impulse

Qwen3 Embedding 8B

Open weightsEmbedding
API id Qwen3-Embedding-8B
Input / 1M
$0.01
at Nebius AI Studio
Output / 1M
$0.00
at Nebius AI Studio
Context window
41K
tokens
Max output
41K
tokens per reply
Hosts
5
5 listings
Released
-
date not published

Pricing

List prices at Nebius AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.01$0.00

What it costs a month

At Nebius AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$3.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$4.80
  • Coding agent1,000 requests a day, 40K in / 2K out$12.00
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$24.00
Use your own numbers

Where to run it

5 hosts serve Qwen3 Embedding 8B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Qwen3-Embedding-8B
$0.01 / $0.00
LlamaGateGateway
qwen3-embedding-8b
$0.02 / $0.00
+100% vs headline
Novita AIInference
qwen3-embedding-8b
$0.07 / $0.00
+600% vs headline
qwen3-embedding-8b
$0.10 / $0.00
+900% vs headline
Fireworks AIInference
qwen3-embedding-8b
$0.10 / $0.00
+900% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Embeddings
Open weights
License: Apache-2.0
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Nebius AI Studio.

Smaller Alibaba Qwen models

No cheaper Alibaba Qwen model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using Nebius AI Studio's API.

Python
from litellm import completion

response = completion(
    model="nebius/Qwen3-Embedding-8B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen3 Embedding 8B cost?

On Nebius AI Studio, Qwen3 Embedding 8B costs $0.01 per million input tokens.

Which APIs offer Qwen3 Embedding 8B?

Qwen3 Embedding 8B runs on 5 APIs: Nebius AI Studio, LlamaGate, Novita AI, Scaleway and Fireworks AI.

What is Qwen3 Embedding 8B's context window?

41K tokens, with up to 41K tokens in one reply.

Is Qwen3 Embedding 8B being retired?

No retirement date is scheduled for it on any API we track.

What is Qwen3 Embedding 8B's API model id?

Use Qwen3-Embedding-8B with Nebius AI Studio. Other hosts use their own ids: qwen3-embedding-8b on LlamaGate, qwen3-embedding-8b on Novita AI, qwen3-embedding-8b on Scaleway, qwen3-embedding-8b on Fireworks AI.

Sources

Raw catalog entry for Qwen3-Embedding-8B on Nebius AI Studio
{
  "max_input_tokens": 40960,
  "input_cost_per_token": 1e-8,
  "output_cost_per_token": 0,
  "litellm_provider": "nebius",
  "mode": "embedding",
  "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B"
}