Check.AI

Model reference · Synced 2025-04-29

DeepSeek V3.1

DeepSeek V3.1 is an AI model from Nvidia. 128K context window. Capabilities: reasoning, tool calling, multimodal vision, open weights. Available on 20 providers. Cheapest listing: $0 input / $0 output per 1M tokens.

Quick facts

→ Add DeepSeek V3.1 to the comparison tool

Provider pricing

Same model, different providers, different prices. Cheapest first.

ProviderInput / 1MOutput / 1MContextListed
Nvidia $0 $0 128K 2025-08-20
NanoGPT $0.2 $0.7 128K 2025-07-26
submodel $0.2 $0.8 75K 2025-08-23
OpenRouter $0.2 $0.8 164K 2025-08-21
Jiekou.AI $0.27 $1 164K 2026-01
NovitaAI $0.27 $1 131K 2025-08-21
Meganova $0.27 $1 164K 2025-08-25
Vercel AI Gateway $0.3 $1 164K 2025-08-21
Baseten $0.5 $1.5 164K 2025-08-25
Abacus $0.55 $1.66 128K 2025-01-20
Weights & Biases $0.55 $1.65 161K 2025-08-21
Fireworks AI $0.56 $1.68 164K 2025-08-21
Azure Cognitive Services $0.56 $1.68 131K 2025-08-21
Synthetic $0.56 $1.68 128K 2025-08-21
LLM Gateway $0.56 $1.68 128K 2025-08-21
Azure $0.56 $1.68 131K 2025-08-21
Alibaba (China) $0.574 $1.72 131K 2025-01-01
Amazon Bedrock $0.58 $1.68 164K 2025-09-18
Vertex $0.6 $1.7 164K 2025-08-28
Together AI $0.6 $1.7 131K 2025-08-21

Prices synced daily from models.dev + provider docs.

How to use this model

If you're picking DeepSeek V3.1 for a project, the three things that matter most:

Related models

FAQ

How much does DeepSeek V3.1 cost? $0 input / $0 output per 1M tokens at the cheapest listing. See the table above for other providers.

What is the context window? 128K tokens.

Which providers offer it? NanoGPT, Abacus, submodel, OpenRouter, Fireworks AI, Alibaba (China), Jiekou.AI, NovitaAI, Weights & Biases, Amazon Bedrock, and others — see the full table above.

Where do these numbers come from? models.dev + provider documentation, synced daily. About the data.