Kimi-K3.1-Pro
Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series. With a 1-million-token context window, Kimi K3.1 Pro delivers substantial improvements in coding, 3D creation, financial research, factual accuracy, and o...
Params
2,780.1 B
Context
—
Downloads 30d
28 K
Likes
1,805
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)28 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | u8 | 1,561.3 GB | 2,134.9 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-11-10$2.00
input / 1M
$10.00
output / 1M
$0.20
cached input / 1M
$12.00
1M in + 1M out
- Context window
- 1,048,576 tokens
- Max output
- 943,718 tokens
- Providers
- 17
- Cheapest provider
- Relace · $0.39 / $7.92
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 46.5 / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- KimiK31ForConditionalGeneration
- Parameters
- 2,780.1 B
- Tensor type
- U8
- Licence
- other
- First seen on the Hub
- 2026-11-02
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-06
Compare with any image-text-to-text model