DeepSeek V4.1 Flash pricing

DeepSeek V4.1 Flash from DeepSeek runs on 11 providers. The lowest price is $0.112 input and $0.336 output per 1M tokens, on DeepInfra. On Together AI it costs 3.1× as much.

Updated

Lab
DeepSeek
Context
1.05M
Input
Text and images
Providers
11
What each provider chargesBlended price per 1M tokens, 3 parts input to 1 part output. The highest is 3.1× the lowest.
  1. DeepInfra$0.168Lowest
  2. CoreWeave$0.261.5×
  3. Cohere$0.3111.9×
  4. Novita AI$0.3412.0×
  5. Alibaba Cloud$0.3672.2×
  6. DigitalOcean$0.3942.3×
  7. Crusoe$0.5173.1×
  8. Fireworks AI$0.5253.1×
  9. Google Vertex AI$0.5253.1×
  10. Baseten$0.5253.1×
  11. Together AI$0.5253.1×

Every price, by provider

DeepSeek V4.1 Flash prices by provider, in US dollars per 1 million tokens
ProviderInputOutputCachedCache writeBatch inBatch outContextMax output
DeepInfrafp8$0.112$0.336$0.0034–$0.112$0.3361.05M393K
CoreWeavefp8$0.13$0.65$0.002–––1.05M944K
Coherefp8$0.195$0.66$0.003–––1.05M384K
Novita AIfp8$0.195$0.78$0.0039–––1.05M393K
Alibaba Cloud$0.21$0.84$0.0042–––1M393K
DigitalOcean$0.225$0.90$0.006–––1.05M944K
Crusoefp8$0.29$1.20$0.007–––1.05M944K
Fireworks AI$0.30$1.20$0.006–$0.15$0.601.05M944K
USRegion$0.45$1.80$0.009
SpotTier$0.21$0.84$0.0042
Google Vertex AI$0.30$1.20$0.03–––1.05M944K
Baseten$0.30$1.20$0.007–––1.05M262K
USRegion$0.30$1.20$0.007
Together AI$0.30$1.20$0.006–––1.05M944K

Prices in US dollars. Token prices are per 1 million tokens. abracadabra compiles them from each provider’s listing on OpenRouter, the LiteLLM price list and the providers’ own pricing pages, and refreshes them daily. The dataset is free to use: /api/ai-pricing.

See which tasks your agent finishes.

A price says what a call costs. abracadabra reads every conversation your agent has and shows the topics people bring, the tasks that get done and the turn where the rest stop.

Free to start, no card. Or open the playground (opens in a new tab).