AI Rate CardOrnith 1.5 35B A3B vs DeepSeek V4 Flash 0731: API price and specs
DeepSeek V4 Flash 0731 is 58% cheaper than Ornith 1.5 35B A3B on input price.
DeepSeek V4 Flash 0731 is 76% cheaper than Ornith 1.5 35B A3B on output price.
DeepSeek V4 Flash 0731 is 66% cheaper than Ornith 1.5 35B A3B on a 1M-in / 200k-out workload.
DeepSeek V4 Flash 0731 has a 220% larger context than Ornith 1.5 35B A3B.
| Field | Ornith 1.5 35B A3B | DeepSeek V4 Flash 0731 |
|---|---|---|
| Lowest input, per 1M | $0.10 +137% | $0.0422 |
| Median input, per 1M | $0.20 +41.8% | $0.14 |
| Lowest output, per 1M | $0.40 +321.3% | $0.09495 |
| Median output, per 1M | $1.70 +466.7% | $0.30 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.18 +194.2% | $0.06119 |
| Context | 328K +68.8% | 1M |
| Max output | 66K +93.8% | 1M |
| Providers | 2 +95.3% | 43 |
| Regions | CN | CN, EU, GLOBAL, US |
| Accepts | image, text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | runinfra | trustedrouter |
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 Flash 0731?
DeepSeek V4 Flash 0731 is 58% cheaper than Ornith 1.5 35B A3B on input price. DeepSeek V4 Flash 0731 is 76% cheaper than Ornith 1.5 35B A3B on output price. DeepSeek V4 Flash 0731 is 66% cheaper than Ornith 1.5 35B A3B on a 1M-in / 200k-out workload.
Which has the larger context, Ornith 1.5 35B A3B or DeepSeek V4 Flash 0731?
Ornith 1.5 35B A3B: 328K tokens; DeepSeek V4 Flash 0731: 1M tokens.
Where can I use both Ornith 1.5 35B A3B and DeepSeek V4 Flash 0731?
iteracompute, runinfra