Hyperbolic models & pricing
Hyperbolic hosts 16 models (16 with public pricing) covering 1 modalities. Decentralized GPU inference for Llama, Qwen, DeepSeek, and FLUX. Cheapest input starts at $0.120/M tokens; the most premium goes up to $2.00/M. Use Future AGI's Agent Command Center to route any Hyperbolic model with cost-optimized fallback and unified observability.
chat 16
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| Meta Llama Llama 3.2 3B Instruct | $0.120/M | $0.300/M | 32,768 | tools |
| Meta Llama Llama 3.3 70B Instruct | $0.120/M | $0.300/M | 131,072 | tools |
| Meta Llama Meta Llama 3.1 405B Instruct | $0.120/M | $0.300/M | 32,768 | tools |
| Meta Llama Meta Llama 3.1 70B Instruct | $0.120/M | $0.300/M | 32,768 | tools |
| Meta Llama Meta Llama 3.1 8B Instruct | $0.120/M | $0.300/M | 32,768 | tools |
| Meta Llama Meta Llama 3.70B Instruct | $0.120/M | $0.300/M | 131,072 | tools |
| Nousresearch Hermes 3 Llama 3.1 70B | $0.120/M | $0.300/M | 32,768 | tools |
| Qwen Qwen2.5 72B Instruct | $0.120/M | $0.300/M | 131,072 | tools |
| Qwen Qwen2.5 Coder 32B Instruct | $0.120/M | $0.300/M | 32,768 | tools |
| DeepSeek AI DeepSeek v3 | $0.200/M | $0.200/M | 32,768 | tools |
| Qwen Qwq 32B | $0.200/M | $0.200/M | 131,072 | tools |
| DeepSeek AI DeepSeek R1.0528 | $0.250/M | $0.250/M | 131,072 | tools |
| DeepSeek AI DeepSeek R1 | $0.400/M | $0.400/M | 32,768 | tools |
| DeepSeek AI DeepSeek v3.0324 | $0.400/M | $0.400/M | 32,768 | tools |
| Moonshotai Kimi K2 Instruct | $2.00/M | $2.00/M | 131,072 | tools |
| Qwen Qwen3.235b A22b | $2.00/M | $2.00/M | 131,072 | tools |
FAQ
How many Hyperbolic models are there?
16 Hyperbolic models are listed across 1 modality on this page. 16 have public per-token pricing.
How is Hyperbolic pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which Hyperbolic model is cheapest?
Input pricing on Hyperbolic starts at $0.120 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to Hyperbolic via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Hyperbolic target, and call Hyperbolic models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.