Deprecated on Jul 13, 2026. 12 providers still list it at the prices below.
DeepSeek V3 0324Deprecated
Context
164K
Max output
164K
Serving providers
12
Cheapest input
$0.20 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
84 t/s
tokens / second
Time to first token
0.71s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Automation Bench | 0.0 | default | — | |||||||||||||||||
| CritPt | 0% | default | — | |||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 126.9 | default | — | |||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 324.9 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 65% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 5% | default | — | |||||||||||||||||
| IFBench | 41% | default | — | |||||||||||||||||
| LiveCodeBench | 41% | default | — | |||||||||||||||||
| Long-Context Reasoning | 41% | default | — | |||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 82% | default | — | |||||||||||||||||
| Omniscience | -40.7 | default | — | |||||||||||||||||
| Omniscience Accuracy | 0.2 | default | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.1 | default | — | |||||||||||||||||
| SciCode | 39% | default | — | |||||||||||||||||
| Terminal Bench40 | 0 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 15% | default | — | |||||||||||||||||
| TerminalBench v2.1 | 14% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 5% | default | — | |||||||||||||||||
| τ²-bench | 47% | default | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.20 to $3.00 per 1M tokens across 12 providers, so the dearest route costs 1400% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Lambda AICheapest | $0.20 | $0.60 | 1 | |||||||||||||
Standardlambda_ai/deepseek-v3-0324
| ||||||||||||||||
| DeepInfra | $0.24 | $0.90 | 1 | |||||||||||||
Standarddeepinfra/deepseek-ai/DeepSeek-V3-0324
| ||||||||||||||||
| Novita | $0.27 | $1.12 | 1 | |||||||||||||
Standardnovita/deepseek/deepseek-v3-0324
| ||||||||||||||||
| Gmi | $0.28 | $0.88 | 1 | |||||||||||||
Standardgmi/deepseek-ai/DeepSeek-V3-0324
| ||||||||||||||||
| Hyperbolic | $0.40 | $0.40 | 1 | |||||||||||||
Standardhyperbolic/deepseek-ai/DeepSeek-V3-0324
| ||||||||||||||||
| Nebius | $0.50 | $1.50 | 1 | |||||||||||||
Standardnebius/deepseek-ai/DeepSeek-V3-0324
| ||||||||||||||||
| Baseten | $0.77 | $0.77 | 1 | |||||||||||||
Standardbaseten/deepseek-ai/DeepSeek-V3-0324
| ||||||||||||||||
| Fireworks AI | $0.90 | $0.90 | 1 | |||||||||||||
Standardfireworks_ai/accounts/fireworks/models/deepseek-v3-0324
| ||||||||||||||||
| SambaNova is dearest at $3.00 / $4.50 | ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 82% since first tracked
Cost calculator
estimate your monthly spend on this model$88
estimated / month
Model IDs
copy the exact identifier for your platformlambda_ai/deepseek-v3-0324deepinfra/deepseek-ai/DeepSeek-V3-0324novita/deepseek/deepseek-v3-0324gmi/deepseek-ai/DeepSeek-V3-0324hyperbolic/deepseek-ai/DeepSeek-V3-0324nebius/deepseek-ai/DeepSeek-V3-0324baseten/deepseek-ai/DeepSeek-V3-0324fireworks_ai/accounts/fireworks/models/deepseek-v3-0324azure_ai/deepseek-v3-0324wandb/deepseek-ai/DeepSeek-V3-0324crusoe/deepseek-ai/DeepSeek-V3-0324sambanova/DeepSeek-V3-0324
Frequently asked questions
DeepSeek V3 0324 pricing, context and availabilityIs DeepSeek V3 0324 still available?
DeepSeek V3 0324 was deprecated on 2026-07-13, but 12 serving providers still list it.
How much does DeepSeek V3 0324 cost?
DeepSeek V3 0324 costs $0.20 per 1M input tokens from Lambda AI, and $0.40 per 1M output tokens from Hyperbolic. Across 12 serving providers, input prices range from $0.20 to $3.00 per 1M tokens.
What is the context window of DeepSeek V3 0324?
DeepSeek V3 0324 accepts up to 164K tokens of context and can return up to 164K output tokens.
Which providers serve DeepSeek V3 0324?
DeepSeek V3 0324 is available from 12 serving providers, each with its own pricing and model ID. Lambda AI is currently the cheapest.
What can DeepSeek V3 0324 do?
DeepSeek V3 0324 supports tool use, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineupDeepSeek V4 Flash 0423$0.09/1M · 18 providersDeepSeek V4 Flash 0731$0.016/1M · 16 providersDeepSeek V4 Pro 0423$0.435/1M · 16 providersR1$0.40/1M · 14 providersDeepSeek V4.1 Flash$0.01/1M · 12 providersDeepSeek V4 Pro 0813$0.66/1M · 12 providersDeepSeek R1 Distill Llama 70B$0.20/1M · 11 providersDeepSeek V3.1$0.25/1M · 11 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI