Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| Kimi K3 moonshot/kimi-k3 | Jev 1.14 typesafe/jev-1.14.0 | |
|---|---|---|
| Provider | Moonshot | Typesafe |
| Family | ||
| Modality | text | text |
| Context window | 1,048,576 tok | 32,000 tok |
| Max output | 32,768 tok | 32,000 tok |
| Released | 2026-07-16 | 2026-10-16 |
| Input price | $3.00 /1M | $0.042 /1M |
| Output price | $15.00 /1M | $0.0000 /1M |
| Cache read | — | — |
| Tools | yes | — |
| Streaming | yes | yes |
| Vision | yes | — |
| JSON mode | yes | — |
| Reasoning | yes | — |
| Prompt caching | — | — |
Kimi K3 is Moonshot's flagship 2.8 trillion-parameter model, built on Kimi Delta Attention (a hybrid linear attention mechanism) with Attention Residuals. It offers native visual understanding, always-on reasoning, and a 1M-token context window for long-horizon coding, knowledge work, and deep reasoning tasks.
Jev 1.14 is TypeSafe's structured evaluation model. It evaluates one state against typed Noul, Choice, Score, and Box questions and returns calibrated answers with probabilities and confidence. Image inputs and Box questions are beta and dreamer-ready, not recommended for production.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try Kimi K3
client.chat.completions.create(
model="moonshot/kimi-k3",
messages=[{"role":"user","content":"hello"}],
)
# Try Jev 1.14 — same client, same key
client.chat.completions.create(
model="typesafe/jev-1.14.0",
messages=[{"role":"user","content":"hello"}],
)