Compare

Jev 1.14 vs MiniMax H3 Highspeed

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
J1
Jev 1.14
typesafe/jev-1.14.0
MiniMax H3 Highspeed
minimax/h3-highspeed
Provider
Typesafe
MiniMax
Family
Modality
text
video
Context window
32,000 tok
—
Max output
32,000 tok
—
Released
2026-10-16
2026-10-30
License
Open-weight
Open-weight
Input price
$0.042 /1M
—
Output price
$0.0000 /1M
—
Per output second
—
$0.030 /sec
Tools
—
—
Streaming
yes
—
Vision
—
—
JSON mode
—
—
Reasoning
—
—
Prompt caching
—
—
Batch API
—
—
Try it
Open in playground →
View model →
Jev 1.14
typesafe/jev-1.14.0
Full spec →

Jev (1.14) is TypeSafe's decision model for structured evaluation. Classify inputs and score decisions using typed questions, probabilities, and confidence.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
MiniMax H3 Highspeed
minimax/h3-highspeed
Full spec →

A multimodal video generation model that balances quality and speed, supporting text-to-video, first and last frame image-to-video, and reference-to-video generation at 480P and 768P.

Strengths
  • Text-to-video generation
Use cases
PromosDemosStoryboards

Compare with another

Gemini 4 Carbon vs Jev 1.14
google/gemini-4-carbon · typesafe/jev-1.14.0
Gemini 4 Carbon vs MiniMax H3 Highspeed
google/gemini-4-carbon · minimax/h3-highspeed
Claude Opus 5.5 vs Jev 1.14
anthropic/claude-opus-5.5 · typesafe/jev-1.14.0
Claude Opus 5.5 vs MiniMax H3 Highspeed
anthropic/claude-opus-5.5 · minimax/h3-highspeed
Claude Sonnet 5.5 vs Jev 1.14
anthropic/claude-sonnet-5.5 · typesafe/jev-1.14.0
Claude Sonnet 5.5 vs MiniMax H3 Highspeed
anthropic/claude-sonnet-5.5 · minimax/h3-highspeed
Kimi-K3.1-Pro vs Jev 1.14
moonshot/kimi-k3.1-pro · typesafe/jev-1.14.0
Kimi-K3.1-Pro vs MiniMax H3 Highspeed
moonshot/kimi-k3.1-pro · minimax/h3-highspeed
Deepseek-V4.1-Flash-1017 vs Jev 1.14
deepseek/deepseek-v4.1-flash-1017 · typesafe/jev-1.14.0
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Jev 1.14
client.chat.completions.create(
    model="typesafe/jev-1.14.0",
    messages=[{"role":"user","content":"hello"}],
)

# MiniMax H3 Highspeed
client.chat.completions.create(
    model="minimax/h3-highspeed",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →