Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

DeepSeek V3 0324

submodelOpen weights

DeepSeek V3 0324 by submodel costs $0.20 per 1M input tokens and $0.80 per 1M output tokens, with a 75K-token context window.

Pricing

Input (per 1M tokens)
$0.20
Output (per 1M tokens)
$0.80
Cached input (per 1M)
—

Specifications

Provider
submodel
Context window
75K tokens
Parameters
—
Released
Mar 2025
Open weights
Yes
Frontier model
No

Compare DeepSeek V3 0324 with…

DeepSeek V3 0324 vs DeepSeek V4 Pro$0.80/1MDeepSeek V3 0324 vs Trinity Large Thinking$0.80/1MDeepSeek V3 0324 vs Llama 3.1 70B$0.80/1MDeepSeek V3 0324 vs Qwen 2.5 Coder 32B$0.79/1MDeepSeek V3 0324 vs Qwen-Plus$0.78/1MDeepSeek V3 0324 vs Llama 4 Scout 17B 16E Instruct$0.78/1M

FAQ

How much does DeepSeek V3 0324 cost?

DeepSeek V3 0324 is priced at $0.20 per 1M input tokens and $0.80 per 1M output tokens. Output tokens cost more than input.

What is DeepSeek V3 0324's context window?

DeepSeek V3 0324 supports a context window of 75K tokens — the maximum prompt plus response length it can handle in a single request.

Is DeepSeek V3 0324 open weight?

Yes — DeepSeek V3 0324 has openly available weights.

Data as of 2026-10-29. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.