimi coding specialist with a very large context window.
Kimi K2.6
kimi-k2.6
Large-context Kimi model for heavier research and coding.
Kimi K2.5
kimi-k2.5
Balanced Kimi model for general-purpose agent work.
Kimi K2.5 Lightning
kimi-k2.5-lightning
Premium Kimi lightning variant for fast responses.
Qwen & More
Qwen and additional specialist models for broad, lower-cost work.
Mimo V2.5 Pro
mimo-v2.5-pro
Large-context reasoning model for heavier coding and planning.
Gemma 4 31B IT
gemma-4-31b-it
Fast, lightweight model for everyday coding and assistant work.
MiniMax M2.5
minimax-m2.5
Low-cost reasoning model for long prompts and agent turns.
Qwen 3.6 27B
qwen3.6-27b
Fast multimodal Qwen model for broad coding and research.
Qwen 3.5 397B A17B
qwen3.5-397b-a17b
High-capacity Qwen model for larger multimodal workloads.
Qwen 3.5 9B
qwen3.5-9b
Small, fast Qwen model for low-cost iteration.