AI Rate CardQwen3 Embedding 4B vs jina-embeddings-v2-base-code: API price and specs
Qwen3 Embedding 4B is 80% cheaper than jina-embeddings-v2-base-code on input price.
Qwen3 Embedding 4B is 79% cheaper than jina-embeddings-v2-base-code on output price.
Qwen3 Embedding 4B is 80% cheaper than jina-embeddings-v2-base-code on a 1M-in / 200k-out workload.
Qwen3 Embedding 4B has a 300% larger context than jina-embeddings-v2-base-code.
| Field | Qwen3 Embedding 4B | jina-embeddings-v2-base-code |
|---|---|---|
| Lowest input, per 1M | $0.01 | $0.05 +400% |
| Median input, per 1M | $0.02 | $0.05138 +156.9% |
| Lowest output, per 1M | $0.01049 | $0.05 +376.6% |
| Median output, per 1M | $0.03925 | $0.05 +27.4% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.0121 | $0.06 +395.9% |
| Context | 33K | 8K +75% |
| Max output | 33K | — |
| Providers | 6 | 2 +66.7% |
| Regions | — | — |
| Accepts | text | text |
| Returns | text | embeddings |
| Type | Embeddings | Embeddings |
| Free option | no | no |
| Cheapest provider | huggingface | aihubmix |
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 jina-embeddings-v2-base-code?
Qwen3 Embedding 4B is 80% cheaper than jina-embeddings-v2-base-code on input price. Qwen3 Embedding 4B is 79% cheaper than jina-embeddings-v2-base-code on output price. Qwen3 Embedding 4B is 80% cheaper than jina-embeddings-v2-base-code on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3 Embedding 4B or jina-embeddings-v2-base-code?
Qwen3 Embedding 4B: 33K tokens; jina-embeddings-v2-base-code: 8K tokens.
Where can I use both Qwen3 Embedding 4B and jina-embeddings-v2-base-code?
aihubmix, trustedrouter