DeepSeek V4 Pro Fast
deepseek-v4-pro-fastPricing
List prices at Wally, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.91 | $3.83 | |
| Cached input 92% off input | $0.16 | 92% off input |
What it costs a month
At Wally list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$703
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$635
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,052
- Overnight batch20,000 requests a day, 4K in / 0.4K out$5,503
Where to run it
1 host serve DeepSeek V4 Pro Fast. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
WallyCloud deepseek-v4-pro-fast | $1.91 / $3.83 | deepseek-v4-pro-fast |
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
- Effort settings the source lists
- noneminimallowmediumhighmax
- Features
- Prompt 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 Wally.
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
- 16% less
- 37% less
- 48% less
- 92% less
Open-weight picks
- 11% less
- 28% less
- 64% less
- 67% less
Call it
Using Wally's API.
from litellm import completion
response = completion(
model="wally/deepseek-v4-pro-fast",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek V4 Pro Fast cost?
On Wally, DeepSeek V4 Pro Fast costs $1.91 per million input tokens and $3.83 per million output tokens. Cached input costs $0.16 per million tokens.
Which APIs offer DeepSeek V4 Pro Fast?
DeepSeek V4 Pro Fast runs on 1 API: Wally.
What is DeepSeek V4 Pro Fast's context window?
1M tokens, with up to 66K tokens in one reply.
Is DeepSeek V4 Pro Fast being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek V4 Pro Fast?
Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (16% less), Gemini 3.8 Flash on Google AI Studio (37% less) and Qwen4 Max on Together AI (11% less). Savings are on a mix of 3 input tokens to 1 output token.
What is DeepSeek V4 Pro Fast's API model id?
Use deepseek-v4-pro-fast with Wally.
Sources
Raw catalog entry for deepseek-v4-pro-fast on Wally
{
"cache_read_input_token_cost": 1.6e-7,
"input_cost_per_token": 0.00000191,
"litellm_provider": "wally",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 0.00000383,
"reasoning_effort_levels": [
"none",
"minimal",
"low",
"medium",
"high",
"max"
],
"source": "https://www.runwally.com/pricing",
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": false
}