DeepSeek V3.2 Speciale
DeepSeek-V3.2-SpecialePricing
List prices at GMI Cloud, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.28 | $0.40 |
What it costs a month
At GMI Cloud list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$114
- RAG over documents2,000 requests a day, 8K in / 0.6K out$149
- Coding agent1,000 requests a day, 40K in / 2K out$360
- Overnight batch20,000 requests a day, 4K in / 0.4K out$768
Where to run it
2 hosts serve DeepSeek V3.2 Speciale. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
GMI CloudInference DeepSeek-V3.2-Speciale | $0.28 / $0.40 | DeepSeek-V3.2-Speciale | |
Azure AI FoundryCloud deepseek-v3.2-speciale | $0.58 / $1.68 +176% vs headline Retires 1 Nov 2027 | deepseek-v3.2-speciale | Retires 1 Nov 2027 |
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 GMI Cloud.
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
- 35% less
- 35% less
- 15% less
Open-weight picks
- 15% less
- 17% less
- 19% less
- 42% less
Call it
Using GMI Cloud's API.
from litellm import completion
response = completion(
model="gmi/DeepSeek-V3.2-Speciale",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek V3.2 Speciale cost?
On GMI Cloud, DeepSeek V3.2 Speciale costs $0.28 per million input tokens and $0.40 per million output tokens.
Which APIs offer DeepSeek V3.2 Speciale?
DeepSeek V3.2 Speciale runs on 2 APIs: GMI Cloud and Azure AI Foundry.
What is DeepSeek V3.2 Speciale's context window?
164K tokens, with up to 128K tokens in one reply.
Is DeepSeek V3.2 Speciale being retired?
Azure AI Foundry retires it on 1 Nov 2027. 1 host keeps serving it.
What are cheaper alternatives to DeepSeek V3.2 Speciale?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (35% less), GPT-6 Luna on OpenAI (35% less) and Mistral Small 2603 on Mistral AI (15% less). Savings are on a mix of 3 input tokens to 1 output token.
What is DeepSeek V3.2 Speciale's API model id?
Use DeepSeek-V3.2-Speciale with GMI Cloud. Other hosts use their own ids: deepseek-v3.2-speciale on Azure AI Foundry.
Sources
Raw catalog entry for DeepSeek-V3.2-Speciale on GMI Cloud
{
"input_cost_per_token": 2.8e-7,
"litellm_provider": "gmi",
"max_input_tokens": 163840,
"mode": "chat",
"output_cost_per_token": 4e-7,
"source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts"
}