Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | moonshotaiMoonshotAI: Kimi K3 (batch)Remove × | fal-aiMarigold V2 DepthRemove × |
|---|---|---|
| What’s different | Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at... | Estimate depth from a single image with Marigold V2, a diffusion-based depth model built on Qwen-Image-Edit, returning a colorized depth map. |
| Date | Jul 16, 2026Listed | Oct 2, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $2.28 in / $11.40 out/ 1M tokensDeepInfra · via OpenRouter · all routes ↗deepinfra/bf16 · quantization=bf16 | See provider quotes |
| Provider endpoints | 2 endpoints → | 0 endpoints → |
Specifications | ||
| Context window | 1M | — |
| Max output | 16.4K | — |
| Parameters | — | — |
| Tool calling | Supported | Not reported |
| Structured output | Supported | Not reported |
| Image input | Supported | Not reported |
| Video input | Supported | Not reported |
| Reasoning | Supported | Not reported |
| Prompt caching | Supported | Not reported |
| Open weights | Supported | Not reported |