DeepSeek V3.1 Terminus API Pricing
As of October 10, 2026, DeepSeek V3.1 Terminus costs $0.27 per 1M input tokens and $1.00 per 1M output tokens from Novita AI, the lowest of 3 providers, with cache reads at $0.135 per 1M tokens. It has a 131,072-token context window and returns up to 32,768 tokens per response.
- Input
- $0.27 / 1M tokens
- Output
- $1.00 / 1M tokens
- Cache read
- $0.135 / 1M tokens
- Context window
- 131,072 tokens
- Max output
- 32,768 tokens
- Providers
- 3
- Added to LiteLLM
- October 2025
DeepSeek V3.1 Terminus pricing by provider
3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| Novita AI | novita/deepseek/deepseek-v3.1-terminus | $0.27 | $1.00 | $0.135 | 128K |
| DeepInfra | deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus | $0.27 | $1.00 | $0.216 | 160K |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus | $0.56 | $1.68 | – | 128K |
What DeepSeek V3.1 Terminus costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Novita AI | $1.04 |
| DeepInfra | $1.04 |
| Fireworks AI | $1.96 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Novita AI | $2.90 |
| DeepInfra | $2.90 |
| Fireworks AI | $5.936 |
DeepSeek V3.1 Terminus features
- Function calling
- Parallel tool calls
- Structured output
- Reasoning
Use DeepSeek V3.1 Terminus with LiteLLM
Call DeepSeek V3.1 Terminus 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.
from litellm import completion
response = completion(
model="novita/deepseek/deepseek-v3.1-terminus",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: deepseek-v3.1-terminus
litellm_params:
model: novita/deepseek/deepseek-v3.1-terminus
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "deepseek-v3.1-terminus",
"messages": [{"role": "user", "content": "Hello!"}]
}'DeepSeek V3.1 Terminus FAQ
How much does DeepSeek V3.1 Terminus cost?
DeepSeek V3.1 Terminus costs $0.27 per 1M input tokens and $1.00 per 1M output tokens from Novita AI, the lowest of 3 providers, with cache reads at $0.135 per 1M tokens.
What is the context window of DeepSeek V3.1 Terminus?
DeepSeek V3.1 Terminus has a 131,072-token context window and returns up to 32,768 tokens per response.
Which providers offer DeepSeek V3.1 Terminus?
DeepSeek V3.1 Terminus is available from 3 providers through LiteLLM: Novita AI, DeepInfra and Fireworks AI. The lowest price is on Novita AI.
How do I call DeepSeek V3.1 Terminus with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="novita/deepseek/deepseek-v3.1-terminus", 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.
What features does DeepSeek V3.1 Terminus support?
DeepSeek V3.1 Terminus supports function calling, parallel tool calls, structured output and reasoning.
When did LiteLLM add DeepSeek V3.1 Terminus?
DeepSeek V3.1 Terminus was added to LiteLLM's model price file in October 2025.
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: DeepInfra, Fireworks AI.
Provider pages: Novita AI, DeepInfra, Fireworks AI.