API pricing per million tokens
qwen3-embedding-4b Open weightsChecked 8h ago
- Input
- $0.02
- per 1M, DeepInfra (us)
- Output
- Free
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 33K
- released Oct 28, 2025
Where to buy it (1)
DeepInfraus$0.02 / Free$0.015 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $2.00 direct.
Helicone$2.00+0%
Kong AI Gateway$2.00+0%
LiteLLM$2.00+0%
Vercel AI Gateway$2.00+0%
AWS Bedrock$2.00+0%
Azure AI Foundry$2.00+0%
Google Vertex AI$2.00+0%
Databricks Mosaic AI$2.00+0%
Hugging Face Inference$2.00+0%
Cloudflare AI Gateway$2.10+5%
Requesty$2.10+5%
Eden AI$2.11+5.5%
OpenRouter$2.11+5.5%
Snowflake Cortex AI$2.40+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
Qwen3.8 Max PrimeQwen (Alibaba) · 1M$4 / $12in / out per 1M$4$12$0.51MSep 23, 2026
Text Embedding 3 SmallOpenAI · 8K$0.02 / Freein / out per 1M$0.02Freen/a8KOct 30, 2025
Llama 3.1 8B InstructMeta · via DeepInfra (fp8) · 131K$0.02 / $0.04in / out per 1M$0.02$0.04n/a131KJul 23, 2024
Mistral NemoMistral AI · via DekaLLM (fp8) · 131K$0.018 / $0.03in / out per 1M$0.018$0.03n/a131KJul 19, 2024
About Qwen3 Embedding 4B
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.
Takes text in and returns embeddings. First listed Sep 24, 2026. Blended price $0.015 per 1M tokens at 3 input to 1 output.
Across fru.devCompany profile
Questions
How much does Qwen3 Embedding 4B cost?
$0.02 per million input tokens and Free per million output tokens.
What is the context window of Qwen3 Embedding 4B?
33K tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.