DeepSeek v3

DeepSeek V3 API delivers frontier-level intelligence with 671B parameters. Optimized for coding and math, this MoE model offers a 128k context window and GPT-4o performance at significantly lower costs through GPTProto.com.

Modalities

API Usage Examples

curl --request POST "https://gptproto.com/v1/chat/completions" \
  --header "Authorization: Bearer $GPTPROTO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "deepseek-v3",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

DeepSeek v3 pricing

Chat, coding agents & document work. Priced per 1M tokens — input, cached input and output are billed separately. GPTProto is 40% below official rates.

Your usage

Model

DeepSeek · ≈ 100M tokens/mo (0M cached)

Monthly volume

OpenRouter

List + 5.5% credit fee

$45.62

per month

Input (non-cached)$22.81

Output$22.81

DeepSeek

Direct from DeepSeek (list price)

$43.25

per month

Input (non-cached)$21.62

Output$21.62

BEST VALUE

GPTProto

40% off official

$25.95

per month

After discount$25.95

Effective$25.95

Monthly cost by source

OpenRouter

$45.62

DeepSeek

$43.25

GPTProto

$25.95

Save $17.30 / month

on GPTProto vs DeepSeek (−40%)

Annual savings ≈ $207.55 · pay as you go

OpenRouter costs include its ~5.5% credit purchase fee. GPTProto applies a per-model discount (10–30% off) and your bonus credits are also spent at discounted rates — savings compound. Estimates assume a 60% cache hit rate.

Related Models

All Models

DeepSeek v3

Current

byDeepSeek$0.1622/M input$0.6487/M output

DeepSeek Flash

byDeepSeek$0.3/M input$1.2/M output

Hy4 Preview

byHunyuan$0.7923/M input$2.376/M output

GPT 6 Astra

byOpenAI1.05M context$8/M input$40/M output

Gemini 3.8 Flash

byGoogle1.05M context$0.9/M input$4.5/M output

Claude Fable 5.1

byClaude1M context$9/M input$45/M output

Qwen3.8 Max 0902

byQwen1M context$1.8/M input$5.4/M output

GLM 5.3 Flash

byZ-AI1.31M context$0.15/M input$0.5/M output

DeepSeek v4 Flash Vision Exp

byDeepSeek1.05M context$0.3/M input$1.2/M output

GLM 5.3

byZ-AI1.31M context$1.26/M input$3.96/M output

Gemini 3.7 Flash

byGoogle1.05M context$0.9/M input$4.5/M output

Grok 4.6

byGrok500K context$1.2/M input$3.6/M output

Qwen3.8 Max

byQwen1M context$1.8/M input$5.4/M output

Claude Opus 5

byClaude1M context$4.5/M input$22.5/M output

Gemini 3.6 Flash

byGoogle1.05M context$0.9/M input$4.5/M output

Kimi K3

byMoonshotAI1.05M context$2.7/M input$13.5/M output

GPT 5.6 Luna

byOpenAI1.05M context$0.16/M input$0.96/M output

GPT 5.6 Terra

byOpenAI1.05M context$1.6/M input$9.6/M output

Grok 4.5

byGrok500K context$1.2/M input$3.6/M output

Claude Sonnet 5

byClaude1M context$1.8/M input$9/M output

Minimax M3

byMiniMax1.05M context$0.48/M input$0.96/M output

GLM 5.2

byZ-AI1.05M context$1.26/M input$3.96/M output

Qwen3.7 Max

byQwen1M context$0.36/M input$1.44/M output

DeepSeek v4 Flash

byDeepSeek1.05M context$0.3/M input$1.2/M output

DeepSeek v4 Pro

byDeepSeek1.05M context$1.122/M input$3.366/M output

Grok 4.3

byGrok1M context$0.75/M input$1.5/M output

Kimi K2.6

byMoonshotAI262K context$0.855/M input$3.6/M output

DeepSeek v3.2

byDeepSeek164K context$0.168/M input$0.252/M output

Minimax M2.5

byMiniMax205K context$0.24/M input$0.96/M output

Kimi K2.5

byMoonshotAI262K context$0.54/M input$2.7/M output

DeepSeek R1

byDeepSeek64K context$0.33/M input$1.3135/M output

Doubao Seed 1.6 Thinking (Build 250715)

byBytedance262K context$0.0971/M input$0.9714/M output

Doubao Seed 1.6 Thinking (Build 250615)

byBytedance262K context$0.0971/M input$0.9714/M output

Doubao Seed 1.6 Flash (Build 250615)

byBytedance262K context$0.0182/M input$0.1821/M output

Model					Input → Output
DeepSeek v3Current $		—	$0.16 / $0.65 per 1M	—	Input: Text Output: Text
DeepSeek Flash $	—	—	$0.30 / $1.20 per 1M	— / $0.006 per 1M	Input: TextInput: Image Output: Text
Hy4 Preview $		—	$0.79 / $2.38 per 1M	— / $0.04 per 1M	Input: Text Output: Text
GPT 6 Astra $		1.05M	$8.00 / $40.00 per 1M	$10.00 / $0.80 per 1M	Input: TextInput: ImageInput: Document Output: Text
Gemini 3.8 Flash $		1.05M	$0.90 / $4.50 per 1M	$0.60 / $0.09 per 1M	Input: TextInput: ImageInput: VideoInput: DocumentInput: Audio Output: Text
Claude Fable 5.1 $		1M	$9.00 / $45.00 per 1M	$11.25 / $0.23 per 1M	Input: TextInput: ImageInput: Document Output: Text
Qwen3.8 Max 0902 $		1M	$1.80 / $5.40 per 1M	$2.25 / $0.23 per 1M	Input: TextInput: ImageInput: VideoInput: DocumentInput: Audio Output: Text
GLM 5.3 Flash $	—	1.31M	$0.15 / $0.50 per 1M	— / $0.03 per 1M	Input: TextInput: ImageInput: VideoInput: Document Output: Text
DeepSeek v4 Flash Vision Exp $	—	1.05M	$0.30 / $1.20 per 1M	— / $0.006 per 1M	Input: TextInput: Image Output: Text
GLM 5.3 $		1.31M	$1.26 / $3.96 per 1M	— / $0.23 per 1M	Input: TextInput: ImageInput: Document Output: Text
Gemini 3.7 Flash $		1.05M	$0.90 / $4.50 per 1M	$0.60 / $0.09 per 1M	Input: TextInput: ImageInput: Document Output: Text
Grok 4.6 $		500K	$1.20 / $3.60 per 1M	— / $0.30 per 1M	Input: TextInput: Image Output: Text
Qwen3.8 Max $		1M	$1.80 / $5.40 per 1M	$2.25 / $0.23 per 1M	Input: TextInput: ImageInput: VideoInput: Document Output: Text
Claude Opus 5 $		1M	$4.50 / $22.50 per 1M	$5.63 / $0.45 per 1M	Input: TextInput: ImageInput: Document Output: Text
Gemini 3.6 Flash $		1.05M	$0.90 / $4.50 per 1M	$0.60 / $0.09 per 1M	Input: TextInput: ImageInput: Document Output: Text
Kimi K3 $		1.05M	$2.70 / $13.50 per 1M	$0.27 / $0.27 per 1M	Input: TextInput: ImageInput: Document Output: Text
GPT 5.6 Luna $		1.05M	$0.16 / $0.96 per 1M	$0.20 / $0.02 per 1M	Input: TextInput: ImageInput: Document Output: Text
GPT 5.6 Terra $		1.05M	$1.60 / $9.60 per 1M	$2.00 / $0.16 per 1M	Input: TextInput: ImageInput: Document Output: Text
Grok 4.5 $		500K	$1.20 / $3.60 per 1M	$0.30 / $0.30 per 1M	Input: TextInput: Image Output: Text
Claude Sonnet 5 $		1M	$1.80 / $9.00 per 1M	$2.25 / $0.18 per 1M	Input: TextInput: Document Output: Text
Minimax M3 $		1.05M	$0.48 / $0.96 per 1M	$0.10 / $0.10 per 1M	Input: TextInput: ImageInput: Document Output: Text
GLM 5.2 $		1.05M	$1.26 / $3.96 per 1M	$0.23 / $0.23 per 1M	Input: TextInput: ImageInput: Document Output: Text
Qwen3.7 Max $		1M	$0.36 / $1.44 per 1M	$0.07 / $0.07 per 1M	Input: TextInput: Document Output: Text
DeepSeek v4 Flash $	—	1.05M	$0.30 / $1.20 per 1M	— / $0.006 per 1M	Input: Text Output: Text
DeepSeek v4 Pro $		1.05M	$1.12 / $3.37 per 1M	— / $0.04 per 1M	Input: Text Output: Text
Grok 4.3 $		1M	$0.75 / $1.50 per 1M	$0.12 / $0.12 per 1M	Input: TextInput: Image Output: Text
Kimi K2.6 $		262K	$0.85 / $3.60 per 1M	$0.14 / $0.14 per 1M	Input: TextInput: Document Output: Text
DeepSeek v3.2 $		164K	$0.17 / $0.25 per 1M	$0.02 / $0.02 per 1M	Input: Text Output: Text
Minimax M2.5 $		205K	$0.24 / $0.96 per 1M	$0.30 / $0.02 per 1M	Input: TextInput: Document Output: Text
Kimi K2.5 $		262K	$0.54 / $2.70 per 1M	$0.09 / $0.09 per 1M	Input: TextInput: Document Output: Text
DeepSeek R1 $		64K	$0.33 / $1.31 per 1M	—	Input: Text Output: Text
Doubao Seed 1.6 Thinking (Build 250715) $		262K	$0.10 / $0.97 per 1M	—	Input: TextInput: Image Output: Text
Doubao Seed 1.6 Thinking (Build 250615) $		262K	$0.10 / $0.97 per 1M	—	Input: TextInput: Image Output: Text
Doubao Seed 1.6 Flash (Build 250615) $		262K	$0.02 / $0.18 per 1M	—	Input: TextInput: Image Output: Text

DeepSeek V3 API Standout Features

Discover the technical innovations that make the DeepSeek V3 API a leader in model efficiency.

Elite Coding and Logic

DeepSeek V3 API scores 82.6% on HumanEval, making it a powerhouse for automated programming, unit testing, and refactoring tasks.

Advanced MoE Architecture

With 671B total parameters and 37B active per token, DeepSeek delivers GPT-4o level intelligence with superior inference speed.

Massive 128k Context

Process high-volume documents or entire codebases easily using the DeepSeek V3 API's extensive 128,000 token context window.

Unbeatable API Pricing

Save over 90% on input costs compared to frontier rivals. DeepSeek V3 API offers a standard input price of just $0.14 per 1M tokens.

DeepSeek V3 API Frequently Asked Questions

Find technical details and integration tips for the DeepSeek V3 API to maximize your project performance.

What makes DeepSeek V3 API cost-effective?

DeepSeek uses a Mixture-of-Experts architecture where only 37B parameters are active per token. This efficiency, combined with FP8 precision training, allows us to offer the DeepSeek V3 API at prices significantly lower than GPT-4o while maintaining elite performance in coding and math tasks.

Is the DeepSeek V3 API compatible with OpenAI?

Yes. The DeepSeek V3 API is designed to be fully OpenAI-compatible. Developers can migrate existing workflows by simply updating the base URL and model name in their current SDK setup, making the transition to DeepSeek seamless and immediate.

How does DeepSeek handle long context windows?

DeepSeek supports up to 128,000 tokens. It uses Multi-head Latent Attention (MLA) to manage memory efficiently, ensuring that even large-scale data extraction or long-form synthesis tasks remain fast and reliable via the DeepSeek V3 API.

What are the benchmark scores for DeepSeek V3?

DeepSeek V3 excels in technical fields, scoring 82.6% on HumanEval and 90.2% on MATH-500. These results prove that DeepSeek is a top-tier choice for programming, logic, and scientific applications compared to other frontier models.

Does GPTProto.com offer context caching for DeepSeek?

Yes. DeepSeek natively supports context caching. When you use the DeepSeek V3 API via our platform, repeat prompts can receive up to a 90% discount on input costs, making it the most economical choice for repetitive agentic workflows.

Can the DeepSeek V3 API process images or video?

Currently, the standard DeepSeek V3 API is a text-only model optimized for reasoning and code. For multimodal tasks involving vision, developers should look for specific vision-enabled versions of the DeepSeek model family.