AI Rate CardQwen3.8 2.4T A95B vs Ornith 1.5 35B A3B: API price and specs
Ornith 1.5 35B A3B is 91% cheaper than Qwen3.8 2.4T A95B on input price.
Ornith 1.5 35B A3B is 67% cheaper than Qwen3.8 2.4T A95B on output price.
Ornith 1.5 35B A3B is 86% cheaper than Qwen3.8 2.4T A95B on a 1M-in / 200k-out workload.
Qwen3.8 2.4T A95B has a 220% larger context than Ornith 1.5 35B A3B.
| Field | Qwen3.8 2.4T A95B | Ornith 1.5 35B A3B |
|---|---|---|
| Lowest input, per 1M | $1.05 +955% | $0.10 |
| Median input, per 1M | $2.00 +900% | $0.20 |
| Lowest output, per 1M | $1.20 +200% | $0.40 |
| Median output, per 1M | $6.00 +252.9% | $1.70 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $1.29 +619.4% | $0.18 |
| Context | 1M | 328K +68.8% |
| Max output | 262K | 66K +75% |
| Providers | 25 | 2 +92% |
| Regions | CN, EU, GLOBAL, US | CN |
| Accepts | image, text | image, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | trustedrouter | runinfra |
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, Qwen3.8 2.4T A95B or Ornith 1.5 35B A3B?
Ornith 1.5 35B A3B is 91% cheaper than Qwen3.8 2.4T A95B on input price. Ornith 1.5 35B A3B is 67% cheaper than Qwen3.8 2.4T A95B on output price. Ornith 1.5 35B A3B is 86% cheaper than Qwen3.8 2.4T A95B on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3.8 2.4T A95B or Ornith 1.5 35B A3B?
Qwen3.8 2.4T A95B: 1M tokens; Ornith 1.5 35B A3B: 328K tokens.
Where can I use both Qwen3.8 2.4T A95B and Ornith 1.5 35B A3B?
iteracompute, runinfra