New: $100 promo credits · Daily limits applyGet started

Jev

Chat model by TypeSafe AI.

TypeSafe AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.

Get API keyPlayground
Models / JevID: typesafe/jev

Context window

Maximum input context length.

128K

tokens

Max output

Maximum completion tokens per request.

1K

tokens

Maker

TypeSafe AI

Served On: TypeSafe AI

Specifications

Context window, ranked against other chat models

Proportional scale: 0 to 1.05M tokens. Not ranked, no published context window: qwen-plus-2025-09-11, voxtral-small-24b-2507, qwen3.6-plus-2026-04-02.

Context window

128.0K

tokens
Max output

1K

tokens
Modality

chat

Vision
Function calling
System prompt

Benchmarks & performance rankings

Empirical intelligence benchmarks and category leaderboard placements for Jev.

Compare in BenchmarksLeaderboard
Leaderboard placements
#1
speedScore: 99.9%
Core benchmark dimensionsSource: TypeSafe AI Empirical Benchmark
MMLUKnowledge

0%

HumanEvalCoding

0%

Latency p50TTFT

95ms

p99: 280ms

ThroughputStream

250tok/s

SWE-bench: 0%

Recommended by nRouter Smart Routing: Real-time request routing and instant AI guardrails. Key operational strength: 70-95ms decision latency with zero output token lag.

Pricing

Rates are read live

Pricing for typesafe/jev is fetched from the live catalogue on load, so it is never served from a cache that could outlive a repricing.

Availability

Not enough data yet

We have not collected enough health probes for this model to publish an uptime or latency figure. A percentage from a handful of samples is fabricated precision, so none is shown until the sample count supports one.

How Jev is billed

Billed at the provider's list price, with no per-token markup.

Exact list price
Tokens settle at the published rate of the model that served your call.
Cache discounts passed through
Provider prompt-caching discounts reach your balance with no added fee.
Cost on every response
Each response carries the x-nr-request-cost header, so you can reconcile spend per request.

Start building with typesafe/jev

One API key, three steps. Choose your tool to begin.

  1. Get a key

    Create API key

  2. Set your API key

    export NROUTER_API_KEY="<YOUR_API_KEY>"

  3. Configure Claude Code

    Choose a tool, then copy its setup from the panel.

npm install -g @anthropic-ai/claude-code
Claude Code · typesafe/jev
# Point Claude Code to nRouter gateway
export ANTHROPIC_BASE_URL="https://api.nrouter.ai"
export ANTHROPIC_API_KEY="$NROUTER_API_KEY"

# Launch with typesafe/jev
claude --model typesafe/jev

FAQs

What is Jev?

TypeSafe AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.

How much does Jev cost?

Jev is billed at the provider's list price on nRouter with no per-token markup — tokens settle at the exact upstream rate. Input and output rates are read live, so see the pricing section above for the current figures.

What is the context length of Jev?

Jev supports a 128,000-token context window. It can generate up to 1,024 output tokens per request.

Does Jev support tool calling and structured outputs?

No. Jev does not support tool calling, so it cannot invoke external tools or functions.

What inputs and outputs does Jev support?

Jev takes text as input and returns text as output.

How do I use Jev via nRouter?

Use any OpenAI-compatible client: point it at https://api.nrouter.ai/v1 with your nRouter API key and set the model to "typesafe/jev". The quick-start panel above has a copy-paste curl command for this model.

When was Jev released?

Jev was released on September 29, 2026.

Where is the Jev documentation?

Start at nrouter.ai/docs. The quick-start guide (nrouter.ai/docs/getting-started/quick-start) covers API keys and your first request, and the API reference (nrouter.ai/docs/api-reference) lists every parameter.