DeepSeek V3 (2506) — DeepSeek | Modeldex

DeepSeek V3 (2506)

Active

Latest version of DeepSeek V3.

Updated 4 days agoStructured data from Modeldex catalog

AgenticOpen source

API release

Dec 1, 2025(5 months ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

History

DeepSeek V3 (2506) became available via the DeepSeek API on 2025-12-01.

Training & availability

Weights are publicly available, making this an open-weight model suitable for on-prem deployment and fine-tuning.

Capabilities

Context window: 131K tokens.
Max output: 8K tokens.
Input modalities: text.

Recommended for: agentic, open-source.

Limitations

Text-only — cannot process images, audio, or video inputs.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="deepseek/deepseek-v3-2",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Popularity

Signals from open-source communities — not a quality measure, but useful for gauging adoption among developers.

🤗

HuggingFace downloads

10.2M/ month

HuggingFace likes

1.4K

Benchmarks

Benchmark	Score	Source
SWE-bench VerifiedCoding	42% resolved	Third-party Papers With Code

Integrations & tooling support

Tool calling: Supported
Structured outputs: Not supported

Price vs quality

Below-average benchmarks

Performance trails frontier models. Pricing not publicly available — check the provider.