Compare

Wan 3.0 Prime (Text To Video) vs Kimi-K2.6

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
Wan 3.0 Prime (Text To Video)
alibaba/wan-3.0-prime
Kimi-K2.6
moonshot/kimi-k2.6
Provider
Alibaba
Moonshot
Family
Kimi
Modality
video
text
Context window
262,144 tok
Max output
16,384 tok
Released
2026-09-01
2026-04-20
License
Open-weight
Open-weight
Input price
$0.950 /1M
Output price
$4.00 /1M
Cache read
$0.160 /1M
Per output second
$0.050 /sec
Tools
yes
Streaming
yes
Vision
yes
JSON mode
yes
Reasoning
yes
Prompt caching
yes
Batch API
Try it
View model →
Open in playground →
Wan 3.0 Prime (Text To Video)
alibaba/wan-3.0-prime
Full spec →

Wan 3.0 Prime Text-to-Video transforms written prompts into polished videos with accelerated generation, fluid motion, strong scene fidelity, and coherent visual storytelling. Built for fast creative iteration, it brings complex ideas to life while preserving visual detail and cinematic consistency throughout each shot.

Strengths
  • Text-to-video generation
  • Cinematic motion
Use cases
AdsStoryboardsDemos
Kimi-K2.6
moonshot/kimi-k2.6
Full spec →

Kimi K2.6 is a frontier-scale open-source 1T parameter model with a 262.1k context window, multi-turn tool calling, vision inputs, and structured outputs for agentic workloads.

Strengths
  • Frontier-scale 1T parameters, open-weight
  • ~10× cheaper than Opus
  • Multi-turn tool calling + vision
Use cases
Code agentsLong-document reasoningCost-conscious production

Benchmarks

Wan 3.0 Prime (Text To Video)
Kimi-K2.6
HumanEval
92.7
SWE-Bench
68.2

Source: each provider's published benchmarks. Higher is better. Run an eval to compare on your own data.

Compare with another

Kimi-K2.6 vs Kimi-K2.7-Code
moonshot/kimi-k2.6 · moonshot/kimi-k2.7-code
Claude Fable 5.1 vs Wan 3.0 Prime (Text To Video)
anthropic/claude-fable-5.1 · alibaba/wan-3.0-prime
Claude Fable 5.1 vs Kimi-K2.6
anthropic/claude-fable-5.1 · moonshot/kimi-k2.6
Gemini 3.8 Flash vs Wan 3.0 Prime (Text To Video)
google/gemini-3.8-flash · alibaba/wan-3.0-prime
Gemini 3.8 Flash vs Kimi-K2.6
google/gemini-3.8-flash · moonshot/kimi-k2.6
Claude Opus 5 vs Wan 3.0 Prime (Text To Video)
anthropic/claude-opus-5 · alibaba/wan-3.0-prime
Claude Opus 5 vs Kimi-K2.6
anthropic/claude-opus-5 · moonshot/kimi-k2.6
Grok 4.6 vs Wan 3.0 Prime (Text To Video)
xai/grok-4.6 · alibaba/wan-3.0-prime
Grok 4.6 vs Kimi-K2.6
xai/grok-4.6 · moonshot/kimi-k2.6
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-...",
)

# Wan 3.0 Prime (Text To Video)
client.chat.completions.create(
    model="alibaba/wan-3.0-prime",
    messages=[{"role":"user","content":"hello"}],
)

# Kimi-K2.6
client.chat.completions.create(
    model="moonshot/kimi-k2.6",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →