Models Every AI model available through LLMAI, with API slugs, context sizes, and token pricing.
Use the slug from the table below as the model field in your request. All models are available on every account — no model-specific unlocking or tier requirements.
Model API Slug Context Window Input / 1M tokens Output / 1M tokens Claude Opus 4.7 claude-opus-4.71M $1.750 $8.750 Claude Opus 4.7 Thinking claude-opus-4.7-thinking1M $1.750 $8.750 Claude Sonnet 4.6 claude-sonnet-4.61M $1.050 $5.250 Claude Sonnet 4.6 Thinking claude-sonnet-4.6-thinking1M $1.050 $5.250 Claude Opus 4.6 claude-opus-4.61M $1.750 $8.750 Claude Opus 4.6 Thinking claude-opus-4.6-thinking1M $1.750 $8.750 Claude Haiku 4.5 claude-haiku-4.5200K $0.350 $1.750
Model API Slug Context Window Input / 1M tokens Output / 1M tokens GPT-5.5 gpt-5.51M $1.750 $10.500 GPT-5.4 gpt-5.41M $0.875 $5.250 GPT-5.3 Codex gpt-5.3-codex400K $0.613 $4.900 GPT-5.2 gpt-5.2128K $0.613 $4.900
Model API Slug Type Price GPT Image 2 gpt-image-2Image generation $0.01275 / image
GPT Image 2 is billed per generated image rather than per token. Send requests to the standard /v1/images/generations endpoint with "model": "gpt-image-2".
Model API Slug Context Window Input / 1M tokens Output / 1M tokens Gemini 3.1 Pro gemini-3.1-pro1M $1.250 $4.800 Gemma 4 gemma-4256K $0.046 $0.130
Model API Slug Context Window Input / 1M tokens Output / 1M tokens GLM 5 Turbo glm-5-turbo200K $0.420 $1.400 GLM 5 glm-5200K $0.350 $1.120 GLM 5.1 glm-5.1200K $0.550 $1.300
Model API Slug Context Window Input / 1M tokens Output / 1M tokens MiniMax M3 ✦ NEW minimax-m31M $0.420 $1.680 MiniMax M2.7 minimax-m2.7200K $0.200 $0.850
Model API Slug Context Window Input / 1M tokens Output / 1M tokens Kimi K2.6 kimi-k2.6256K $0.620 $2.600 Kimi K2.5 kimi-k2.5128K $0.210 $1.050
Model API Slug Context Window Input / 1M tokens Output / 1M tokens MiMo V2.5 Pro mimo-v2.5-pro1M $0.650 $1.950 MiMo V2.5 mimo-v2.51M $0.260 $1.300
Model API Slug Context Window Input / 1M tokens Output / 1M tokens Qwen 3.6 Plus qwen3.6-plus128K $0.120 $0.680 Qwen 3.5 Plus qwen3.5-plus128K $0.140 $0.810
Model API Slug Context Window Input / 1M tokens Output / 1M tokens DeepSeek V4 Pro deepseek-v4-pro128K $0.610 $1.220 DeepSeek V4 Flash deepseek-v4-flash128K $0.050 $0.100 DeepSeek V3.2 deepseek-v3.2128K $0.088 $0.132
Every model slug that contains a dot is also available in a dash notation variant where dots are replaced by dashes. Both formats resolve to the same model:
Dot notation (default) Dash notation (alias) claude-opus-4.7claude-opus-4-7gpt-5.5gpt-5-5glm-5.1glm-5-1deepseek-v3.2deepseek-v3-2qwen3.6-plusqwen3-6-plus
Use whichever format your tool supports. Some clients — notably Cursor IDE — reject model names containing dots. In those cases, use the dash notation instead.
Set the model field to the exact slug shown above:
curl https://api.llmai.dev/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "glm-5.1", "messages": [{"role": "user", "content": "Review this Python snippet for bugs."}] }' Slugs are case-sensitive . GPT-5.4 and gpt-5.4 are not equivalent — use the lowercase slug exactly as shown.
curl https://api.llmai.dev/v1/models \ -H "Authorization: Bearer YOUR_API_KEY" Returns a standard ListModelsResponse object containing all model IDs currently available on the platform.
All rates are quoted per one million tokens .
Actual charges scale proportionally — a request using 2,000 tokens costs (2,000 ÷ 1,000,000) × rate.
Input and output tokens are priced independently.
Context window is the combined maximum for prompt and completion tokens in a single call.
Model availability is subject to change; check the Models catalog for the current live list.