LLM PricesModelsChangelog
Prices in USD per 1M tokens, text only. Each price shows where it came from and when it was last verified. Prices marked unverified come from models.dev (community-maintained) until we read them from the provider directly.
← All models

DeepSeek-V3.1

Same open weights, served by 2 providers. Weights: deepseek-ai/DeepSeek-V3.1.

deepseekOpen weights164k contextReleased 2025-08-21deepseek/deepseek-v3.1

Providers

Show flex / batch / priority tiersFull precision only
ProviderTheir model idServingInputOutputCached inBlended 3:1Source
DeepInfra
deepseek-ai/DeepSeek-V3.1
standardFP4
$0.25$0.95$0.13$0.425
Provider API
Verified 5h ago · Changed 7h ago
AWS Bedrock
deepseek.v3-v1:0
standardQuantization not disclosed
$0.58$1.68—$0.855
Unverified (via models.dev)
Verified 7h ago · Changed 7h ago

Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.

Monthly cost estimate

DeepInfra fp4$44/mo
AWS Bedrock $91.6/mo

Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.