Deprecated on Aug 31, 2025. 10 providers still list it at the prices below.
Context
164K
Max output
164K
Serving providers
10
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
43 t/s
tokens / second
Time to first token
1.22s
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 | — | |
| GDPval (normalized)Frozen Aug 18, 2026 | 0% | default | — | |
| GPQA Diamond | 56% | default | — | |
| Humanity's Last Exam | 3% | default | — | |
| IFBench | 35% | default | — | |
| LiveCodeBench | 36% | default | — | |
| Long-Context Reasoning | 29% | default | — | |
| Omniscience | -41.6 | default | — | |
| Omniscience Accuracy | 0.3 | default | — | |
| Omniscience Non Hallucination | 0.1 | default | — | |
| SciCode | 36% | default | — | |
| Terminal Bench40 | 0 | default | — | |
| TerminalBench Hard | 7% | default | — | |
| TerminalBench v2.1 | 17% | default | — | |
| τ-bench Banking | 5% | default | — | |
| τ²-bench | 23% | default | — |
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 $1.45 per 1M tokens across 10 providers, so the dearest route costs 625% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HyperbolicCheapest | $0.20 | $0.20 | 1 | ||||||||||||||||
Standardhyperbolic/deepseek-ai/DeepSeek-V3
| |||||||||||||||||||
| DeepSeek | $0.27 | $1.10 | 1 | ||||||||||||||||
Standarddeepseek/deepseek-v3
| |||||||||||||||||||
| DeepInfra | $0.32 | $0.89 | 1 | ||||||||||||||||
Standarddeepinfra/deepseek-ai/DeepSeek-V3
| |||||||||||||||||||
| Nebius | $0.50 | $1.50 | 1 | ||||||||||||||||
Standardnebius/deepseek-ai/DeepSeek-V3
| |||||||||||||||||||
| Novita | $0.89 | $0.89 | 1 | ||||||||||||||||
Standardnovita/deepseek/deepseek_v3
| |||||||||||||||||||
| Fireworks AI | $0.90 | $0.90 | 1 | ||||||||||||||||
Standardfireworks_ai/accounts/fireworks/models/deepseek-v3
| |||||||||||||||||||
| VercelVercel reseller quote | $0.90 | $0.90 | 1 | ||||||||||||||||
Standardvercel_ai_gateway/deepseek/deepseek-v3
| |||||||||||||||||||
| Azure | $1.14 | $4.56 | 1 | ||||||||||||||||
Standardazure_ai/deepseek-v3
| |||||||||||||||||||
| Replicate is dearest at $1.45 / $1.45 | |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 78% since first tracked
Cost calculator
estimate your monthly spend on this model$56
estimated / month
Model IDs
copy the exact identifier for your platformhyperbolic/deepseek-ai/DeepSeek-V3deepseek/deepseek-v3deepinfra/deepseek-ai/DeepSeek-V3nebius/deepseek-ai/DeepSeek-V3novita/deepseek/deepseek_v3fireworks_ai/accounts/fireworks/models/deepseek-v3vercel_ai_gateway/deepseek/deepseek-v3azure_ai/deepseek-v3together_ai/deepseek-ai/DeepSeek-V3replicate/deepseek-ai/deepseek-v3
Frequently asked questions
DeepSeek V3 pricing, context and availabilityIs DeepSeek V3 still available?
DeepSeek V3 was deprecated on 2025-08-31, but 10 serving providers still list it.
How much does DeepSeek V3 cost?
DeepSeek V3 costs $0.20 per 1M input tokens from Hyperbolic, and $0.20 per 1M output tokens from Hyperbolic. Across 10 serving providers, input prices range from $0.20 to $1.45 per 1M tokens.
What is the context window of DeepSeek V3?
DeepSeek V3 accepts up to 164K tokens of context and can return up to 164K output tokens.
Which providers serve DeepSeek V3?
DeepSeek V3 is available from 10 serving providers, each with its own pricing and model ID. Hyperbolic is currently the cheapest.
What can DeepSeek V3 do?
DeepSeek V3 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 V3 0324$0.20/1M · 12 providersDeepSeek V4 Pro 0813$0.66/1M · 12 providersDeepSeek R1 Distill Llama 70B$0.20/1M · 11 providers
Popular comparisons
head-to-head pages featuring DeepSeek V3
DeepSeek V3 vs GPT-4o-mini 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