DeepSeek-V3.1-Terminus
This update maintains the model's original capabilities while addressing issues reported by users, including:
Params
684.5 B
Context
163,840
Downloads 30d
13 K
Likes
385
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)13 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 | f8_e4m3 | 688.6 GB | 860.6 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 160K ctx | 688.6 GB | 2,811.5 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/deepseek-v3-1-terminus
{
"hf_id": "deepseek-ai/DeepSeek-V3.1-Terminus",
"params_b": 684.53,
"context_length": 163840,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 13067,
"vram_estimates": [
{ "quant": "f8_e4m3", "gb": 860.6 }
],
"updated_at": "2026-10-19T06:00:35Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.27
input / 1M
$1.00
output / 1M
—
cached input / 1M
$1.27
1M in + 1M out
- Context window
- 163,840 tokens
- Max output
- 147,456 tokens
- Providers
- 2
- Cheapest provider
- SiliconFlow · $0.27 / $1.00
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 14.8 / 43.5 / 6.8
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✗ Prompt caching
Specifications
- Architecture
- DeepseekV3ForCausalLM
- Parameters
- 684.5 B
- Tensor type
- F8_E4M3
- Context length
- 163,840
- Vocabulary
- 129,280
- Layers / heads
- 61 / 128
- Licence
- mit
- First seen on the Hub
- 2025-09-22
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model