Qwen3 embedding model with 32K context and configurable output dimensions (32–4096) via Matryoshka representation learning. No. 1 on the MTEB multilingual leaderboard as of June 2025 (score 70.58), supporting 100+ languages.
DigitSpace routes requests to the best providers that are able to handle your prompt size and parameters.
Qwen3 embedding model with 32K context and configurable output dimensions (32–4096) via Matryoshka representation learning. No. 1 on the MTEB multilingual leaderboard as of June 2025 (score 70.58), supporting 100+ languages. You can access it through DigitSpace's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Qwen3 Embedding 8B on DigitSpace starts at $0.01 per million input tokens and $0.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Qwen3 Embedding 8B supports a context window of up to 32,768 tokens on its largest provider deployment.
Qwen3 Embedding 8B is served by DeepInfra through DigitSpace. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
No. Qwen3 Embedding 8B does not currently support tool calling or structured JSON outputs through DigitSpace.
Qwen3 Embedding 8B was released on June 5, 2025.
Qwen3.8 Flash
128,000 context$0.14 in / $0.45 out per 1M
Qwen3.8 Max
128,000 context$2.02 in / $6.05 out per 1M
Qwen3.7 Plus
128,000 context$0.30 in / $1.22 out per 1M
Qwen3.7 Max
128,000 context$1.40 in / $4.20 out per 1M
Qwen3.6 Plus
128,000 context$0.31 in / $1.85 out per 1M
Qwen3.6 35B A3B
128,000 context$0.21 in / $1.24 out per 1M