impulse

Openjev Qwen35 4B

Open weightsOther
API id databricks-openjev-qwen35-4b
Input / 1M
$0.042
at Databricks
Output / 1M
$0.00
at Databricks
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.042$0.00
Cached input$0.042
Cache write, 5 minutes$0.042

What it costs a month

At Databricks list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$12.60
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$20.16
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$50.40
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$101
Use your own numbers

Where to run it

1 host serve Openjev Qwen35 4B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
databricks-openjev-qwen35-4b
$0.042 / $0.00

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
Text
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 Independent models

No cheaper Independent 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 Databricks's API.

Python
from litellm import completion

response = completion(
    model="databricks/databricks-openjev-qwen35-4b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Openjev Qwen35 4B cost?

On Databricks, Openjev Qwen35 4B costs $0.042 per million input tokens. Cached input costs $0.042 per million tokens.

Which APIs offer Openjev Qwen35 4B?

Openjev Qwen35 4B runs on 1 API: Databricks.

Is Openjev Qwen35 4B being retired?

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

What is Openjev Qwen35 4B's API model id?

Use databricks-openjev-qwen35-4b with Databricks.

Sources

Raw catalog entry for databricks-openjev-qwen35-4b on Databricks
{
  "cache_creation_input_token_cost": 4.2e-8,
  "cache_read_input_token_cost": 4.2e-8,
  "input_cost_per_token": 4.2e-8,
  "input_dbu_cost_per_token": 6e-7,
  "litellm_provider": "databricks",
  "metadata": {
    "notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. The serving-endpoints API lists it at 0.6 DBUs per 1M input tokens (input_price on the foundation_model entry, read 2026-10-27); input_cost_per_token is that dbu cost * $0.070, the same conversion as the other databricks rows. Output is free. Databricks publishes no cache rates for it, so cache tokens bill at the input rate."
  },
  "mode": "evaluation",
  "output_cost_per_token": 0,
  "output_dbu_cost_per_token": 0,
  "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models"
}