DeepSeek V3
Released
2024-12-26
Last refreshed
2026-05-22
Status
Researched 46d ago
Open SourceCodingAgentsClassificationJSON / Tool use
DeepSeek V3 is worth evaluating for coding, agents, and classification when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, agents, and classification
- Workloads that can use a 64k context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
Specifications
- Family
- DeepSeek V3
- Released
- 2024-12-26
- Context
- 64k
- Parameters
- 671B
- Architecture
- Mixture of Experts
- Knowledge cutoff
- 2024-04
- Specialization
- general
- Training
- finetuned
Created by
Pricing
Output / 1M
$0.280
Input / 1M
$0.140
Cheapest of 13 routes · DeepSeek Platform
About
DeepSeek V3: Latest flagship model. 685B total with MoE. 128K context. Open-source.
DeepSeek V3 is an open-source model. The structured metadata tracks a 64k-token context window, function calling, tool use, and structured outputs. This page tracks provider routes through DeepInfra, Fireworks AI, DeepSeek Platform, and 10 more, with the cheapest tracked route listed at $0.1 input and $0.3 output per 1M tokens. Headline tracked benchmarks include HellaSwag 95.7, HumanEval 85.5, and Massive Multitask Language Understanding 88.5.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ B4 relevant benchmarks in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Classification
Q/$ B3 relevant benchmarks in the decision map.
Provider price ladder
Compare all 13Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| DeepSeek Platform | $0.140 | $0.280 | Serverless |
| Bitdeer AI | $0.100 | $0.300 | Serverless |
| OpenRouter | $0.252 | $0.378 | Serverless |
| SiliconFlow | $0.150 | $0.500 | Serverless |
Capabilities
Function CallingTool UseStructured Outputs
Benchmark peer barsfor Coding
Benchmark scores(9)
Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
| Benchmark | Score | Version | Source |
|---|---|---|---|
| HellaSwag | 95.7 | 10-shot | https://arxiv.org/abs/2412.19437 |
| HumanEval | 85.5 | pass@1 | https://arxiv.org/abs/2412.19437 |
| Massive Multitask Language Understanding | 88.5 | 5-shot | https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard |
| LiveCodeBench | 49.6 | 2026-04 | https://livecodebench.github.io/performances_generation.json |
| Aider Polyglot | 48.4 | 2026-04 | https://aider.chat/docs/leaderboards |
| BigCodeBench | 50.0 | 2025-01 (Instruct Pass@1) | https://bigcode-bench.github.io/results.json |
| Chatbot Arena | 1302.0 | — | https://lmarena.ai |
| MMLU PRO | 75.9 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
| Mostly Basic Programming Problems+ | 76.0 | — | https://evalplus.github.io/leaderboard.html |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(10)
Best LLMs for Code GenerationListedBest AI Agents & Agentic ModelsListedBest LLMs for ClassificationListedBest Open Source LLMsListedBest LLMs for Function Calling & Tool UseListedCheapest LLM APIs You Can Call Right NowListedBest Mainstream LLM APIs, RankedListedBest LLMs for EnterpriseListedBest Free LLMs You Can Use Right NowListedBest LLMs for WritingListed
Comparison and alternatives
Browse all comparisons →DeepSeek V3 vs GPT-4o Mini (07-18)DeepSeek V3 vs GPT-4o (08-06)DeepSeek V3 vs Claude 3.5 SonnetDeepSeek V3 vs Gemini 2.5 FlashDeepSeek V3 vs Llama 4 Maverick 17B Instruct FP8DeepSeek V3 vs DeepSeek R1DeepSeek V3 vs Composer 2.5DeepSeek V3 vs Step 3.7 FlashDeepSeek V3 vs Grok 4DeepSeek V3 vs Kimi K2.6DeepSeek V3 vs Tencent Hy3 PreviewDeepSeek V3 vs Qwen2.5-72BDeepSeek V3 vs GLM-5.1DeepSeek V3 vs Qwen3-MaxDeepSeek V3 vs DeepSeek V4 ProDeepSeek V3 vs Xiaomi MiMo-V2.5
Show all 79 popular comparisonssorted by 7-day search impressions
DeepSeek V3 vs Kimi K2.5224DeepSeek V3 vs Kimi K2 Thinking219DeepSeek V3 vs DeepSeek R1 0528217DeepSeek V3 vs StepFun Step-2213DeepSeek V3 vs GLM-5205DeepSeek V3 vs Claude Sonnet 4.6201DeepSeek V3 vs Ling-2.6-1T196DeepSeek V3 vs Llama 3.1 405B170DeepSeek V3 vs Claude Sonnet 4.5162DeepSeek V3 vs Tencent Hunyuan Turbo S158DeepSeek V3 vs Xiaomi MiMo-V2.5-TTS-Series158DeepSeek V3 vs Qwen3.6-27B139DeepSeek V3 vs Step 3.5 Flash132DeepSeek V3 vs Qwen3.6-35B-A3B129DeepSeek V3 vs Kimi K2124DeepSeek V3 vs Qwen2.5-72B-Instruct123DeepSeek V3 vs Qwen2.5-7B-Instruct108DeepSeek V3 vs Grok 3 Mini95DeepSeek V3 vs Qwen2.5-72B87DeepSeek V3 vs Llama 3.1 405B Instruct87DeepSeek V3 vs Llama 3 70B Instruct86DeepSeek V3 vs gpt-oss-120b86DeepSeek V3 vs Gemma 4 31B IT85DeepSeek V3 vs Mistral Large 281DeepSeek V3 vs Trinity-Large-Thinking81DeepSeek V3 vs Qwen3-235B-A22B77DeepSeek V3 vs Qwen3.5-9B72DeepSeek V3 vs Grok Code Fast 170DeepSeek V3 vs GPT-5.563DeepSeek V3 vs Qwen3.5-27B63DeepSeek V3 vs Llama 3.1 70B Instruct60DeepSeek V3 vs GPT-5.259DeepSeek V3 vs Gemma 4 26B A4B IT58DeepSeek V3 vs Qwen3.5-122B-A10B57DeepSeek V3 vs o355DeepSeek V3 vs Claude Opus 4.753DeepSeek V3 vs GLM-5 Turbo53DeepSeek V3 vs o3 Mini53DeepSeek V3 vs gpt-oss-20b52DeepSeek V3 vs Qwen2.5-32B-Instruct49DeepSeek V3 vs Claude Opus 4.649DeepSeek V3 vs Mixtral 8x7B46DeepSeek V3 vs Mistral Small 336DeepSeek V3 vs Grok-336DeepSeek V3 vs GPT-5.435DeepSeek V3 vs Claude 3.7 Sonnet34DeepSeek V3 vs DeepSeek V3.132DeepSeek V3 vs GPT-5.5 Pro28DeepSeek V3 vs GPT-5.4 Mini28DeepSeek V3 vs Gemini 2.5 Pro26DeepSeek V3 vs GPT-4o-mini Search Preview25DeepSeek V3 vs Claude Opus 4.522DeepSeek V3 vs Gemini 2.5 Flash Live API21DeepSeek V3 vs Llama 3.2 1B Instruct14DeepSeek V3 vs GLM-5V-Turbo14DeepSeek V3 vs GPT-4 Turbo14DeepSeek V3 vs DeepSeek R1 Distill Llama 70B13DeepSeek V3 vs Composer 213DeepSeek V3 vs Qwen3.5-397B-A17B12DeepSeek V3 vs Together AI - Gemma 3n-e4B12DeepSeek V3 vs Together AI - Llama 3 8B Lite11DeepSeek V3 vs o3 Deep Research11DeepSeek V3 vs Qwen3.6 Max Preview11DeepSeek V3 vs Qwen3.5-35B-A3B10DeepSeek V3 vs Gemma 7B Instruct10DeepSeek V3 vs DeepSeek R1 Lite10DeepSeek V3 vs Gemini 2.5 Pro Computer Use Preview9DeepSeek V3 vs Phi-3 Mini 4k9DeepSeek V3 vs Kimi K2 Instruct9DeepSeek V3 vs GPT-4 Vision Preview8DeepSeek V3 vs GLM-5 9B5DeepSeek V3 vs Llama 3 8B Instruct5DeepSeek V3 vs Mistral Nemotron5DeepSeek V3 vs Mixtral 8x22B Instruct v0.35DeepSeek V3 vs GPT-5.4-Cyber4DeepSeek V3 vs Phi-4 Mini Flash Reasoning3DeepSeek V3 vs Qwen2-7B-Instruct1DeepSeek V3 vs DeepSeek V4 Flash0DeepSeek V3 vs Llama 2 13B Chat0