DeepSeek V4 Flash Thinking
deepseek-v4-flash-thinkingPricing
List prices at LibertAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.25 | $1.75 |
What it costs a month
At LibertAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$206
- RAG over documents2,000 requests a day, 8K in / 0.6K out$183
- Coding agent1,000 requests a day, 40K in / 2K out$405
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,020
Where to run it
1 host serve DeepSeek V4 Flash Thinking. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
LibertAICloud deepseek-v4-flash-thinking | $0.25 / $1.75 | deepseek-v4-flash-thinking |
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
- 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 LibertAI.
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
- 26% less
- 68% less
- 68% less
- 58% less
Open-weight picks
- 16% less
- 16% less
- 23% less
- 28% less
Call it
Using LibertAI's API.
from litellm import completion
response = completion(
model="libertai/deepseek-v4-flash-thinking",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek V4 Flash Thinking cost?
On LibertAI, DeepSeek V4 Flash Thinking costs $0.25 per million input tokens and $1.75 per million output tokens.
Which APIs offer DeepSeek V4 Flash Thinking?
DeepSeek V4 Flash Thinking runs on 1 API: LibertAI.
What is DeepSeek V4 Flash Thinking's context window?
200K tokens, with up to 200K tokens in one reply.
Is DeepSeek V4 Flash Thinking being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek V4 Flash Thinking?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (26% less), Claude Haiku 5.5 on Anthropic (68% less) and DeepSeek Flash on DeepSeek (16% less). Savings are on a mix of 3 input tokens to 1 output token.
What is DeepSeek V4 Flash Thinking's API model id?
Use deepseek-v4-flash-thinking with LibertAI.
Sources
Raw catalog entry for deepseek-v4-flash-thinking on LibertAI
{
"max_input_tokens": 200000,
"max_output_tokens": 200000,
"input_cost_per_token": 2.5e-7,
"output_cost_per_token": 0.00000175,
"litellm_provider": "libertai",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_system_messages": true,
"supports_vision": false,
"supports_reasoning": true,
"source": "https://docs.libertai.io/apis/text/"
}