Kimi-K2-Thinking
Kimi K2 Thinking is the latest, most capable version of open-source thinking model. Starting with Kimi K2, we built it as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks by dramatically scaling multi-step reasoning depth and maintaining stable tool-use across 200–300 sequential calls. At the sam...
Params
1,026.4 B
Context
262,144
Downloads 30d
48 K
Likes
1,731
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)48 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 | i32 | 594.2 GB | 808.1 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 594.2 GB | 5,580.9 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/kimi-k2-thinking
{
"hf_id": "moonshotai/Kimi-K2-Thinking",
"params_b": 1026.41,
"context_length": 262144,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 47623,
"vram_estimates": [
{ "quant": "i32", "gb": 808.1 }
],
"updated_at": "2026-10-19T06:03:09Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.60
input / 1M
$2.50
output / 1M
$0.15
cached input / 1M
$3.10
1M in + 1M out
- Context window
- 262,144 tokens
- Max output
- 98,304 tokens
- Providers
- 2
- Cheapest provider
- Google · $0.60 / $2.50
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 22 / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- DeepseekV3ForCausalLM
- Parameters
- 1,026.4 B
- Tensor type
- I32
- Context length
- 262,144
- Vocabulary
- 163,840
- Layers / heads
- 61 / 64
- Licence
- other
- First seen on the Hub
- 2025-11-04
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model