API pricing per million tokens
deepseek-v3-2 Open weightsChecked 5h ago
- Input
- $0.209
- per 1M, GMICloud (fp8)
- Output
- $0.31
- per 1M tokens
- Cached input
- $0.022
- no batch tier listed
- Context
- 164K
- 66K max output
Where to buy it (15)
- GMICloudfp8, fp8$0.209 / $0.31cached $0.022
- StreamLakefp8, fp8$0.215 / $0.322cached $0.021
- AtlasCloudfp8, fp8$0.26 / $0.38cached $0.13
DeepInfrafp4, fp4$0.26 / $0.38cached $0.13
Venicedefault region$0.268 / $0.39cached $0.13
SiliconFlowfp8, fp8$0.259 / $0.42cached $0.135
Novita AIfp8, fp8$0.269 / $0.4cached $0.135
- Baidufp8, fp8$0.28 / $0.42cached $0.028
DigitalOceandefault region$0.3 / $0.96cached $0.09
Qwen (Alibaba)fp8, fp8$0.371 / $1.11cached $0.074
Friendlidefault region$0.5 / $1.5cached $0.25
Google Vertex AIdefault region$0.56 / $1.68$0.84 blended
- Phaladefault region$1 / $1cached $0.5
- Maradefault region$3 / $4.5$3.38 blended
SambaNovadefault region$3 / $4.5$3.38 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $27.07 direct.
Helicone$27.07+0%
Kong AI Gateway$27.07+0%
LiteLLM$27.07+0%
Vercel AI Gateway$27.07+0%
AWS Bedrock$27.07+0%
Azure AI Foundry$27.07+0%
Databricks Mosaic AI$27.07+0%
Hugging Face Inference$27.07+0%
Cloudflare AI Gateway$28.43+5%
Requesty$28.43+5%
Eden AI$28.56+5.5%
OpenRouter$28.56+5.5%
Snowflake Cortex AI$32.49+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
DeepSeek V4.1 FlashDeepSeek · 1M$0.15 / $0.6in / out per 1M$0.15$0.6$0.0031MSep 10, 2026
GPT-6 LunaOpenAI · 1.05M$0.1 / $0.5in / out per 1M$0.1$0.5$0.011.05MSep 22, 2026
Muse Spark 1.3 ContributorMeta · 1M$0.1 / $0.2in / out per 1M$0.1$0.2$0.0021MSep 2, 2026
About DeepSeek V3.2
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.
Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.234 per 1M tokens at 3 input to 1 output.
Across fru.devCompany profile
Questions
How much does DeepSeek V3.2 cost?
$0.209 per million input tokens and $0.31 per million output tokens, with cached input at $0.022.
What is the context window of DeepSeek V3.2?
164K tokens, with up to 66K tokens of output.
Where is DeepSeek V3.2 cheapest?
Of 15 routes tracked, GMICloud is cheapest at $0.209 input and $0.31 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.