Pay only for what you use. No hidden fees. 50% less than official APIs.
| Model | Type | Input Price | Output Price | Description |
|---|---|---|---|---|
| gpt-4.1 | Chat | $1.25 per 1M tokens | $5.00 | Latest preview model with enhanced reasoning capabilities. |
| gpt-5-mini | Chat | $0.10 per 1M tokens | $0.40 | Next-gen efficient model for rapid tasks. |
| grok-3 | Chat | $1.00 per 1M tokens | $3.00 | Advanced reasoning model with real-time knowledge. |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | Chat | $0.15 per 1M tokens | $0.30 | Advanced open model finetuned for instruction following. |
| gpt-oss-120b | Chat | $0.50 per 1M tokens | $1.00 | Massive 120B parameter open source model. |
| Kimi-K2.5 | Chat | $0.25 per 1M tokens | $0.50 | Kimi K2.5 general purpose chat model. |
| Kimi-K2-Thinking | Reasoning | $0.25 per 1M tokens | $0.50 | Kimi model with enhanced reasoning capabilities. |
| DeepSeek-V3.1 | Chat | $0.07 per 1M tokens | $0.14 | DeepSeek V3.1 (Standard OpenAI Compatible). |
| FLUX.1-Kontext-pro | Image | $0.02 per image | - | State-of-the-art image generation. |
| grok-4-fast-non-reasoning | Chat | $0.50 per 1M tokens | $1.00 | The fastest Grok model for non-reasoning tasks. |
| DeepSeek-R1-0528 | Chat | $0.50 per 1M tokens | $2.00 | Specialized reasoning model. |
| Mistral-Large-3 | Chat | $1.00 per 1M tokens | $3.00 | Large-scale European flagship model. |
| gpt-4o-mini | Chat | $0.075 per 1M tokens | $0.30 | Affordable and intelligent model for fast, lightweight tasks. |
| gpt-4o | Chat | $1.25 per 1M tokens | $5.00 | Flagship Omni model with multimodal capabilities. |
| dall-e-3 | Image | $0.02 per image | - | Advanced image generation model. |
| sora | Video | $0.05 per second | - | Text-to-video generation. |
| gpt-5.2-chat | Chat | $0.10 per 1M tokens | $0.40 | Advanced GPT-5.2 Preview from Sweden region. |
| DeepSeek-V3.2 | Chat | $0.07 per 1M tokens | $0.14 | Latest DeepSeek V3.2 model. |
| model-router | Router | $0.075 per 1M tokens | $0.30 | Intelligent router that selects the best model for your query. |
| gpt-audio | Audio | $0.003 per minute | $0.006 | Speech-to-text and text-to-speech capabilities. |
| gpt-4o-mini-tts | Audio | $0.0075 per 1k chars | - | High definition text-to-speech. |
| gpt-realtime-mini | Realtime | $0.05 per minute | $0.20 | Low latency speech-to-speech. |
| gpt-4o-mini-realtime-preview | Realtime | $0.05 per minute | $0.20 | Latest realtime preview model. |
| gpt-4o-mini-audio-preview | Audio | $0.003 per minute | $0.006 | Preview model describing audio inputs. |