DeepSeek V4 Pro API Benchmarks, Pricing & Provider Data
Compare DeepSeek V4 Pro with another model
Choose a model to open its comparison page.
DeepSeek V4 Pro benchmark, API pricing, and provider data cover undefined API provider} other undefined API providers}}, with prices starting at $0.0020/request. DeepSeek V4 Pro free API options are available from undefined provider} other undefined providers}}. The page also shows measured API speed and first-token latency.
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 5 / 8
- Methodology
- V3.0
#1Reasoning54.5RatedGlobal rank #193/4 Measured dimensions
#2Knowledge52.6Provisional1/4 Measured dimensions
#3Agents50Estimated2/4 Measured dimensions
#4Coding46.9RatedGlobal rank #324/4 Measured dimensions
#5Math31.6Estimated2/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Technical Details
- Input
- Output
- Released
- Apr 2026
- Tokenizer
- DeepSeek
- Architecture
- text->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Rankings
Excels at
Falls behind in
Detailed scores
Updated: Sep 13, 2026Overall
undefined metric} other undefined metrics}}
Overall score61.0#43 / 112
Overall
undefined metric} other undefined metrics}}
Speed & latency
undefined metric} other undefined metrics}}
Output speed67.9 tok/s#60 / 80Time to first token1.10 s#34 / 80
Speed & latency
undefined metric} other undefined metrics}}
Pricing
undefined metric} other undefined metrics}}
Input price$0.435/M#82 / 186Output price$0.870/M#40 / 186
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · Estimated
Score5080% interval39.5–60.62/4 Measured dimensionsAgentic score61.8#40 / 77Terminal-Bench 2.063.3#29 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Estimated
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Score46.9#3280% interval40.3–53.54/4 Measured dimensionsSciCode51.0%#30 / 89Coding score48.4#59 / 87
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score54.5#1980% interval45.5–63.53/4 Measured dimensionsMMLU-Pro87.1%#12 / 129GPQA90.5%#30 / 218
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score52.680% interval34.6–70.71/4 Measured dimensionsKnowledge score64.3#53 / 83SimpleQA46.2#2 / 4
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Score31.680% interval19.5–43.82/4 Measured dimensionsHMMT Feb 202694.0#4 / 18IMOAnswerBench88.0#4 / 7
Math
V3.0undefined metric} other undefined metrics}} · Estimated
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
No data80% interval30.8–69.20/4 Measured dimensions
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
OpenRouter endpoints
14 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Baidu baidu/fp8 | $0.656/M | $1.31/M | 100.0% | — | — | undefined tokens / undefined tokens |
Novita novita/fp8 | $1.60/M | $3.20/M | 100.0% | — | — | undefined tokens / undefined tokens |
Alibaba alibaba/fp8 | $1.42/M | $2.83/M | 100.0% | — | — | undefined tokens / undefined tokens |
DigitalOcean digitalocean | $0.870/M | $1.74/M | 100.0% | — | — | undefined tokens / undefined tokens |
NextBit nextbit/fp8 | $2/M | $4/M | 99.9% | — | — | undefined tokens / undefined tokens |
Parasail parasail/fp8 | $1.74/M | $3.48/M | 99.8% | — | — | undefined tokens / undefined tokens |
BaseTen baseten/fp4 | $1.74/M | $3.48/M | 99.8% | — | — | undefined tokens / undefined tokens |
GMICloud gmicloud/fp8 | $0.957/M | $1.91/M | 99.7% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/fp8 | $1.30/M | $2.60/M | 99.5% | — | — | undefined tokens / undefined tokens |
Azure azure/us | $1.91/M | $3.83/M | 99.3% | — | — | undefined tokens / undefined tokens |
AtlasCloud atlas-cloud/fp4 | $1.68/M | $3.38/M | 99.3% | — | — | undefined tokens / undefined tokens |
StreamLake streamlake/fp8 | $0.647/M | $1.29/M | 98.6% | — | — | undefined tokens / undefined tokens |
SiliconFlow siliconflow/fp8 | $1.50/M | $3.14/M | 98.4% | — | — | undefined tokens / undefined tokens |
Venice venice | $1.65/M | $3.30/M | 98.4% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare DeepSeek V4 Pro API pricing across 338 providers. Prices range from $0.0020/request to $238.36/M. 3173721 API offers the lowest rate at $0.0020/request. 11 providers offer free API credits or a free tier.
Alternatives & Similar Models
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.
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
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.
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.
Claude Sonnet 4.6
claude-sonnet-4-6
Anthropic Claude Sonnet 4.6 extends the Sonnet line with improved tool use, coding reliability, and long-context performance for everyday production workloads.
Claude Opus 4.6
claude-opus-4-6
Anthropic Claude Opus 4.6 is the most capable Claude Opus tier, optimized for complex analysis, long-horizon coding, and high-stakes enterprise reasoning workloads.
Frequently Asked Questions
- What benchmark data does DeepSeek V4 Pro include?
- LMSpeed shows DeepSeek V4 Pro benchmark context, API price, output speed, first-token latency, and provider data across 349 providers when those signals are available.
- What is the DeepSeek V4 Pro API price?
- DeepSeek V4 Pro has pricing from undefined provider} other undefined providers}}, ranging from $0.0020/request to $238.36/M. 3173721 API has the lowest listed price.
- What does the DeepSeek V4 Pro API pricing table include?
- The DeepSeek V4 Pro API pricing table compares 349 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 V4 Pro API pricing?
- 3173721 API currently has the lowest listed DeepSeek V4 Pro price at $0.0020/request across undefined provider} other undefined providers}}.
- Can I compare DeepSeek V4 Pro API price and speed together?
- Yes. LMSpeed shows DeepSeek V4 Pro API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is DeepSeek V4 Pro API free?
- Yes, DeepSeek V4 Pro free API options are available through 11 providerundefined other undefined} on LMSpeed, including 梦德 API, 初叶🍂Furry API, Dext API, Dext API, Moyanjdc API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get DeepSeek V4 Pro free API access?
- LMSpeed currently lists 11 free API providerundefined other undefined} for DeepSeek V4 Pro: 梦德 API, 初叶🍂Furry API, Dext API, Dext API, Moyanjdc API. Check each provider row before using it because free tier limits can change.