DeepSeek Coder API pricing
DeepSeek Coder costs $0.14 per million input tokens and $0.28 per million output tokens on the DeepSeek API, and $0.014 per million cached input tokens. Context window: 128k tokens. Updated .
| Price per 1M tokens | US dollars |
|---|---|
| Input | $0.14 |
| Cached input | $0.014 |
| Output | $0.28 |
What it costs in practice
- One chat or extraction call (2,000 tokens in, 500 out): $0.0004
- 1,000 such calls: $0.420
- 1 million tokens at a typical 80% input / 20% output mix: $0.168
Abilities: tool use. Batch, long-context, priority and regional prices differ; check the full table and the provider’s own pricing page before you commit.
Cheapest alternatives from other providers
| Model | Input | Output | Context | Typical call ×1,000 |
|---|---|---|---|---|
| Qwen Turbo Alibaba (Qwen) | $0.050 | $0.20 | 129k | $0.20 |
| GLM 4 32b 0414 128k Zhipu (GLM) | $0.10 | $0.10 | 128k | $0.25 |
| GPT-5 nano OpenAI | $0.050 | $0.40 | 272k | $0.30 |
| Gemini 2.5 Flash Lite Google | $0.10 | $0.40 | 1.0M | $0.40 |
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | $0.45 |
| GPT-6 luna OpenAI | $0.10 | $0.50 | 922k | $0.45 |
Other DeepSeek models
| Model | Input | Output | Context | Typical call ×1,000 |
|---|---|---|---|---|
| DeepSeek V3.2 DeepSeek | $0.28 | $0.40 | 164k | $0.76 |
| DeepSeek V3 DeepSeek | $0.27 | $1.10 | 66k | $1.09 |
| DeepSeek Flash DeepSeek | $0.30 | $1.20 | 1M | $1.20 |
| DeepSeek V4 Flash DeepSeek | $0.30 | $1.20 | 1M | $1.20 |
| DeepSeek V4 Flash Vision Exp DeepSeek | $0.30 | $1.20 | 1M | $1.20 |
| DeepSeek R1 DeepSeek | $0.55 | $2.19 | 66k | $2.19 |
Questions
How much does DeepSeek Coder cost?
DeepSeek Coder costs $0.14 per million input tokens and $0.28 per million output tokens on the DeepSeek API; cached input is $0.014 per million. A typical call with 2,000 tokens in and 500 out costs about $0.0004.
What is the context window of DeepSeek Coder?
DeepSeek Coder accepts up to 128,000 input tokens and returns up to 4,096 output tokens.
Is there a cheaper alternative to DeepSeek Coder?
For a typical call, Qwen Turbo (Alibaba (Qwen), $0.0002 per call), GLM 4 32b 0414 128k (Zhipu (GLM), $0.0003 per call), GPT-5 nano (OpenAI, $0.0003 per call) cost less and also support tool use. Quality differs, so test on your own prompts.
Source: the open LiteLLM model price map (MIT), checked daily (data file).