All models are private. Zero data retention — no prompts, inputs, or outputs are stored or logged.
Chat Models
| Model | ID | Cost | Context | Added |
|---|
| GPT-5 | gpt-5 | $0.006/req | 128K | Jan 2026 |
| GPT-5 Mini | gpt-5-mini | $0.003/req | 128K | Jan 2026 |
| Claude Opus 4.6 | claude-opus-4.6 | $0.030/req | 200K | Mar 2026 |
| Claude Sonnet 4.6 | claude-sonnet-4.6 | $0.015/req | 200K | Mar 2026 |
| Claude Sonnet 4.5 | claude-sonnet-4.5 | $0.006/req | 200K | Dec 2025 |
| Claude Haiku 4.5 | claude-haiku-4.5 | $0.006/req | 200K | Dec 2025 |
| o3-mini | o3-mini | $0.006/req | 128K | Feb 2026 |
| Gemini 2.5 Pro | gemini-2.5-pro | $0.006/req | 1M | Feb 2026 |
| Gemini 2.5 Flash | gemini-2.5-flash | $0.003/req | 1M | Feb 2026 |
| Gemini 3 Pro | gemini-3-pro | $0.006/req | 1M | Mar 2026 |
| Gemini 3.1 Pro | gemini-3.1-pro | $0.006/req | 1M | Mar 2026 |
| Gemini 3 Flash | gemini-3-flash | $0.003/req | 1M | Mar 2026 |
| Grok 4 | grok-4 | $0.006/req | 128K | Mar 2026 |
| DeepSeek V3 | deepseek-v3 | $0.003/req | 128K | Nov 2025 |
| Kimi K2 | kimi-k2 | $0.006/req | 128K | Feb 2026 |
| Kimi K2.5 | kimi-k2.5 | $0.006/req | 128K | Mar 2026 |
| Mistral Large | mistral-large | $0.006/req | 128K | Jan 2026 |
| Llama 4 Maverick | llama-4-maverick | $0.006/req | 128K | Mar 2026 |
| Llama 4 Scout | llama-4-scout | $0.003/req | 128K | Mar 2026 |
| QwQ 32B | qwq-32b | $0.003/req | 32K | Jan 2026 |
| GLM 5 | glm-5 | $0.003/req | 128K | Feb 2026 |
| MiniMax M2.5 | minimax-m2.5 | $0.003/req | 128K | Jan 2026 |
| Ninja 1 | ninja-1 | $0.003/req | 128K | Oct 2025 |
| Uncensored AI | uncensored-ai | $0.003/req | 128K | Oct 2025 |
Image Models
| Model | ID | Cost | Speed | Added |
|---|
| FLUX Kontext Max | flux-kontext-max | $0.10/img | ~5-15s | Mar 2026 |
| FLUX.2 Flex | flux-2-flex | $0.08/img | ~5-10s | Mar 2026 |
| FLUX.1 Pro Ultra | flux-1-pro-ultra | $0.08/img | ~8-15s | Dec 2025 |
| Recraft V3 | recraft-v3 | $0.08/img | ~5s | Nov 2025 |
| Google Imagen 4 | google-imagen-4 | $0.08/img | ~15s | Mar 2026 |
| Nano Banana Pro | nano-banana-pro | $0.08/img | ~5s | Feb 2026 |
| Seedream | seedream | $0.08/img | ~8s | Mar 2026 |
| FLUX.2 Pro | flux-2-pro | $0.05/img | ~3-5s | Feb 2026 |
| FLUX Kontext Pro | flux-kontext-pro | $0.05/img | ~5s | Mar 2026 |
| Nano Banana 2 | nano-banana-2 | $0.05/img | ~3s | Jan 2026 |
| FLUX.1 Fill | flux-1-fill | $0.05/img | ~5s | Dec 2025 |
| FLUX.2 Klein | flux-2-klein | $0.03/img | under 2s | Feb 2026 |
| Nano Banana | nano-banana | $0.03/img | ~2s | Oct 2025 |
Video Models
| Model | ID | Cost | Duration | Speed | Added |
|---|
| Runway Gen-4.5 | runway-gen4.5 | $5.00/vid | 5-10s | ~1-3 min | Mar 2026 |
| Veo 3.1 | veo-3.1 | $5.00/vid | 4-8s | ~3-5 min | Mar 2026 |
| Veo 3.1 Fast | veo-3.1-fast | $3.00/vid | 4-8s | ~1-2 min | Mar 2026 |
| Google Veo 2 | google-veo-2 | $3.00/vid | 5-8s | ~40s | Jan 2026 |
| Veo 3 Fast | google-veo-3-fast | $3.00/vid | 4-8s | ~1-2 min | Mar 2026 |
| Seedance 2 | seedance-2 | $3.00/vid | 5-15s | ~1-2 min | Feb 2026 |
| Kling Video | kling-video | $3.00/vid | 5-10s | ~3-4 min | Feb 2026 |
| Runway Gen-4 Turbo | runway-gen4-turbo | $3.00/vid | 5-10s | ~30-60s | Mar 2026 |
Smart Routing
| ID | Strategy | Billed at |
|---|
auto | Best model per task type | Resolved model’s rate |
auto-fast | Lowest latency | Resolved model’s rate |
auto-cheap | Lowest cost | Resolved model’s rate |
auto-quality | Highest quality | Resolved model’s rate |
ensemble | 3-model consensus | $0.040/req |
ensemble-quality | Premium consensus | $0.050/req |
How smart routing works