Context
131K
Max output
131K
Serving providers
3
Cheapest input
$0.12 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
31 t/s
tokens / second
Time to first token
2.27s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| EvalComputeProxyFrozen Aug 18, 2026 | 14.9 | default | — | |||||||||||||
| GPQA Diamond | 40% | default | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 4% | default | — | |||||||||||||
| LiveCodeBench | 19% | default | — | |||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 57% | default | — | |||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 23% | — | — | |||||||||||||
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.12 to $0.70 per 1M tokens across 3 providers, so the dearest route costs 483% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HyperbolicCheapest | $0.12 | $0.30 | 1 | ||||||||||
Standardhyperbolic/NousResearch/Hermes-3-Llama-3.1-70B
| |||||||||||||
| DeepInfra | $0.70 | $0.70 | 1 | ||||||||||
Standarddeepinfra/NousResearch/Hermes-3-Llama-3.1-70B
| |||||||||||||
| OpenRouter | $0.70 | $0.70 | 1 | ||||||||||
Standardnousresearch/hermes-3-llama-3.1-70b
| |||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$48
estimated / month
Model IDs
copy the exact identifier for your platformhyperbolic/NousResearch/Hermes-3-Llama-3.1-70Bnousresearch/hermes-3-llama-3.1-70bdeepinfra/NousResearch/Hermes-3-Llama-3.1-70B
Frequently asked questions
Hermes 3 70B Instruct pricing, context and availabilityHow much does Hermes 3 70B Instruct cost?
Hermes 3 70B Instruct costs $0.12 per 1M input tokens from Hyperbolic, and $0.30 per 1M output tokens from Hyperbolic. Across 3 serving providers, input prices range from $0.12 to $0.70 per 1M tokens.
What is the context window of Hermes 3 70B Instruct?
Hermes 3 70B Instruct accepts up to 131K tokens of context and can return up to 131K output tokens.
Which providers serve Hermes 3 70B Instruct?
Hermes 3 70B Instruct is available from 3 serving providers, each with its own pricing and model ID. Hyperbolic is currently the cheapest.
What can Hermes 3 70B Instruct do?
Hermes 3 70B Instruct supports tool use.
Other Nous Research models
compare pricing across the Nous Research lineupHermes 3 405B Instruct$1.00/1M · 3 providersHermes 4 70B$0.13/1M · 2 providersNous Hermes 2 Mixtral 8x7B Dpo$0.50/1M · 2 providersHermes 4 405B$1.00/1M · 2 providersHermes3 8B$0.025/1M · 1 providerHermes3 70B$0.12/1M · 1 providerHermes 2 Pro Llama 3 8B$0.14/1M · 1 providerHermes 3 8B Tee$0.15/1M · 1 provider
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI