impulse

Jev Preview

OtherPreview
API id jev-preview
Input / 1M
$0.042
at TypeSafe
Output / 1M
$0.00
at TypeSafe
Context window
66K
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.042$0.00

What it costs a month

At TypeSafe list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$12.60
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$20.16
  • Coding agent1,000 requests a day, 40K in / 2K out$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 Jev Preview. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
jev-preview
$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

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 TypeSafe.

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 TypeSafe's API.

Python
from litellm import completion

response = completion(
    model="typesafe/jev-preview",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Jev Preview cost?

On TypeSafe, Jev Preview costs $0.042 per million input tokens.

Which APIs offer Jev Preview?

Jev Preview runs on 1 API: TypeSafe.

What is Jev Preview's context window?

66K tokens.

Is Jev Preview being retired?

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

What is Jev Preview's API model id?

Use jev-preview with TypeSafe.

Sources

Raw catalog entry for jev-preview on TypeSafe
{
  "input_cost_per_token": 4.2e-8,
  "litellm_provider": "typesafe",
  "max_input_tokens": 65536,
  "mode": "evaluation",
  "output_cost_per_token": 0,
  "source": "https://docs.typesafe.ai/models",
  "supports_box_questions": true
}