DeepSeek V3 API Benchmarks, Pricing & Provider Data
Compare DeepSeek V3 with another model
Choose a model to open its comparison page.
DeepSeek V3 API pricing covers undefined API provider} other undefined API providers}}, from $0.0096/M to $2.00/M. DeepSeek V3 free API options are available from undefined provider} other undefined providers}}.
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported ev...
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Technical Details
- Input
- Output
- Released
- Dec 2024
- Knowledge cutoff
- 2024-07-31
- Tokenizer
- DeepSeek
- Architecture
- text->text
- Moderated
- No
- Supported parameters
- frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
OpenRouter endpoints
2 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 |
|---|---|---|---|---|---|---|
StreamLake streamlake | $0.257/M | $1.03/M | 99.6% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/fp4 | $0.320/M | $0.890/M | 96.0% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare DeepSeek V3 API pricing across 35 providers. Prices range from $0.0096/M to $2.00/M. Zero API offers the lowest rate at $0.0096/M. 3 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | deepseek-chat | default | $0.274/M Cache read$0.068/M | $1.10/M | — | — | — | |
L1 100% | deepseek-chat | deepseek | $0.012/M Cache read$0.0012/M | $0.017/M | — | — | — | |
L1 100% | deepseek-chat | default | $0.0096/M Cache read$0.0019/M | $0.019/M | — | — | — | |
L1 100% | deepseek-chat | default | $0.548/M Cache read$0.137/M | $0.548/M | — | — | — | |
L1 99% | deepseek-chat | 国产模型渠道 | $2.00/M | $3.00/M | — | — | — | |
兔子API Free | L1 99% | deepseek-chat | default | Free | Free | — | — | — |
L1 100% | deepseek-chat | default | $0.274/M Cache read$0.068/M | $1.10/M | — | — | — | |
L1 100% | deepseek-chat | Alibaba-1 | $0.297/M Cache read$0.074/M | $0.445/M | — | — | — | |
L1 99% | deepseek-chat | Alibaba-1 | $0.297/M Cache read$0.074/M | $0.445/M | — | — | — | |
L1 100% | deepseek-chat | default | $0.037/M Cache read$0.0092/M | $0.037/M | — | — | — | |
L1 100% | deepseek-chat | default | $0.137/M Cache read$0.034/M | $0.205/M | — | — | — | |
L1 98% | deepseek-chat | SSVIP | $2.00/M | $8.00/M | — | — | — | |
L1 0% | deepseek-chat | default | $0.270/M Cache read$0.033/M | $0.270/M | — | — | — | |
L1 0% | deepseek-chat | default | $0.040/request | - | — | — | — | |
L1 0% | deepseek-chat | 懒人 | $0.140/M Cache read$0.0028/MCache write$1.12/MCache write 1h$1.79/M | $0.280/M | — | — | — |
Alternatives & Similar Models
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.
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.
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.
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-5.2
gpt-5-2
OpenAI GPT-5.2 is a GPT-5 series model emphasizing advanced reasoning, multimodal understanding, and high-quality outputs for complex enterprise 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 V3 include?
- LMSpeed shows DeepSeek V3 benchmark context, API price, output speed, first-token latency, and provider data across 38 providers when those signals are available.
- What is the DeepSeek V3 API price?
- DeepSeek V3 has pricing from undefined provider} other undefined providers}}, ranging from $0.0096/M to $2.00/M. Zero API has the lowest listed price.
- What does the DeepSeek V3 API pricing table include?
- The DeepSeek V3 API pricing table compares 38 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 API pricing?
- Zero API currently has the lowest listed DeepSeek V3 price at $0.0096/M across undefined provider} other undefined providers}}.
- Is DeepSeek V3 API free?
- Yes, DeepSeek V3 free API options are available through 3 providerundefined other undefined} on LMSpeed, including 兔子API, Zero 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 free API access?
- LMSpeed currently lists 3 free API providerundefined other undefined} for DeepSeek V3: 兔子API, Zero API, 兔子API. Check each provider row before using it because free tier limits can change.