← All models
Balanced — strong quality at a mid priceOpen Weights
Hermes 4 70B Pricing
Nous · nousresearch-hermes-4-70b
Input / 1M tokens
$0.130
Output / 1M tokens
$0.400
Context window
131,072 tokens
≈ 175 pages of text
Max output
—
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0003
1,000 requests / month$0.316/mo10,000 requests / month$3.16/mo100,000 requests / month$31.60/moEstimate your own workloadOpens the calculator with Hermes 4 70B preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Strong instruction following and structured output generation for agent workflows and multi-turn tasks.
The business tradeoff
Quality and latency vary with self-hosted or third-party inference; output token pricing is higher than some Llama 70B alternatives.
Head-to-head
Vendor list rates, as of Jun 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.