AI Rate CardQwen3 Embedding 4B vs BGE M3: API price and specs
BGE M3 is 5% cheaper than Qwen3 Embedding 4B on output price.
BGE M3 is 1% cheaper than Qwen3 Embedding 4B on a 1M-in / 200k-out workload.
Qwen3 Embedding 4B has a 300% larger context than BGE M3.
| Field | Qwen3 Embedding 4B | BGE M3 |
|---|---|---|
| Lowest input, per 1M | $0.01 | $0.01 |
| Median input, per 1M | $0.02 +95.2% | $0.01025 |
| Lowest output, per 1M | $0.01049 +4.9% | $0.01 |
| Median output, per 1M | $0.03925 +283% | $0.01025 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.0121 +0.8% | $0.012 |
| Context | 33K | 8K +75% |
| Max output | 33K | — |
| Providers | 6 | 6 |
| Regions | — | — |
| Accepts | text | text |
| Returns | text | text |
| Type | Embeddings | Embeddings |
| Free option | no | no |
| Cheapest provider | huggingface | 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 4B or BGE M3?
BGE M3 is 5% cheaper than Qwen3 Embedding 4B on output price. BGE M3 is 1% cheaper than Qwen3 Embedding 4B on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3 Embedding 4B or BGE M3?
Qwen3 Embedding 4B: 33K tokens; BGE M3: 8K tokens.
Where can I use both Qwen3 Embedding 4B and BGE M3?
deepinfra, moark