AI Rate CardQwen3 Embedding 8B vs bge-large-zh-v1.5: API price and specs
Qwen3 Embedding 8B is 5% cheaper than bge-large-zh-v1.5 on input price.
Qwen3 Embedding 8B is 4% cheaper than bge-large-zh-v1.5 on a 1M-in / 200k-out workload.
| Field | Qwen3 Embedding 8B | bge-large-zh-v1.5 |
|---|---|---|
| Lowest input, per 1M | $0.01 | $0.01049 +4.9% |
| Median input, per 1M | $0.01055 | $0.02225 +110.9% |
| Lowest output, per 1M | $0.01049 | $0.01049 |
| Median output, per 1M | $0.01049 | $0.02225 +112% |
| Lowest unit price | $0.001118 / request | — |
| Cost of 1M in + 200k out | $0.0121 | $0.01259 +4.1% |
| Context | 41K | — |
| Max output | 33K | — |
| Providers | 14 | 2 +85.7% |
| Regions | — | — |
| Accepts | text | image, text |
| Returns | embedding, embeddings, text, vector | — |
| Type | Embeddings | Embeddings |
| Free option | no | no |
| Cheapest provider | deepinfra | moark |
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 Embedding 8B or bge-large-zh-v1.5?
Qwen3 Embedding 8B is 5% cheaper than bge-large-zh-v1.5 on input price. Qwen3 Embedding 8B is 4% cheaper than bge-large-zh-v1.5 on a 1M-in / 200k-out workload.
Where can I use both Qwen3 Embedding 8B and bge-large-zh-v1.5?
aihubmix, moark