Side-by-side comparison
Phi 4 vs Hermes 4 70B
| Phi 4 | Hermes 4 70B | |
|---|---|---|
| Provider | Microsoft | Nous |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 16,384 | 131,072 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | json_mode | json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.0650 | 0.1300 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.1400 | 0.4000 |
Frequently asked questions
Which is cheaper, Phi 4 or Hermes 4 70B?
Phi 4 is cheaper than Hermes 4 70B on a 50/50 input/output blend by about $0.1625 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, Phi 4 or Hermes 4 70B?
Hermes 4 70B has the larger context window at 131k tokens versus 16k tokens for Phi 4. That means Hermes 4 70B can ingest about 8.0x as much text per request.
What is the difference between Phi 4 and Hermes 4 70B?
Phi 4 comes from Microsoft; Hermes 4 70B comes from Nous. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.