tokenstat
tokenstat

Hermes 3 70B Instruct

deepinfra/NousResearch/Hermes-3-Llama-3.1-70B · rates as of · Benchmarks · Plans · Calculator

Open Llama instruction model for multilingual chat, reasoning, and coding

Cheapest input
$0.12
$/MTok · LiteLLM
Cheapest output
$0.3
$/MTok
Context
131K
tokens
Offers
7
3 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
LiteLLMcheapesthyperbolic/NousResearch/Hermes-3-Llama-3.1-70B$0.12$0.3$0.012
LiteLLMdeepinfra/NousResearch/Hermes-3-Llama-3.1-70B$0.3$0.3$0.03
LiteLLMNousResearch/Hermes-3-Llama-3.1-70B$0.3$0.3$0.03
LiteLLMHermes-3-Llama-3.1-70B$0.3$0.3$0.03
models.devNousResearch/hermes-3-llama-3.1-70bNanoGPT$0.408$0.408$066K
models.devnousresearch/hermes-3-llama-3.1-70bKilo Gateway$0.7$0.7$0131K
OpenRouternousresearch/hermes-3-llama-3.1-70bOpenRouter$0.7$0.7$0131K

Capabilities

  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2023-12-31Released: 2024-08-18Family: nousresearch

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash