DeepSeek Coder 33B on Together AI

DeepSeek Coder · DeepSeek

ServerlessOpen Weights

Last refreshed 2026-06-15. Next refresh: weekly.

Why use DeepSeek Coder 33B on Together AI?

Together AI offers DeepSeek Coder 33B with pay-as-you-go pricing at $0.80/1M input tokens. Together AI is a platform for running open-source and proprietary LLMs with fast serverless and dedicated endpoints at competitive inference pricing.

Compare DeepSeek Coder 33B across 3 providers to find the best fit for your use case
Input / 1M
$0.80
Output / 1M
$0.80
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install together
Auth
export TOGETHER_API_KEY=...
Call
from together import Together
client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="deepseek-coder-33b",
Model ID
deepseek-coder-33b

Request example

from together import Together

client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="deepseek-coder-33b",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.
  • The examples expect TOGETHER_API_KEY; rename it only if your application config maps the new variable.

Compare DeepSeek Coder 33B Across Providers

ProviderInput (per 1M)Output (per 1M)
Together AI$0.80$0.80
Alibaba Cloud PAI-EAS——
Fireworks AI$0.90$0.90

Pricing

TypePrice (per 1M)
Input tokens$0.80
Output tokens$0.80

Capabilities

Structured Outputs

About DeepSeek Coder 33B

DeepSeek Coder 33B is DeepSeek's DeepSeek Coder model focused on code generation and software engineering. It offers a 16K-token context window with weights openly available for self-hosting and scores 57.1 on HumanEval.

Get Started

Model Specs

Released2024-03-07
Parameters33B
Context16k
ArchitectureDecoder Only
Knowledge cutoff2023-03

Related Models on Together AI