AI Rate CardQwen3 Embedding 8B vs all-mpnet-base-v2: API price and specs
all-mpnet-base-v2 is 50% cheaper than Qwen3 Embedding 8B on input price.
all-mpnet-base-v2 is 41% cheaper than Qwen3 Embedding 8B on a 1M-in / 200k-out workload.
Qwen3 Embedding 8B has a 7900% larger context than all-mpnet-base-v2.
| Field | Qwen3 Embedding 8B | all-mpnet-base-v2 |
|---|---|---|
| Lowest input, per 1M | $0.01 +100% | $0.005 |
| Median input, per 1M | $0.01055 +36.2% | $0.007746 |
| Lowest output, per 1M | $0.01049 | $0.01049 |
| Median output, per 1M | $0.01049 | $0.01049 |
| Lowest unit price | $0.001118 / request | — |
| Cost of 1M in + 200k out | $0.0121 +70.4% | $0.007098 |
| Context | 41K | 512 +98.8% |
| Max output | 33K | — |
| Providers | 14 | 2 +85.7% |
| Regions | — | — |
| Accepts | text | — |
| Returns | embedding, embeddings, text, vector | — |
| Type | Embeddings | Embeddings |
| Free option | no | no |
| Cheapest provider | deepinfra | 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
Frequently asked questions
Which is cheaper, Qwen3 Embedding 8B or all-mpnet-base-v2?
all-mpnet-base-v2 is 50% cheaper than Qwen3 Embedding 8B on input price. all-mpnet-base-v2 is 41% cheaper than Qwen3 Embedding 8B on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3 Embedding 8B or all-mpnet-base-v2?
Qwen3 Embedding 8B: 41K tokens; all-mpnet-base-v2: 512 tokens.
Where can I use both Qwen3 Embedding 8B and all-mpnet-base-v2?
deepinfra, moark