Calculate the cost of using Hermes-4-70B from Nebius for your AI applications
Pricing data last updated:
Mode: Chat
Max: 131,072 tokens
Max: 131,072 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
Hermes-4-70B is a chat model from Nebius, one of 55 chat models they offer. It is priced at $0.13 per 1M input tokens and $0.40 per 1M output tokens, ranking 595 out of 3639 chat models by cost and cheaper than 83% of models in this category. Hermes-4-70B supports function calling, reasoning. It accepts up to 131K input tokens.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 131,072 input tokens. The maximum output length is 131,072 tokens.
At $0.13 per 1M input tokens and $0.40 per 1M output tokens, Hermes-4-70B ranks 595 out of 3639 chat models by input cost. It is more affordable compared to the median of $0.58 for chat models, and is cheaper than 83% of models in this category.
Hermes-4-70B is one of 55 Nebius chat models, with support for function calling, reasoning.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs Hermes-4-70B |
|---|---|---|---|---|
| Phi-4-reasoning | Azure | $0.13 | $0.50 | -4% |
| qwen3-next-80b-a3b-thinking | Dashscope | $0.15 | $1.20 | +15% |
| qwen3-vl-32b-thinking | Dashscope | $0.16 | $2.87 | +23% |
Similar chat models from other providers
No. Hermes-4-70B costs $0.13 per 1M input tokens while Phi-4-reasoning costs $0.13 per 1M input tokens, making Phi-4-reasoning 4% more affordable for input. However, Hermes-4-70B may offer different capabilities or performance characteristics that justify the price difference.
Hermes-4-70B input pricing is $0.13 per 1M tokens, which is 78% below the median of $0.58 for chat models. It ranks 595 out of 3639 chat models by input cost, making it cheaper than 83% of models in this category. For output, it costs $0.40 per 1M tokens compared to the median of $1.66.
Among Nebius's 55 chat models, Hermes-4-70B ranks 21 by input cost.
The most comparable chat models to Hermes-4-70B are: Phi-4-reasoning from Azure ($0.13/1M input tokens); qwen3-next-80b-a3b-thinking from Dashscope ($0.15/1M input tokens); qwen3-vl-32b-thinking from Dashscope ($0.16/1M input tokens); qwen3-next-80b-a3b-thinking from Qwencloud ($0.15/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
Hermes-4-70B is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.13 and generating 1M output tokens costs $0.40.