Jev
jevPricing
List prices at Vercel AI Gateway, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.042 | $0.00 |
What it costs a month
At Vercel AI Gateway 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
Where to run it
2 hosts serve Jev. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
TypeSafeCloud jev-latest | $0.042 / $0.00 | jev-latest | |
Vercel AI GatewayGateway jev | $0.042 / $0.00 | jev |
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
- ImagesText
- 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 Vercel AI Gateway.
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 Vercel AI Gateway's API.
from litellm import completion
response = completion(
model="vercel_ai_gateway/jev",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Jev cost?
On Vercel AI Gateway, Jev costs $0.042 per million input tokens.
Which APIs offer Jev?
Jev runs on 2 APIs: TypeSafe and Vercel AI Gateway.
What is Jev's context window?
32K tokens.
Is Jev being retired?
No retirement date is scheduled for it on any API we track.
What is Jev's API model id?
Use jev with Vercel AI Gateway. Other hosts use their own ids: jev-latest on TypeSafe.
Sources
Raw catalog entry for jev on Vercel AI Gateway
{
"input_cost_per_token": 4.2e-8,
"litellm_provider": "vercel_ai_gateway",
"max_input_tokens": 32000,
"metadata": {
"notes": "Vercel AI Gateway model list entry typesafe-ai/jev, read 2026-11-09: input 0.000000042 per token, output 0, context window 32000. A direct /v1/decisions probe with a 768x768 input_image answered 200 on 2026-11-10, while a 96x96 one answered 400 invalid request body."
},
"mode": "evaluation",
"output_cost_per_token": 0,
"source": "https://ai-gateway.vercel.sh/v1/models",
"supported_modalities": [
"text",
"image"
],
"supports_box_questions": true,
"supports_vision": true
}