AI Rate CardQwen3 Embedding 4B vs Qwen3 Embedding 8B: API price and specs
Qwen3 Embedding 8B has a 25% larger context than Qwen3 Embedding 4B.
| Field | Qwen3 Embedding 4B | Qwen3 Embedding 8B |
|---|---|---|
| Lowest input, per 1M | $0.01 | $0.01 |
| Median input, per 1M | $0.02 +89.6% | $0.01055 |
| Lowest output, per 1M | $0.01049 | $0.01049 |
| Median output, per 1M | $0.03925 +274.1% | $0.01049 |
| Lowest unit price | — | $0.001118 / request |
| Cost of 1M in + 200k out | $0.0121 | $0.0121 |
| Context | 33K +20% | 41K |
| Max output | 33K | 33K |
| Providers | 6 +57.1% | 14 |
| Regions | — | — |
| Accepts | text | text |
| Returns | text | embedding, embeddings, text, vector |
| 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
aihubmix, deepinfra, huggingface, moark, trustedrouter, vercel
Frequently asked questions
Which has the larger context, Qwen3 Embedding 4B or Qwen3 Embedding 8B?
Qwen3 Embedding 4B: 33K tokens; Qwen3 Embedding 8B: 41K tokens.
Where can I use both Qwen3 Embedding 4B and Qwen3 Embedding 8B?
aihubmix, deepinfra, huggingface, moark, trustedrouter, vercel