Qwen 3 Embedding 4B
InferenceOpen weights
Qwen 3 Embedding 4B by Inference costs $0.01 per 1M input tokens and $0.00 per 1M output tokens, with a 32K-token context window.
Pricing
Input (per 1M tokens)
$0.01
Output (per 1M tokens)
$0.00
Cached input (per 1M)
—
Specifications
- Provider
- Inference
- Context window
- 32K tokens
- Parameters
- —
- Released
- Jan 2025
- Open weights
- Yes
- Frontier model
- No
Compare Qwen 3 Embedding 4B with…
Qwen 3 Embedding 4B vs Mistral Nemo 12B Instruct$0.10/1MQwen 3 Embedding 4B vs Google Gemma 3$0.30/1MQwen 3 Embedding 4B vs Osmosis Structure 0.6B$0.50/1MQwen 3 Embedding 4B vs Qwen 2.5 7B Vision Instruct$0.20/1MQwen 3 Embedding 4B vs Llama 3.1 8B Instruct$0.03/1MQwen 3 Embedding 4B vs Llama 3.2 1B Instruct$0.01/1M
FAQ
Pricing is per 1M tokens (USD); confirm with the provider before production use.