Models
Current model availability and pricing from the live public catalog.
Model slugs in examples are illustrative. Confirm current availability in the live catalog and your account's /v1/models before use.
Model Reference
The table below is fetched from the live public catalog (GET /api/public/models). Only globally active models with a configured eligible upstream route appear. Your organization's admin may restrict access further; check /v1/models with your API key for the models available to your account. A price in Admin → Model Pricing does not enable a model or provision an upstream route.
| Model | API Slug | Provider | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|---|
| Qwen 3.5 Plus | qwen3.5-plus | alibaba | $0.140 | $0.810 |
| Claude Opus 5 | claude-opus-5 | anthropic | $2.625 (cached $0.2625) | $10.500 |
| Claude Sonnet 4.6 | claude-sonnet-4.6 | anthropic | $1.050 (cached $0.105) | $5.250 |
| Claude Opus 4.6 | claude-opus-4.6 | anthropic | $1.575 (cached $0.1575) | $7.875 |
| Claude Opus 4.7 | claude-opus-4.7 | anthropic | $2.625 (cached $0.2625) | $10.500 |
| Claude Opus 4.8 | claude-opus-4.8 | anthropic | $2.625 (cached $0.2625) | $10.500 |
| Claude Sonnet 5 | claude-sonnet-5 | anthropic | $1.050 | $5.250 |
| DeepSeek V4 Pro | deepseek-v4-pro | deepseek | $0.2175 (cached $0.0218) | $0.435 |
| Gemini 3.1 Flash Lite | gemini-3.1-flash-lite | $0.125 (cached $0.0125) | $0.750 | |
| Gemini 3 Flash (Preview) | gemini-3-flash-preview | $0.250 (cached $0.025) | $1.500 | |
| Gemini 2.5 Pro | gemini-2.5-pro | $0.625 (cached $0.0625) | $5.000 | |
| Gemma 4 | gemma-4 | $0.046 | $0.130 | |
| Gemini 3.5 Flash | gemini-3.5-flash | $0.750 (cached $0.075) | $4.500 | |
| Kimi K2.7 Code | kimi-k2.7-code | kimi | $0.665 | $2.800 |
| Kimi K2.6 | kimi-k2.6 | kimi | $0.620 | $2.600 |
| Kimi K2.5 | kimi-k2.5 | kimi | $0.210 | $1.050 |
| MiniMax M2.7 | minimax-m2.7 | minimax | $0.200 | $0.850 |
| MiniMax M3 | minimax-m3 | minimax | $0.420 | $1.680 |
| GPT-5.6 Sol | gpt-5.6-sol | openai | $2.500 (cached $0.250) | $15.000 |
| GPT-5.6 Terra | gpt-5.6-terra | openai | $1.250 | $7.500 |
| Grok 4.5 | grok-4.5 | xai | $1.000 | $3.000 |
| MiMo V2.5 | mimo-v2.5 | xiaomi | $0.098 | $0.196 |
| MiMo V2.5 Pro | mimo-v2.5-pro | xiaomi | $0.3045 | $0.609 |
| GLM 5.3 Flash | glm-5.3-flash | zhipu | $0.075 (cached $0.015) | $0.250 |
| GLM 5.1 | glm-5.1 | zhipu | $0.550 | $1.300 |
| GLM 5.2 | glm-5.2 | zhipu | $0.700 (cached $0.130) | $2.200 |
Rates may change. Models with long-context or cache-write rates may have additional pricing tiers; see the live model catalog for details.
Making a Request
Set the model field to an exact slug returned by /v1/models for your account:
curl https://api.llmai.dev/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "YOUR_AVAILABLE_MODEL_SLUG",
"messages": [{"role": "user", "content": "Review this Python snippet for bugs."}]
}'Slugs are case-sensitive. Copy them exactly from the current catalog.
Fetching the Model List Programmatically
curl https://api.llmai.dev/v1/models \
-H "Authorization: Bearer YOUR_API_KEY"Returns a standard ListModelsResponse object containing model IDs currently available to your account, subject to its tenant and key restrictions.
Notes on Pricing
- Token-priced models charge per one million tokens — input and output independently.
- Actual charges scale proportionally — a request using 2,000 tokens costs (2,000 ÷ 1,000,000) × rate.
- Model availability is subject to change; check the Models catalog for the current live list.