DeepSeek V3.1 API Benchmarks, Pricing & Provider Data
Compare DeepSeek V3.1 with another model
Choose a model to open its comparison page.
DeepSeek V3.1 benchmark, API pricing, and provider data cover undefined API provider} other undefined API providers}}, with prices starting at $0.010/request. DeepSeek V3.1 free API options are available from undefined provider} other undefined providers}}. The page also shows measured API speed and first-token latency.
DeepSeek V3.1 is an open-weights style frontier model from DeepSeek with strong math, coding, and Chinese-English bilingual reasoning.
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 6 / 8
- Methodology
- V3.0
#1Math53Provisional1/4 Measured dimensions
#2Coding50.4Provisional1/4 Measured dimensions
#3Reasoning48.4RatedGlobal rank #483/4 Measured dimensions
#4Instruction following42.8Provisional1/4 Measured dimensions
#5Knowledge40.7Provisional1/4 Measured dimensions
#6Agents40.6Provisional1/4 Measured dimensions
Specifications
Rankings
Excels at
Falls behind in
Detailed scores
Updated: Sep 13, 2026Pricing
undefined metric} other undefined metrics}}
Input price$0.570/M#94 / 186Output price$1.68/M#71 / 186
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Score40.680% interval24.5–56.61/4 Measured dimensionsΤ²-bench results37.4#70 / 82
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Score50.480% interval36.5–64.31/4 Measured dimensionsLiveCodeBench57.7%#46 / 115AA-SciCode39.1#79 / 113
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score48.4#4880% interval39.7–57.03/4 Measured dimensionsMMLU-Pro85.1%#30 / 129GPQA73.5%#132 / 218
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score40.780% interval24.7–56.71/4 Measured dimensionsArtificial Analysis Intelligence Index21.0#82 / 117AA-GPQA Diamond77.9#81 / 113
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Score5380% interval36.9–69.21/4 Measured dimensions
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
80% interval30.8–69.20/4 Measured dimensionsDesign Arena Website1134.0#64 / 78
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score42.880% interval26.8–58.81/4 Measured dimensionsAA-IFBench41.5#65 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Pricing Comparison
Compare DeepSeek V3.1 API pricing across 211 providers. Prices range from $0.010/request to $87.60/M. 素墨API offers the lowest rate at $0.010/request. 4 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 99% | FAST/deepseek-v3.1 | 翻译 | -64%$0.205/M | -88%$0.205/M | 265.3 t/s | 0.96 s | — | |
L1 100% | deepseek-v3.1 | default | -52%$0.274/M | -51%$0.822/M | — | — | — | |
L1 100% | deepseek-v3-1-250821 | default | -52%$0.274/M | -51%$0.822/M | — | — | — | |
L1 100% | deepseek-v3-1 | default | -52%$0.274/M | -51%$0.822/M | — | — | — | |
L1 100% L2 0% | deepseek/deepseek-v3.1 | default | -67%$0.190/M Cache read$0.060/M | -58%$0.710/M | — | — | — | |
L1 100% | deepseek-v3-1-250821 | default | -52%$0.274/M | -51%$0.822/M | — | — | — | |
L1 100% | deepseek-v3.1 | default | -52%$0.274/M | -51%$0.822/M | — | — | — | |
L1 100% | deepseek-v3-1 | default | -52%$0.274/M | -51%$0.822/M | — | — | — | |
L1 100% | deepseek-v3.1 | default | -4%$0.548/M | -2%$1.64/M | — | — | — | |
L1 100% | deepseek-ai/DeepSeek-V3.1 | default | -4%$0.548/M | -2%$1.64/M | — | — | — | |
L1 100% | deepseek-v3.1-fast | default | $10.27/M | $20.55/M | — | — | — | |
L1 100% | DeepSeek-V3.1 | default | $10.27/M | $20.55/M | — | — | — | |
L1 100% | deepseek-v3.1 | default | $0.571/M Cache read$0.229/MCache write$0.571/MCache write 1h$0.914/M | $1.71/M | — | — | — | |
L1 100% | deepseek-v3.1 | default | $7.67/M | $7.67/M | — | — | — | |
L1 100% | deepseek-v3.1 | default | -93%$0.038/M Cache read$0.0075/M | -93%$0.115/M | — | — | — | |
L1 100% | deepseek-v3.1 | azure03-0 | -98%$0.012/M | -99%$0.017/M | — | — | — | |
L1 100% | deepseek-v3-1 | Self-Deployed-1 | -91%$0.052/M | -91%$0.155/M | — | — | — | |
L1 100% | deepseek-v3-1-250821 | Self-Deployed-1 | -91%$0.052/M | -91%$0.155/M | — | — | — | |
L1 100% | deepseek-v3.1 | Self-Deployed-1 | -91%$0.052/M | -91%$0.155/M | — | — | — | |
L1 100% | deepseek-v3.1 | default | -71%$0.164/M | -71%$0.493/M | — | — | — |
Alternatives & Similar Models
DeepSeek V3.2
deepseek-v3-2
DeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
GLM-5.1
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
GLM-5
glm-5
Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.
Frequently Asked Questions
- What benchmark data does DeepSeek V3.1 include?
- LMSpeed shows DeepSeek V3.1 benchmark context, API price, output speed, first-token latency, and provider data across 215 providers when those signals are available.
- What is the DeepSeek V3.1 API price?
- DeepSeek V3.1 has pricing from undefined provider} other undefined providers}}, ranging from $0.010/request to $87.60/M. 素墨API has the lowest listed price.
- What does the DeepSeek V3.1 API pricing table include?
- The DeepSeek V3.1 API pricing table compares 215 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest DeepSeek V3.1 API pricing?
- 素墨API currently has the lowest listed DeepSeek V3.1 price at $0.010/request across undefined provider} other undefined providers}}.
- Can I compare DeepSeek V3.1 API price and speed together?
- Yes. LMSpeed shows DeepSeek V3.1 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is DeepSeek V3.1 API free?
- Yes, DeepSeek V3.1 free API options are available through 4 providerundefined other undefined} on LMSpeed, including 兔子API, Zero API, 兔子API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get DeepSeek V3.1 free API access?
- LMSpeed currently lists 4 free API providerundefined other undefined} for DeepSeek V3.1: 兔子API, Zero API, 兔子API, 兔子API. Check each provider row before using it because free tier limits can change.