DeepSeek-V3.1
deepseek/v3제공: DeepSeek · 패밀리: deepseek · 출시 2024-12-26 · 지식 컷오프: 2024-07
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
기능
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding84
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)4/20
- Provider availability10/10
Agents100
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output98
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume18/20
Cost efficiency60
- Headline price (log-scaled)60/95
- Has prompt-cache pricing0/5
Long context51
- Context window (100K → 2M)41/90
- Has published price for full window10/10
Production-readiness96
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $1.75 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $3.50 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $1.00 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $3.00 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $3.60 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
가격 상세
추천 가격 제공자: siliconflow-cn · Pro/deepseek-ai/DeepSeek-V3
가장 저렴한 제공자: iflowcn · Unknown 입력 + Unknown 출력
13곳 제공사에서 이용 가능
| 제공자 | 제공자 모델 ID | 입력 / 1M | 출력 / 1M | 컨텍스트 | 출시일 |
|---|---|---|---|---|---|
| Amazon Bedrock amazon-bedrock | deepseek.v3-v1:0 | $0.580 | $1.68 | 164K | 2025-09-18 |
| Vercel AI Gateway vercel | deepseek/deepseek-v3 | $0.770 | $0.770 | 164K | 2024-12-26 |
| Together AI togetherai | deepseek-ai/DeepSeek-V3 | $1.25 | $1.25 | 131K | 2025-01-20 |
| SiliconFlow (China) siliconflow-cn | Pro/deepseek-ai/DeepSeek-V3 | $0.250 | $1.00 | 164K | 2024-12-26 |
| SiliconFlow (China) siliconflow-cn | deepseek-ai/DeepSeek-V3 | $0.250 | $1.00 | 164K | 2024-12-26 |
| Alibaba (China) alibaba-cn | deepseek-v3 | $0.287 | $1.15 | 66K | 2024-12-01 |
| iFlow iflowcn | deepseek-v3 | Unknown | Unknown | 128K | 2024-12-26 |
| Qiniu qiniu-ai | deepseek-v3 | Unknown | Unknown | 128K | 2025-08-13 |
| Helicone helicone | deepseek-v3 | $0.560 | $1.68 | 128K | 2024-12-26 |
| Synthetic synthetic | hf:deepseek-ai/DeepSeek-V3 | $1.25 | $1.25 | 128K | 2025-01-20 |
| DigitalOcean digitalocean | deepseek-v3 | Unknown | Unknown | 164K | 2024-12-26 |
| SiliconFlow siliconflow | deepseek-ai/DeepSeek-V3 | $0.250 | $1.00 | 164K | 2024-12-26 |
| D.Run (China) drun | public/deepseek-v3 | $0.280 | $1.10 | 131K | 2024-12-26 |
제공자 간 데이터 불일치
- context_window varies: 128000, 131072, 163840, 164000, 65536
- release_date varies (span 291d): 2024-12-01, 2024-12-26, 2025-01-20, 2025-08-13, 2025-09-18
제공자별로 이 모델의 값이 다릅니다. 위의 핵심 정보는 대표 제공자 기준이며, 제공자별 상세는 표를 참고하세요.
Frequently asked questions
How much does DeepSeek-V3.1 cost?
DeepSeek-V3.1 costs $0.250 per 1M input tokens and $1.00 per 1M output tokens, sourced from siliconflow-cn. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of DeepSeek-V3.1?
DeepSeek-V3.1 has a context window of 164K tokens, with a max output of 82K tokens per reply. This is the total combined size of prompt + completion.
Does DeepSeek-V3.1 support tool calling?
Yes. DeepSeek-V3.1 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does DeepSeek-V3.1 support structured output / JSON mode?
Yes. DeepSeek-V3.1 supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can DeepSeek-V3.1 accept image input?
No. DeepSeek-V3.1 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is DeepSeek-V3.1 open-weight?
Yes. DeepSeek-V3.1's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to DeepSeek-V3.1?
If DeepSeek-V3.1 doesn't fit, consider DeepSeek-V3.2, DeepSeek V4 Pro, DeepSeek-R1-0528. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More DeepSeek models
- DeepSeek-V3.2$0.26 in / $0.38 out
- DeepSeek V4 Pro$1.74 in / $3.48 out
- DeepSeek-R1-0528$0.40 in / $1.70 out
- DeepSeek-R1$0.40 in / $1.70 out
- DeepSeek-V3.1$0.20 in / $0.70 out
Capability lists this model is in
마지막 업데이트:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.