impulse

DeepSeek Coder

Open weights
API id deepseek-coder
Input / 1M
$0.14
at DeepSeek
Output / 1M
$0.28
at DeepSeek
Context window
128K
tokens
Max output
4K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at DeepSeek, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.14$0.28
Cached input
90% off input
$0.014

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
Use your own numbers

Where to run it

1 host serve DeepSeek Coder. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepSeekLab API
deepseek-coder
$0.14 / $0.28

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

  • DeepSeek V4.1 Flash
    DeepSeek · on Sail
    $0.09 / $0.30
    Has every key capability
    19% less
  • MiMo V2.6 Flash
    Xiaomi · on GMI Cloud
    $0.112 / $0.224
    Has every key capability
    20% less
  • Qwen3.6 35B A3B
    Alibaba Qwen · on Sail
    $0.05 / $0.40
    Has every key capability
    21% less
  • MiniMax M3.1 Flash
    MiniMax · on Refuseless
    $0.05 / $0.25
    Has every key capability
    43% less

Call it

Using DeepSeek's API.

Python
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
}