LiteLLMModels

DeepSeek Coder 33B Instruct API Pricing

As of October 10, 2026, DeepSeek Coder 33B Instruct costs $0.80 per 1M input tokens and $0.80 per 1M output tokens from Together AI, the lowest of 2 providers. It has a 16,384-token context window and returns up to 16,384 tokens per response.

By DeepSeekModel ID together_ai/deepseek-ai/deepseek-coder-33b-instructPrices updated Checked
Deprecated: Together AI lists August 22, 2024 as the deprecation date for together_ai/deepseek-ai/deepseek-coder-33b-instruct.
Input
$0.80 / 1M tokens
Output
$0.80 / 1M tokens
Context window
16,384 tokens
Max output
16,384 tokens
Providers
2
Added to LiteLLM
December 2025

DeepSeek Coder 33B Instruct pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputContext
Together AItogether_ai/deepseek-ai/deepseek-coder-33b-instruct$0.80$0.8016K
Fireworks AIfireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct$0.90$0.9016K

What DeepSeek Coder 33B Instruct costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Together AI$2.00
Fireworks AI$2.25

Use DeepSeek Coder 33B Instruct with LiteLLM

Call DeepSeek Coder 33B Instruct through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="together_ai/deepseek-ai/deepseek-coder-33b-instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: deepseek-coder-33b-instruct
    litellm_params:
      model: together_ai/deepseek-ai/deepseek-coder-33b-instruct
      api_key: os.environ/TOGETHERAI_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "deepseek-coder-33b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek Coder 33B Instruct FAQ

How much does DeepSeek Coder 33B Instruct cost?

DeepSeek Coder 33B Instruct costs $0.80 per 1M input tokens and $0.80 per 1M output tokens from Together AI, the lowest of 2 providers.

What is the context window of DeepSeek Coder 33B Instruct?

DeepSeek Coder 33B Instruct has a 16,384-token context window and returns up to 16,384 tokens per response.

Which providers offer DeepSeek Coder 33B Instruct?

DeepSeek Coder 33B Instruct is available from 2 providers through LiteLLM: Together AI and Fireworks AI. The lowest price is on Together AI.

How do I call DeepSeek Coder 33B Instruct with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="together_ai/deepseek-ai/deepseek-coder-33b-instruct", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add DeepSeek Coder 33B Instruct?

DeepSeek Coder 33B Instruct was added to LiteLLM's model price file in December 2025.

Is DeepSeek Coder 33B Instruct being deprecated?

Together AI deprecated together_ai/deepseek-ai/deepseek-coder-33b-instruct on August 22, 2024.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Together AI, Fireworks AI.

Provider pages: Together AI, Fireworks AI.