Costs less than most peers
Maker's price: $0.4775 blended / 1M, cheaper than 7 of 8 priced peers.
DeepSeek · Chat
Newer version: DeepSeek V4. Our catalogue has no release date for DeepSeek V4. We compared the version names in our catalogue.
High-performance open-source MoE language model optimized for reasoning, coding, and efficient text generation
Evidence and sources
Maker's price: $0.4775 blended / 1M, cheaper than 7 of 8 priced peers.
The maker has already deprecated this model (13 Jul 2026).
The weights aren't public, so you can't run it yourself.
Supported operations and provider-stated features
| 66K | $0.27cache read $0.07 | $1.10 | — | — | |
| 33K | $0.20 | $0.20 | — | — | |
| 131K | $0.20 | $0.60 | — | — | |
| 75K | $0.20 | $0.80 | — | — | |
| 164K | $0.24cache read $0.135 | $0.90 | — | — | |
| 164K | $0.24 | $0.90 | — | — | |
| 164K | $0.24cache read $0.135 | $0.90 | — | — | |
| 164K | $0.25 | $1.00 | — | — | |
| 164K | $0.25 | $1.00 | — | — | |
| —Not published by the provider | $0.2625 | $1.05 | 26.6 | 4,067ms |
Showing 10 of 62: the maker's own listing first, then the cheapest per 1M input tokens from each provider.
Also sold by 302ai, Aihubmix, Amazon Web Services, Anonrouter, Baseten, Crusoe, Drun, Fastrouter, Fireworks AI, Flowdot, Gmicloud, Jiekou, Meganova, Merge Gateway, Microsoft Azure, Nebius AI Studio, Netmind, Novita AI, Qiniu, Replicate, Requesty, Siliconflow Cn, Simplismart, Streamlake, Tencent Lkeap, Together AI, Vercel, Vercel AI Gateway.
4 listings without a price are hidden.
Named effort levels run from lowest to highest. Select a result to see its source details.
| Benchmark | Score |
|---|---|
| Safety: BBQ - BBQ accuracy | |
| AIR-Bench: AIRBench 2024 - #1: Confidentiality | |
| AIR-Bench: AIRBench 2024 - #2: Integrity | |
| AIR-Bench: AIRBench 2024 - #3: Availability |
| Benchmark | not stated | 0324 |
|---|---|---|
| Arena ELO | ||
| Chinese | ||
| Creative Writing | ||
| English |
| Benchmark | Score |
|---|---|
| FictionLiveBench 0 | |
| 1k | |
| 2k | |
| 4k |
| Benchmark | Score |
|---|---|
| 8k | |
| 16k | |
| 32k | |
| 60k | |
| FictionLiveBench 400 |
| Benchmark | Score |
|---|---|
| Factual | |
| Cloud Skills and Knowledge (CSK) | |
| Conceptual | |
| Fundamental IT Skills (FIS) |
| Benchmark | Score |
|---|---|
| Networking Knowledge (NK) | |
| Operating Systems (OS) | |
| Overall | |
| Procedural | |
| Programming Skills and Knowledge (PSK) | |
| Security Skills and Knowledge (SSK) | |
| Web Knowledge (WK) |
| Benchmark | deepseek-ai/DeepSeek-V3-0324 |
|---|---|
| ALT_バイアス | |
| ALT_倫理・道徳 | |
| ALT_制御性 | |
| ALT_堅牢性 |
Data credits: Aider LLM Leaderboards (Aider-AI), Apache-2.0 (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · LMArena, CC BY 4.0 (licence) · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · CSEBenchmark (Wang et al., IEEE S&P 2025). Copyright (c) 2024 NASP. MIT License. (licence) · CyberGym leaderboard (Wang, Shi, He, Cai, Zhang, Song; UC Berkeley), ICLR 2026. Results evaluated and submitted by the listed teams. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only. · DABstep (Adyen), CC BY 4.0 (licence) · The Fin AI. Published FinBen result summaries and Open Greek Financial LLM Leaderboard aggregates. Results licence not separately stated; fractional FinBen success metrics converted to percentages. · Galileo Agent Leaderboard, Apache-2.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · HAL (Princeton) — cite the HAL paper · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · Stanford HELM (Stanford CRFM), Apache-2.0 (licence) · JMLE2026-Bench and IgakuQA119 by Naoto Iwase; results licence not stated (code MIT, question data CC BY 4.0). · Vasselli, Martínez Peguero, Hudi, Sakajo and Watanabe. Measuring Linguistic Competence of LLMs on Indigenous Languages of the Americas. EACL 2026, ©2026 ACL, CC BY 4.0. Numeric/protocol extract from Tables 1–4; random reference rows omitted. (licence) · LiveMCPBench leaderboard, ICIP-CAS (Mo et al., 2025). Sheet linked from the Apache-2.0 project README; sheet licence not separately stated. · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · MMLU-ProX: Xuan et al., arXiv:2503.10497. Public project-page results; no results licence stated. · Multi-SWE-bench experiments (multi-swe-bench/experiments), Apache-2.0; resolved-rate fractions converted to percentages (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · pfgen-bench, Preferred Networks. Apache-2.0 except LLM-generated outputs; aggregate scores only. (licence) · Phare (Giskard), CC BY 4.0 (licence) · Trishul Lab, PutnamBench public submitted results. Model identities and scaffold budgets preserved; result licence unstated. · SeaExam and SeaBench leaderboard, SeaLLMs (DAMO-NLP-SG). Published leaderboard scores; results licence not stated. · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · SWE-bench-Live (Microsoft and contributors), swe-bench-live.github.io. Resolve rates computed from the published report counts. · Toloka, U-MATH and mu-MATH public leaderboard. MIT Space; generated solution outputs retain underlying model terms and are not ingested. (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Vectara Hallucination Leaderboard, Apache-2.0 (licence) · WebWalkerQA (Alibaba NLP), Apache-2.0 (licence)
youtube.com
youtube.com
Also known as: accounts/fireworks/models/deepseek-v3, azure_ai/deepseek-v3-0324, baseten/deepseek-ai/deepseek-v3-0324, bedrock/ap-northeast-1/deepseek.v3-v1:0, bedrock/ap-south-1/deepseek.v3-v1:0, bedrock/ap-southeast-3/deepseek.v3-v1:0, bedrock/eu-west-2/deepseek.v3-v1:0, cc-deepseek-v3, crusoe/deepseek-ai/deepseek-v3-0324, deepinfra/deepseek-ai/deepseek-v3, deepinfra/deepseek-ai/deepseek-v3-0324, deepseek-ai/deepseek-v3, deepseek-ai/deepseek-v3-0324, deepseek-v3-0324, deepseek-v3-20250324, deepseek-v3-250324, deepseek-v3-aliyun, deepseek-v3-baidu, deepseek-v3-huoshan, deepseek.v3-v1:0, deepseek/deepseek-v3, deepseek/deepseek-v3-0324, deepseek/deepseek_v3, fireworks_ai/accounts/fireworks/models/deepseek-v3, fireworks_ai/accounts/fireworks/models/deepseek-v3-0324, gmi/deepseek-ai/deepseek-v3-0324, hyperbolic/deepseek-ai/deepseek-v3, hyperbolic/deepseek-ai/deepseek-v3-0324, lambda_ai/deepseek-v3-0324, nebius/deepseek-ai/deepseek-v3, nebius/deepseek-ai/deepseek-v3-0324, novita/deepseek/deepseek-v3-0324, novita/deepseek/deepseek_v3, pro/deepseek-ai/deepseek-v3, public/deepseek-v3, replicate/deepseek-ai/deepseek-v3, siliconflow/deepseek-v3-0324, sophnet/deepseek-v3, sophnet/deepseek-v3-0324, sophnet/deepseek-v3-fast, streamlake/deepseek-v3, together_ai/deepseek-ai/deepseek-v3, vercel_ai_gateway/deepseek/deepseek-v3
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works