impulse

Qwen3 Embedding 0 6B

Open weightsEmbedding
API id databricks-qwen3-embedding-0-6b
Input / 1M
$0.02
at Databricks
Output / 1M
$0.00
at Databricks
Context window
33K
tokens
Max output
33K
tokens per reply
Hosts
3
3 listings
Released
-
date not published

Pricing

List prices at Databricks, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.02$0.00
Cached input$0.02
Cache write, 5 minutes$0.02

What it costs a month

At Databricks list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$6.01
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$9.61
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$24.02
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$48.05
Use your own numbers

Where to run it

3 hosts serve Qwen3 Embedding 0 6B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
databricks-qwen3-embedding-0-6b
$0.02 / $0.00
Novita AIInference
qwen3-embedding-0.6b
$0.07 / $0.00
+250% vs headline
Fireworks AIInference
qwen3-embedding-0p6b
-

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 Databricks.

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

Call it

Using Databricks's API.

Python
from litellm import completion

response = completion(
    model="databricks/databricks-qwen3-embedding-0-6b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen3 Embedding 0 6B cost?

On Databricks, Qwen3 Embedding 0 6B costs $0.02 per million input tokens. Cached input costs $0.02 per million tokens.

Which APIs offer Qwen3 Embedding 0 6B?

Qwen3 Embedding 0 6B runs on 3 APIs: Databricks, Novita AI and Fireworks AI.

What is Qwen3 Embedding 0 6B's context window?

33K tokens, with up to 33K tokens in one reply.

Is Qwen3 Embedding 0 6B being retired?

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

What are cheaper alternatives to Qwen3 Embedding 0 6B?

Models that cost less and keep most of what it can do: Qwen3 Embedding 8B on Nebius AI Studio (50% less).

What is Qwen3 Embedding 0 6B's API model id?

Use databricks-qwen3-embedding-0-6b with Databricks. Other hosts use their own ids: qwen3-embedding-0.6b on Novita AI, qwen3-embedding-0p6b on Fireworks AI.

Sources

Raw catalog entry for databricks-qwen3-embedding-0-6b on Databricks
{
  "cache_creation_input_token_cost": 2.002e-8,
  "cache_read_input_token_cost": 2.002e-8,
  "input_cost_per_token": 2.002e-8,
  "input_dbu_cost_per_token": 2.86e-7,
  "litellm_provider": "databricks",
  "max_input_tokens": 32768,
  "metadata": {
    "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."
  },
  "mode": "embedding",
  "output_cost_per_token": 0,
  "output_dbu_cost_per_token": 0,
  "output_vector_size": 1024,
  "source": "https://www.databricks.com/product/pricing/foundation-model-serving"
}