Hyperbolic LLM API pricing
Every model Hyperbolic serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.
Models served
16
on this provider
Cheapest input
$0.12
per 1M tokens
Cheapest output
$0.20
per 1M tokens
Max context
262K
tokens
| Model ID | |||||
|---|---|---|---|---|---|
| Hermes 3 70B Instruct | Nous Research | 131K | $0.12 | $0.30 | hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B |
| Qwen2 5 72B Instruct | Alibaba | 131K | $0.12 | $0.30 | hyperbolic/Qwen/Qwen2.5-72B-Instruct |
| Qwen2 5 Coder 32B Instruct | Alibaba | 33K | $0.12 | $0.30 | hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct |
| Llama 3.2 3B Instruct | Meta | 131K | $0.12 | $0.30 | hyperbolic/meta-llama/Llama-3.2-3B-Instruct |
| Llama 3.3 70B Instruct | Meta | 131K | $0.12 | $0.30 | hyperbolic/meta-llama/Llama-3.3-70B-Instruct |
| Meta Llama 3 70B Instruct | Meta | 131K | $0.12 | $0.30 | hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct |
| Meta Llama 3.1 405B Instruct | Meta | 128K | $0.12 | $0.30 | hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct |
| Meta Llama 3.1 70B Instruct | Meta | 131K | $0.12 | $0.30 | hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct |
| Meta Llama 3.1 8B Instruct | Meta | 131K | $0.12 | $0.30 | hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct |
| QwQ 32B | Alibaba | 131K | $0.20 | $0.20 | hyperbolic/Qwen/QwQ-32B |
| DeepSeek | DeepSeek | 164K | $0.20 | $0.20 | hyperbolic/deepseek-ai/DeepSeek-V3 |
| R1 0528 | DeepSeek | 164K | $0.25 | $0.25 | hyperbolic/deepseek-ai/DeepSeek-R1-0528 |
| DeepSeek V3 0324 | DeepSeek | 164K | $0.40 | $0.40 | hyperbolic/deepseek-ai/DeepSeek-V3-0324 |
| R1 | DeepSeek | 164K | $0.40 | $0.40 | hyperbolic/deepseek-ai/DeepSeek-R1 |
| Qwen3 235B A22B | Alibaba | 262K | $2.00 | $2.00 | hyperbolic/Qwen/Qwen3-235B-A22B |
| Kimi K2 Instruct | Moonshot | 131K | $2.00 | $2.00 | hyperbolic/moonshotai/Kimi-K2-Instruct |
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI