DeepSeekOpen SourceCodingReasoning
DeepSeek V3
DeepSeek’s MoE general model — strong open-weight performance on coding and knowledge tasks with competitive API pricing.
Tool calling · Coding
Last reviewed: 24 July 2026
Overview
DeepSeek’s MoE general model — strong open-weight performance on coding and knowledge tasks with competitive API pricing.
Capabilities
- Vision: No
- Audio input: No
- Tool calling: Yes
- Thinking: No
- MCP: No
- Coding: Yes
- Structured output: Yes
Technical specifications
- Provider
- DeepSeek
- License
- Model License (open weights)
- Context window
- 128K
- Parameters
- MoE (671B total / activated subset)
- Architecture
- Mixture-of-Experts
- Release
- 2024
- Modalities
- Text
- Vision
- No
- Audio input
- No
- Tool calling
- Yes
- Thinking
- No
- MCP
- No
- Open weights
- Yes
- API
- Yes
- Pricing (input)
- DeepSeek API (competitive)
- Pricing (output)
- DeepSeek API (competitive)
Supported modalities
Text
Context window
128K (128,000 tokens)
Pricing
Input: DeepSeek API (competitive)
Output: DeepSeek API (competitive)
Also self-hostable via open weights where license allows.
Availability
API: Yes
Chat UI: Yes
Open weights: Yes
API + Hugging Face / community serving stacks.
Use cases
- Cost-efficient coding assistants
- Self-hosted enterprise chat
- Batch document processing
- Open-weight evaluation baselines
Strengths
- Strong open-weight capability / price ratio
- Good coding performance
- Self-hosting option
Limitations
- Weaker native multimodality than frontier VLMs
- Ecosystem / tooling less mature than OpenAI/Anthropic
Related guides
Related benchmarks
Related research
- DeepSeek-V3 technical report
Original Paper
Related GitHub
Related tools
Related rankings
Companies
Explore more models
- DeepSeek R1DeepSeekDeepSeek’s reasoning-focused model trained with reinforcement learning for multi-step math, science, and coding problem solving.
- DeepSeek V4DeepSeekDeepSeek’s V4 generation — live Flash is V4.1-Flash-1017 (API id deepseek-flash, upgraded 2026-10-17): Causal Encoder–Decoder MoE, 552B backbone (8B active prefill / 16B decode), native image+text, and 1M context. API id and prices are unchanged from the 2026-09-10 Flash list. MIT weights on Hugging Face. Legacy deepseek-v4-flash and deepseek-v4-flash-vision-exp aliases temporarily route here. deepseek-v4-pro still serves V4-Pro-0813 after 2026-09-14 at unchanged Pro rates (DeepSeek withdrew the planned Flash reroute).
- Beam 1.0ReflectionReflection’s Beam 1.0 — Apache-2.0 text-only sparse MoE (501B total, 23B active, 1M context) for agentic coding and reasoning. Weights shipped 2026-10-16 with day-0 support in Hugging Face Transformers, vLLM, and SGLang. This is not the beam.cloud GPU tool.
- Llama 4MetaMeta’s Llama 4 family — open-weight multimodal models designed for research and commercial use under Meta’s community license.
- PhiMicrosoftMicrosoft’s Phi family of small language models — high capability per parameter for on-device, edge, and cost-sensitive deployments.
- Sarvam 105BSarvamSarvam’s flagship open-weight reasoning model. A Mixture-of-Experts transformer with 10.3B active parameters, trained from scratch in India, and used to power the Indus assistant.