Deepseek Ai/Deepseek V3.1 Maas
Deepseek Ai/Deepseek V3.1 Maas is available via Google Vertex AI with a 164K context window and up to 32,768 output tokens. Pricing: $1.35/1M input tokens, $5.40/1M output tokens.
Deepseek Ai/Deepseek V3.1 Maas Pricing & Specifications
What is Deepseek Ai/Deepseek V3.1 Maas?
Deepseek Ai/Deepseek V3.1 Maas is a large language model by Google Vertex AI with a 164K context window and up to 32,768 output tokens. It costs $1.35 per 1M input tokens and $5.40 per 1M output tokens. Deepseek Ai/Deepseek V3.1 Maas is available via Google Vertex AI with a 164K context window and up to 32,768 output tokens. Pricing: $1.35/1M input tokens, $5.40/1M output tokens.
Capabilities
text function calling reasoning
Deepseek Ai/Deepseek V3.1 Maas Cost Examples
Short prompt (500 tokens)
$0.000675
Medium prompt (2K tokens)
$0.00270
Long output (4K tokens)
$0.02160
Count tokens for Deepseek Ai/Deepseek V3.1 Maas
Paste your prompt to see exact token counts and API cost estimates.
Open Token CounterSimilar Models to Deepseek Ai/Deepseek V3.1 Maas
Frequently Asked Questions
How much does Deepseek Ai/Deepseek V3.1 Maas cost per token? +
Deepseek Ai/Deepseek V3.1 Maas costs $1.35 per 1M input tokens and $5.40 per 1M output tokens. For a typical 1,000-token request with a 500-token response, that works out to roughly $0.004050.
What is the context window for Deepseek Ai/Deepseek V3.1 Maas? +
Deepseek Ai/Deepseek V3.1 Maas supports a context window of 163,840 tokens (164K). This determines the maximum combined length of your prompt and conversation history in a single API call.
What is the maximum output length for Deepseek Ai/Deepseek V3.1 Maas? +
Deepseek Ai/Deepseek V3.1 Maas can generate up to 32,768 tokens in a single response. If you need longer outputs, you can make multiple API calls and concatenate the results.
Is Deepseek Ai/Deepseek V3.1 Maas good for coding tasks? +
Yes, Deepseek Ai/Deepseek V3.1 Maas supports capabilities well-suited for coding tasks including code generation, debugging, and refactoring.