7 providers50 models
Provider · hyperbolic

Hyperbolic — models and pricing

Hyperbolic hosts a broad open-weights catalog spanning the Llama, Qwen, DeepSeek, and Mistral families on commodity GPU infrastructure. Pricing is per-token and competitive — typically at or below the median for shared open-weights inference — with no per-tier feature gating between free-trial and paid usage.

The strength is breadth and rate parity: a single API key reaches most production-grade chat models without juggling multiple provider integrations, and the same per-million-token rate often covers Llama 3.3 70B, Qwen 3 72B, and Mixtral 8x22B. Throughput is solid for a GPU-backed host but lower than specialized hardware like Cerebras or Groq.

Best as a default open-weights host when model variety matters more than peak per-model speed, or for teams that want one billing relationship across the open-weights landscape.

Model catalog

11 models
ModelInput / 1MOutput / 1MContext
Qwen 2.5 72B Instruct$0.4000$0.4000131k
Qwen 3 72B Instruct$0.4000$0.4000131k
DeepSeek R1$2.0000$2.0000131k
DeepSeek R1 Distill Llama 70B$0.2000$0.2000131k
DeepSeek V3$0.2500$0.2500131k
Llama 3.1 405B Instruct$4.0000$4.0000131k
Llama 3.1 70B Instruct$0.4000$0.4000131k
Llama 3.1 8B Instruct$0.1000$0.1000131k
Llama 3.3 70B Instruct$0.4000$0.4000131k
Mixtral 8x22B Instruct$0.6000$0.600066k
Mixtral 8x7B Instruct$0.5000$0.500033k

Calculate cost for your workload

Plug in your monthly tokens — get the actual bill on every provider serving each model.

Open calculator