Models
38 models through one API key. Open one to compare its providers and prices.
Model
- OpenAI: GPT-4.1 Mini425.9KFree1256K32.8K
- NVIDIA: Nemotron 3 Nano Omni 30B A3B Reasoning425.8KFree1256K65.5K
- OpenAI: GPT-6 Astra81.5K$1.12 / $5.6051.1M128K
- OpenAI: GPT-6 Sol57.2K$0.22 / $1.1251.1M128K
- OpenAI: GPT-4.126.1KFree1256K32.8K
- OpenAI: GPT-5.6 Sol1.3K$0.45 / $2.2461.1M128K
- OpenAI: GPT-6 Luna619$0.030 / $0.1331.1M128K
- OpenAI: GPT-5.4 Mini500$0.60 / $3.602400K128K
- OpenAI: GPT-5.5393$4.00 / $24.0021.1M128K
- OpenAI: GPT-5 Mini319Free1256K128K
- OpenAI: GPT-5.2207Free1256K128K
- OpenAI: GPT-5202Free1256K128K
- OpenAI: GPT-5.6 Luna201$0.050 / $0.3051.1M128K
- OpenAI: GPT-5.1176Free1256K128K
- OpenAI: GPT-5.4162$2.00 / $12.0021.1M128K
- OpenAI: GPT-5.6 Terra151$0.22 / $1.3551.1M128K
- NVIDIA: Nemotron 3.5 Super VL0Free11M131.1K
- OpenAI: GPT-6.1 Sol—$0.22 / $1.1241.1M128K
- Qwen3.8 Max—$0.22 / $0.6721M131.1K
- Llama: Muse Spark 1.3—$1.00 / $3.4021M943.7K
- OpenAI: GPT-6.1 Terra Pro—$1.00 / $5.0011.1M128K
- OpenAI: GPT-6.1 Terra—$0.25 / $1.2531.1M128K
- OpenAI: GPT-6.1 Sol Pro—$2.00 / $10.0011.1M128K
- OpenAI: GPT-6 Astra Pro—$10.00 / $50.0011.1M128K
- Qwen3.8 Omni Flash—$0.12 / $0.3811M131.1K
- Qwen3.8 Max Prime—$4.60 / $13.8011M131.1K
- Qwen3.8 Max 0902—$2.30 / $6.9011M131.1K
- Qwen3.8 Flash—$0.12 / $0.3811M131.1K
- Qwen3.7 Plus—$0.32 / $1.2811M131.1K
- Qwen3.7 Flash—$0.024 / $0.1011M131.1K
- Qwen3.5 Flash—$0.080 / $0.321128K16.4K
- Qwen3 VL-235B A22B Thinking—$0.40 / $1.601262.1K32.8K
- Qwen3 VL-235B A22B Instruct—$0.24 / $2.191262.1K32.8K
- Qwen2.5 VL-72B Instruct—$0.80 / $0.851128K128K
- Llama: Muse Spark 1.2—$1.00 / $3.4011M943.7K
- Llama: Muse Spark 1.1—$1.00 / $3.4011M943.7K
- OpenAI: GPT-5.5 Pro—$24.00 / $144.0011.1M128K
- OpenAI: GPT-5.4 Nano—$0.16 / $1.001400K128K