DeepSeek Coder
deepseek-coderPricing
List prices at DeepSeek, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.14 | $0.28 | |
| Cached input 90% off input | $0.014 | 90% off input |
What it costs a month
At DeepSeek list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$51.66
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$47.04
- Coding agent1,000 requests a day, 40K in / 2K out, cached$78.96
- Overnight batch20,000 requests a day, 4K in / 0.4K out$403
Where to run it
1 host serve DeepSeek Coder. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
DeepSeekLab API deepseek-coder | $0.14 / $0.28 | deepseek-coder |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Assistant prefillPrompt caching
- Open weights
- License: DeepSeek License (MIT code)Runtimes: SGLang, TGI, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than DeepSeek.
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 19% less
- 20% less
- 21% less
- 43% less
Call it
Using DeepSeek's API.
from litellm import completion
response = completion(
model="deepseek/deepseek-coder",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek Coder cost?
On DeepSeek, DeepSeek Coder costs $0.14 per million input tokens and $0.28 per million output tokens. Cached input costs $0.014 per million tokens.
Which APIs offer DeepSeek Coder?
DeepSeek Coder runs on 1 API: DeepSeek.
What is DeepSeek Coder's context window?
128K tokens, with up to 4K tokens in one reply.
Is DeepSeek Coder being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek Coder?
Models that cost less and keep most of what it can do: DeepSeek V4.1 Flash on Sail (19% less). Savings are on a mix of 3 input tokens to 1 output token.
What is DeepSeek Coder's API model id?
Use deepseek-coder with DeepSeek.
Sources
Raw catalog entry for deepseek-coder on DeepSeek
{
"cache_read_input_token_cost": 1.4e-8,
"input_cost_per_token": 1.4e-7,
"input_cost_per_token_cache_hit": 1.4e-8,
"litellm_provider": "deepseek",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 2.8e-7,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
}