AI Rate CardOrnith 1.5 35B A3B vs DeepSeek V4 Pro 0813: API price and specs
Ornith 1.5 35B A3B is 13% cheaper than DeepSeek V4 Pro 0813 on input price.
Ornith 1.5 35B A3B is 69% cheaper than DeepSeek V4 Pro 0813 on output price.
Ornith 1.5 35B A3B is 52% cheaper than DeepSeek V4 Pro 0813 on a 1M-in / 200k-out workload.
DeepSeek V4 Pro 0813 has a 220% larger context than Ornith 1.5 35B A3B.
| Field | Ornith 1.5 35B A3B | DeepSeek V4 Pro 0813 |
|---|---|---|
| Lowest input, per 1M | $0.10 | $0.12 +15% |
| Median input, per 1M | $0.20 | $1.32 +560% |
| Lowest output, per 1M | $0.40 | $1.29 +221.7% |
| Median output, per 1M | $1.70 | $3.96 +132.9% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.18 | $0.37 +106.9% |
| Context | 328K +68.8% | 1M |
| Max output | 66K +93.8% | 1M |
| Providers | 2 +94.6% | 37 |
| Regions | CN | APAC, EU, GLOBAL, US |
| Accepts | image, text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | runinfra | openrouter |
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
Frequently asked questions
Which is cheaper, Ornith 1.5 35B A3B or DeepSeek V4 Pro 0813?
Ornith 1.5 35B A3B is 13% cheaper than DeepSeek V4 Pro 0813 on input price. Ornith 1.5 35B A3B is 69% cheaper than DeepSeek V4 Pro 0813 on output price. Ornith 1.5 35B A3B is 52% cheaper than DeepSeek V4 Pro 0813 on a 1M-in / 200k-out workload.
Which has the larger context, Ornith 1.5 35B A3B or DeepSeek V4 Pro 0813?
Ornith 1.5 35B A3B: 328K tokens; DeepSeek V4 Pro 0813: 1M tokens.
Where can I use both Ornith 1.5 35B A3B and DeepSeek V4 Pro 0813?
iteracompute, runinfra