AI Rate CardDeepSeek V4 Pro vs Hermes 4 405B: API price and specs
DeepSeek V4 Pro is 84% cheaper than Hermes 4 405B on input price.
DeepSeek V4 Pro is 79% cheaper than Hermes 4 405B on output price.
DeepSeek V4 Pro is 82% cheaper than Hermes 4 405B on a 1M-in / 200k-out workload.
DeepSeek V4 Pro has a 700% larger context than Hermes 4 405B.
| Field | DeepSeek V4 Pro | Hermes 4 405B |
|---|---|---|
| Lowest input, per 1M | $0.16 | $1.00 +531.5% |
| Median input, per 1M | $1.50 +50.2% | $1.00 |
| Lowest output, per 1M | $0.63 | $3.00 +373.8% |
| Median output, per 1M | $3.25 +8.3% | $3.00 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.28 | $1.60 +461.4% |
| Context | 1M | 131K +87.5% |
| Max output | 1M | 128K +87.8% |
| Providers | 44 | 8 +81.8% |
| Regions | APAC, EU, GLOBAL, US | GLOBAL |
| Accepts | file, text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | trustedrouter | cortecs |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
aiml, cortecs, edenai, kilo, nebius, openrouter, requesty, trustedrouter
Frequently asked questions
Which is cheaper, DeepSeek V4 Pro or Hermes 4 405B?
DeepSeek V4 Pro is 84% cheaper than Hermes 4 405B on input price. DeepSeek V4 Pro is 79% cheaper than Hermes 4 405B on output price. DeepSeek V4 Pro is 82% cheaper than Hermes 4 405B on a 1M-in / 200k-out workload.
Which has the larger context, DeepSeek V4 Pro or Hermes 4 405B?
DeepSeek V4 Pro: 1M tokens; Hermes 4 405B: 131K tokens.
Where can I use both DeepSeek V4 Pro and Hermes 4 405B?
aiml, cortecs, edenai, kilo, nebius, openrouter, requesty, trustedrouter