Hyperbolic
Access open-source inference and compute at a fraction of the cost. Build with us. Inference platform · OpenAI-compatible API · Gpu Cloud · Low Cost · Open Source · Serverless
Intelligence vs Price
Best value among Hyperbolic models on this chart: DeepSeek V3 324 · QwQ 32B · Llama 3.3 70B Instruct (and 3 more on the dashed frontier). Hover any dot for full pricing, or click a creator in the legend to isolate.
Hyperbolic models
16 models, 16 with pricingModel | Creator | Input Price, $ | Output Price, $ | Context | Max Output | Inference Providers | Intelligence | Coding | |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3 324 | 0.200 | 0.400 | 164K | 16K | compare (13) | 22.3#1 | 22.0#1 | ||
| QwQ 32B | 0.150 | 0.200 | 131K | 16K | compare (8) | 19.7#2 | N/A | ||
| DeepSeek R1 | 0.280 | 0.400 | 164K | 66K | compare (14) | 18.8#3 | 15.9#3 | ||
| Llama 3.1 405B Instruct | 0.120 | 0.300 | 131K | 16K | compare (11) | 17.4#4 | 14.5#4 | ||
| DeepSeek V3 | 0.200 | 0.200 | 400K | 128K | compare (12) | 16.5#5 | 16.4#2 | ||
| Qwen2.5 72B Instruct | 0.120 | 0.300 | 131K | 16K | compare (8) | 15.6#6 | 11.9#5 | ||
| Llama 3.3 70B Instruct | 0.100 | 0.200 | 131K | 120K | compare (20) | 14.5#7 | 10.7#7 | ||
| Qwen2.5 Coder 32B Instruct | 0.050 | 0.100 | 131K | 33K | compare (8) | 12.9#8 | N/A | ||
| Llama 3.1 70B Instruct | 0.100 | 0.100 | 131K | 16K | compare (13) | 12.5#9 | 10.9#6 | ||
| Llama 3.1 8B Instruct | 0.020 | 0.030 | 200K | 128K | compare (20) | 11.8#10 | 4.9#9 | ||
| Hermes 3 Llama 3.1 70B | 0.120 | 0.300 | 131K | 16K | compare (3) | 10.6#11 | N/A | ||
| Llama 3.2 3B Instruct | 0.015 | 0.020 | 131K | 80K | compare (9) | 9.7#12 | N/A | ||
| Llama 3 70B Instruct | 0.120 | 0.300 | 131K | 8K | compare (9) | 8.9#13 | 6.8#8 | ||
| DeepSeek R1 528 | 0.200 | 0.250 | 164K | 33K | compare (12) | N/A | N/A | ||
| Kimi K2 Instruct | 0.500 | 2.00 | 262K | 33K | compare (9) | N/A | N/A | ||
| Qwen3 235B A22B | 0.071 | 0.100 | 262K | 131K | compare (9) | N/A | N/A |