Models and prices
One API key calls every model below; to switch, change the model field of your request. “N% off” means that much below the model maker's own price, on every item.
DeepSeek V4.1 Flash 40% off
DeepSeek's latest Flash model. Fast and inexpensive, with about 1M tokens of context, tool calls and image input. A good default for coding assistants, agents and everyday chat.
Input $0.1791 · Output $0.7164 / 1M tokens
OpenAI Anthropic
DeepSeek V4 Pro 49% off at peak
DeepSeek's flagship model for hard reasoning, coding and long agent tasks.
Input $0.6716 · Output $2.0149 / 1M tokens
OpenAI Anthropic
Hunyuan Hy3 15% off
The open-weight Hunyuan model. Inexpensive for chat, extraction and agent workloads, with tool calls.
Input $0.1119 · Output $0.4478 / 1M tokens
OpenAI Anthropic
Hunyuan Hy4 Preview 19% off
Preview of the next flagship Hunyuan model for agents and coding, with about 1M tokens of context and tool calls. Preview models may change or be retired.
Input $0.6716 · Output $2.0149 / 1M tokens
OpenAI Anthropic
Hunyuan MT2 Pro (translation) 24% off
Translation model for 33 languages, for documents, product copy and support content. 8K context, up to 4K output tokens per request.
Input $0.056 · Output $0.2239 / 1M tokens
OpenAI
Hunyuan MT2 Plus (translation) 24% off
Compact 7B translation model for 33 languages, with glossary, style and context instructions. 8K context, up to 4K output tokens per request.
Input $0.056 · Output $0.2239 / 1M tokens
OpenAI
Hunyuan MT2 Lite (translation) 23% off
Fast, low-cost translation for 33 languages and high-volume jobs. 8K context, up to 4K output tokens per request.
Input $0.0336 · Output $0.1343 / 1M tokens
OpenAI
GLM-5.3 5% off
Zhipu AI's flagship GLM model for coding, agents and long-context work, with tool calls.
Input $1.3233 · Output $4.159 / 1M tokens
OpenAI Anthropic
GLM-5.3 Flash 5% off
The fast, low-cost GLM model for everyday chat, extraction and high-volume jobs.
Input $0.1418 · Output $0.4726 / 1M tokens
OpenAI Anthropic
MiniMax M2.7
MiniMax's model for coding and agent workflows, with tool calls.
Input $0.2984 · Output $1.1939 / 1M tokens
OpenAI Anthropic
Kimi K3
Moonshot AI's flagship Kimi model for coding and long, multi-step agent tasks.
Input $2.9845 · Output $14.9225 / 1M tokens
OpenAI Anthropic
- USD per 1M tokens; input and output are billed on actual usage.
- Models with peak and off-peak prices show the peak price; see peak hours in your time zone.
- Reasoning models think before they answer; thinking is billed as output tokens.
Peak hours in your time zone
Models marked Peak / Off-peak cost less outside peak hours. The price is set by when the request arrives. Peak hours are 09:00–12:00 and 14:00–18:00 (UTC+8), Monday to Friday. Weekends (UTC+8) are off-peak all day. In local time this week:
| Time zone | Peak hours (all other times are off-peak) |
|---|---|
| UTC (UTC) | Mon–Fri 01:00–04:00 and 06:00–10:00 |
| London (UTC+1) | Mon–Fri 02:00–05:00 and 07:00–11:00 |
| Paris, Berlin, Amsterdam (UTC+2) | Mon–Fri 03:00–06:00 and 08:00–12:00 |
| New York, Toronto (US Eastern) (UTC-4) | Sun–Thu 21:00–24:00 Mon–Fri 02:00–06:00 |
| Los Angeles, Vancouver (US Pacific) (UTC-7) | Sun–Thu 18:00–21:00 and 23:00–03:00 next day |
| India (UTC+5:30) | Mon–Fri 06:30–09:30 and 11:30–15:30 |
| Bangkok, Jakarta, Ho Chi Minh City (UTC+7) | Mon–Fri 08:00–11:00 and 13:00–17:00 |
| Singapore, Kuala Lumpur, Manila, Hong Kong (UTC+8) | Mon–Fri 09:00–12:00 and 14:00–18:00 |
| Tokyo, Seoul (UTC+9) | Mon–Fri 10:00–13:00 and 15:00–19:00 |
| Sydney (UTC+11) | Mon–Fri 12:00–15:00 and 17:00–21:00 |
Times follow daylight saving time and are shown for the current week.