Kyma APIKyma API
TypeSafe

TypeSafe

Jev 1.13

Answers choice questions about a state with one option and a confidence. No prose, no images — a classifier you can put in front of a model, a tool call or a risky command. Billed per input token, rounded up to the nearest $0.0001.

Modalities

Text → Text

Below release

Not established

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#3/71

$0.0567

output $0.00

median $1.013 · best $0.0494

Price · output

$0.00

per 1M tokens generated

median $3.531 · best $0.218

Availability · 30d#1/70

100%

132 observations since 2026-09-20

median 100.0% · best 100.0%

Throughput

median 35.7 tok/s · best 365.1 tok/s

Response time

median 2.96 s · best 0.89 s

Context

32K

max output 255

published by TypeSafe, not measured here

Tick above each rail is this model, below it the other 70. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#77

of 101 active models

Tokens served

55.5K

all-time

Platform share

0.0%

of all tokens

Tokens · last 14 daysSep 26 → Oct 9

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$0.0567 /1M input$0.00 /1M output
Hobby10 req/day · 2K in / 500 out
~$0.03/mo
Production1,000 req/day · 2K in / 500 out
~$3.40/mo
Scale20,000 req/day · 2K in / 500 out
~$68.04/mo
+ Estimate your workload
1,000
2,000
500

Estimated monthly cost

$3.40

$0.1134 / day on Jev 1.13

Same workload on:

DeepSeek V4 Flash Vision$26.40+676%
Qwen 3.7 Flash$6.30+85%

Estimates use list pricing. Actual bills depend on real token counts, and every response includes its exact cost.

How it compares

Against the peers people actually weigh it against.

SpecJev 1.13DeepSeek V4 Flash VisionQwen 3.7 Flash
Input /1M$0.0567$0.2514$0.0504
Output /1M$0.00$0.7542$0.2187
Context32K1M1M
ToolsNoYesYes
ReasoningNoYesYes
Throughput49 tok/s68 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard — $0.50 free credit on the free tier, which covers Jev 1.13. No card required.

    Get API key →
  2. 2

    Make your first request

    Drop in your key, send a state and your questions, and read one answer per question.

    curl https://kymaapi.com/v1/decisions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jev",
    "state": "Proposed shell command: rm -rf ./build in a CI job.",
    "questions": {
      "gate": {
        "type": "choice",
        "instructions": "Should this command run?",
        "criteria": { "allow": "safe", "deny": "refuse", "escalate": "ask a human" }
      }
    }
  }'

FAQ

Common questions about this model.

What is the context window of Jev 1.13?

Jev 1.13 has a 32K-token context window — roughly 47 pages of text in a single request.

How much does the Jev 1.13 API cost?

$0.0567 per 1M input tokens and $0.00 per 1M output tokens. No subscription; you pay only for what you use.

Does Jev 1.13 support function calling?

No — Jev 1.13 does not support tool calling. For agent workloads, choose a tools-enabled model from the catalog.

Is Jev 1.13 ever served below the precision its creator released it at?

Kyma cannot say. Answering it needs the precision TypeSafe released Jev 1.13 in, and we could not source that from TypeSafe's own material — so there is nothing to compare a route against. We publish "not established" rather than reading a low format as a downgrade: on several models in this catalogue a low format is exactly how the creator ships it.

How do I use Jev 1.13?

Jev 1.13 has its own endpoint: POST https://kymaapi.com/v1/decisions with your Kyma API key, a state describing the situation and your questions, each listing the options it may pick. Every question comes back with one of your options and a confidence. It is not a chat model, so /v1/chat/completions returns 400 for it. Signing up is free and includes $0.50 of credit on the free tier, which covers this model — no card required.

Start with $0.50 free credit on the free tier — no card required.Create account →