DeepSeek V3 0324 pricing & benchmarks
DeepSeek V3 0324 is available from DeepSeek at $0.290 per million input tokens and $1.14 per million output tokens ($0.502 blended at 3:1). It accepts up to 163,840 tokens of context. DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
Pricing
Per million tokens · OpenRouter
Input$0.290
Output$1.14
Blended (3:1)$0.502
Specification
deepseek/deepseek-chat-v3-0324
Context window164K
Max output115K
ReleasedMar 2025
LicenceOpen weights
Modalitiesin:text, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 67.6% ±2.7 | — | 2025-04-01 | Independently run · Epoch AI |
| OTIS Mock AIME | 37.8% ±6.2 | — | 2025-04-01 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| Qwen3.7 Flash | Alibaba | $0.055 (−89%) | 82.3% | Compare → |
| Qwen3.5-Flash | Alibaba | $0.114 (−77%) | 82.3% | Compare → |
| GPT-5 Nano | OpenAI | $0.138 (−73%) | 69.4% | Compare → |
| Gemma 4 31B | $0.250 (−50%) | 75.8% | Compare → | |
| gpt-oss-120b | OpenAI | $0.262 (−48%) | 75.8% | Compare → |
Where to run DeepSeek V3 0324
2 hosts · 1.1× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| SiliconFlow | $0.438 | $0.250 / $1.00 | 164K | fp8 | 98.8% |
| GMICloud ⚠ 128K context, not 164K |
$0.502 | $0.290 / $1.14 | 128K | fp8 | 99.8% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare DeepSeek V3 0324
FAQ
How much does DeepSeek V3 0324 cost?
DeepSeek V3 0324 costs $0.290 per million input tokens and $1.14 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.502 per million tokens.
What is DeepSeek V3 0324's context window?
DeepSeek V3 0324 accepts up to 163,840 tokens of context, and can generate up to 115,200 output tokens.
How good is DeepSeek V3 0324 on benchmarks?
DeepSeek V3 0324 scores 67.6% on GPQA Diamond, independently run and published by Epoch AI. 2 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as DeepSeek V3 0324?
Yes — 5 models in our catalogue cost less per token than DeepSeek V3 0324 and score at least as high on the same benchmark. The cheapest is Qwen3.7 Flash at $0.055 per million tokens blended.