DeepSeek V4 Pro vs Hy3: API price and specs
Hy3 is 18% cheaper than DeepSeek V4 Pro on input price.
Hy3 is 17% cheaper than DeepSeek V4 Pro on output price.
Hy3 is 17% cheaper than DeepSeek V4 Pro on a 1M-in / 200k-out workload.
DeepSeek V4 Pro has a 300% larger context than Hy3.
| Field | DeepSeek V4 Pro | Hy3 |
|---|---|---|
| Lowest input, per 1M | $0.16 +21.7% | $0.13 |
| Median input, per 1M | $1.50 +975.4% | $0.14 |
| Lowest output, per 1M | $0.63 +19.9% | $0.53 |
| Median output, per 1M | $3.25 +471.7% | $0.57 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.28 +20.9% | $0.24 |
| Context | 1M | 262K +75% |
| Max output | 1M | 262K +75% |
| Providers | 44 | 19 +56.8% |
| Regions | APAC, EU, GLOBAL, US | APAC, US |
| Accepts | file, text | file, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | yes |
| Cheapest provider | trustedrouter | deepinfra |
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
aihubmix, aiml, deepinfra, edenai, huggingface, impossibl, kenari, kilo, novita, opencode, opencode-go, openrouter, orcarouter, poe, requesty, siliconflow, trustedrouter, vercel, zenmux
Frequently asked questions
Which is cheaper, DeepSeek V4 Pro or Hy3?
Hy3 is 18% cheaper than DeepSeek V4 Pro on input price. Hy3 is 17% cheaper than DeepSeek V4 Pro on output price. Hy3 is 17% cheaper than DeepSeek V4 Pro on a 1M-in / 200k-out workload.
Which has the larger context, DeepSeek V4 Pro or Hy3?
DeepSeek V4 Pro: 1M tokens; Hy3: 262K tokens.
Where can I use both DeepSeek V4 Pro and Hy3?
aihubmix, aiml, deepinfra, edenai, huggingface, impossibl, kenari, kilo, novita, opencode, opencode-go, openrouter, orcarouter, poe, requesty, siliconflow, trustedrouter, vercel, zenmux