Hermes-3-Llama-3.1-70B vs GPT-4o-mini
API pricing, benchmark indices and specs — updated 19 October 2026.
NousResearch · A · Open weights
Params
70.6 B
Context
131,072
30d
2 K
llama3 licence · conditional
openai · B · API-only
Input / 1M
$0.15
Output / 1M
$0.60
AA index
6.7
proprietary · 128K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Hermes-3-Llama-3.1-70B | GPT-4o-mini |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 70.6 B | n/a — API-only |
| Architecture | LlamaForCausalLM | n/a — API-only |
| Context length | 131,072 | 128,000 |
| Licence | llama3 | Proprietary |
| Commercial use | Conditional | Per API terms |
| Languages | 1 | n/a — API-only |
| Downloads 30d | 2,075 | n/a — API-only |
| Downloads all time | 334 K | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2024-07-29 | n/a — API-only |
| API input price / 1M tokens | $0.70 | $0.15 |
| API output price / 1M tokens | $0.70 | $0.60 |
| Est. cost per 1M input + 1M output tokens | $1.40 | $0.75 |
| Cached input / 1M tokens | — | $0.075 |
| AA Intelligence Index | 6.7 | 6.7 |
| AA Coding Index | — | 11.4 |
| AA Agentic Index | — | — |
| Max output tokens | 16,384 | 16,384 |
| API providers | 1 | 2 |
| Tool calling | No | Yes |
| Reasoning mode | No | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Hermes-3-Llama-3.1-70B
$1.40
GPT-4o-mini
$0.75
GPT-4o-mini is 1.9× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Hermes-3-Llama-3.1-70B · fp16 @ 128K ctx
325.0 GB / 24 GB