Skip to content

Listings

All listings for DeepSeek V3.2

Every priced listing we track for this model. Back to DeepSeek V3.2

ProviderMax Input TokensInput $/1MOutput $/1M$/input imageTok/sLatency
Run by the model's maker
 DeepSeek
deepseek-v3.2Sources: GenAI Prices data, LiteLLM data
Data from GenAI Prices
Fields by sourceFrom LiteLLM: context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports prompt caching, supports reasoning, supports assistant prefill, max input tokens, max output tokens, cache-read price
164K$0.2288cache read $0.028$0.3432———
 Amazon Web Servicesdeepseek.v3.2Sources: AWS Bedrock Runtime data, LiteLLM data, Models.dev data
Data from AWS Bedrock Runtime
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported endpoints, supports function calling, supports tool choice, supports response schema, supports batching, supports reasoning, supports audio input, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, input tokens batch, output tokens batchFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
156K$0.62batch $0.31$1.85batch $0.925———
 Amazon Web ServicesRegions: 🇺🇸 usus.deepseek.v3.2Source: LiteLLM data
Data from LiteLLM
164K$0.62batch $0.31$1.85batch $0.925———
 Amazon Web ServicesRegions: 🇪🇺 eueu.deepseek.v3.2Source: LiteLLM data
Data from LiteLLM
164K$0.74$2.22———
 Microsoft Azureazure_ai/FW-DeepSeek-V3.2Sources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
164K$0.62cache read $0.31$1.85———
 GoogleRegions: globalvertex_ai/deepseek-ai/deepseek-v3.2-maas · maasSources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
164K$0.56cache read $0.056batch $0.28$1.68batch $0.84———
 302aiPro/deepseek-ai/DeepSeek-V3.2Sources: 302.ai data, Models.dev data
Data from 302.ai
Fields by sourceFrom Models.dev: max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
160K$0.286$0.429———
 Aihubmixdeepseek-v3.2Source: AIHubMix data docs
Data from AIHubMix
164K$0.58$1.68———
 Atlasclouddeepseek-ai/deepseek-v3.2Source: AtlasCloud data
Data from AtlasCloud
164K$0.26cache read $0.13$0.38———
 Cortecs AIdeepseek-v3.2Sources: Cortecs EU Router data, Models.dev data
Data from Cortecs EU Router
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, max input tokens, max output tokens, supports image input
164K
€0.449cache read €0.135
≈ $0.4927 USD (compared by USD value)
€1.346
≈ $1.4771 USD (compared by USD value)
———
 Eurouterdeepseek-v3.2Source: EURouter data
Data from EURouter
164K$0.30cache read $0.075$0.50———
 Fastrouterdeepseek/deepseek-v3.2Source: FastRouter data
Data from FastRouter
164K$0.26cache read $0.13$0.38———
 Flowdotdeepseek-ai/DeepSeek-V3.2Source: FlowDot data
Data from FlowDot
164K$0.26$0.38———
 Hugging FaceInference by DeepInfradeepseek-ai/DeepSeek-V3.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
164K$0.26$0.38———
 Hugging FaceInference by Novita AIdeepseek-ai/DeepSeek-V3.2Source: GenAI Prices data
Data from GenAI Prices
164K$0.269$0.40———
 Hugging Facedeepseek-ai/DeepSeek-V3.2Source: Models.dev data
Data from Models.dev
164K$0.28$0.40———
 Hugging FaceInference by Digitaloceandeepseek-ai/DeepSeek-V3.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
164K$0.30$0.96———
 Kilodeepseek/deepseek-v3.2Sources: Kilo AI Gateway data, Models.dev data
Data from Kilo AI Gateway
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image inputFrom Kilo AI Gateway: output reasoning tokens, input images, web search cost, web search unit
164K$0.26cache read $0.13$0.38$0.00——
 LlmgatewayInference by DeepInfradeepseek-ai/DeepSeek-V3.2Source: LLMGateway data
Data from LLMGateway
Not published by the provider$0.26cache read $0.13$0.38———
 Llmgatewaydeepseek-v3.2Source: LLMGateway data
Data from LLMGateway
164K$0.26cache read $0.13$0.38———
 LlmgatewayInference by Novita AIdeepseek/deepseek-v3.2Source: LLMGateway data
Data from LLMGateway
Not published by the provider$0.269cache read $0.1345$0.40———
 LlmgatewayInference by DeepSeekdeepseek-chatSource: LLMGateway data
Data from LLMGateway
Not published by the provider$0.28cache read $0.028$0.42———
 LlmgatewayInference by Nebius AI Studiodeepseek-ai/DeepSeek-V3.2Source: LLMGateway data
Data from LLMGateway
Not published by the provider$0.30$0.45———
 LlmgatewayInference by Alibaba Clouddeepseek-v3.2Source: LLMGateway data
Data from LLMGateway
Not published by the provider$0.57cache read $0.114$1.71———
 Meganovadeepseek-ai/DeepSeek-V3.2Sources: MegaNova data, Models.dev data
Data from MegaNova
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, max input tokens, max output tokens, supports image input, cache-read price
164K$0.26cache read $0.13$0.38———
 NanoGPTdeepseek/deepseek-v3.2Sources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
163K$0.26cache read $0.13$0.38———
 NanoGPTdeepseek/deepseek-v3.2:thinking · thinkingSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
163K$0.26cache read $0.13$0.38———
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Distillation allowed — NanoGPT privacy policy
Inference by SiliconFlowRegions: 🇸🇬 SGdeepseek/deepseek-v3.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.272cache read $0.147$0.84—20.710,043ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: Distillation allowed — NanoGPT privacy policy
Inference by SiliconFlowRegions: 🇸🇬 SGdeepseek/deepseek-v3.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.272cache read $0.147$0.84—20.710,043ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by DeepInfraRegions: 🇺🇸 USdeepseek/deepseek-v3.2 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.273cache read $0.1365$0.399—33.31,319ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation allowed — NanoGPT privacy policy
Inference by DeepInfraRegions: 🇺🇸 USdeepseek/deepseek-v3.2:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.273cache read $0.1365$0.399—30.91,673ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Distillation allowed — NanoGPT privacy policy
Inference by BaiduRegions: 🇨🇳 CNdeepseek/deepseek-v3.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.294cache read $0.0294$0.441—30.42,113ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Distillation allowed — NanoGPT privacy policy
Inference by BaiduRegions: 🇨🇳 CNdeepseek/deepseek-v3.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.294cache read $0.0294$0.441—31.52,736ms
 NanoGPT
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
TEE/deepseek-v3.2 · teeSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
164K$1.00cache read $0.50$1.00———
 Nous Portaldeepseek/deepseek-v3.2Source: Nous Portal Inference Gateway data
Data from Nous Portal Inference Gateway
164K$0.26cache read $0.13$0.38———
 Openroute CnDeepSeek-V3.2思考模型Source: OpenRoute CN Marketplace
Data from OpenRoute CN Marketplace
128K
CN¥2.00
≈ $0.2988 USD (compared by USD value)
CN¥3.00
≈ $0.4482 USD (compared by USD value)
———
 OpenRouterInference by SiliconFlowdeepseek/deepseek-v3.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
164K$0.259cache read $0.14$0.80—171,972.5ms
 OpenRouterInference by DeepInfradeepseek/deepseek-v3.2 · fp4Source: OpenRouter data docs
Data from OpenRouter
164K$0.26cache read $0.13$0.38—30646ms
 OpenRouterdeepseek/deepseek-v3.2Sources: GenAI Prices data, Models.dev data, OpenRouter data docs
Data from OpenRouter
Fields by sourceFrom GenAI Prices: offering nameFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
164K$0.26cache read $0.13$0.38———
 OpenRouterInference by Baidudeepseek/deepseek-v3.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
131K$0.28cache read $0.028$0.42—271,248ms
 OpenRouterInference by Digitaloceandeepseek/deepseek-v3.2Source: OpenRouter data docs
Data from OpenRouter
164K$0.30cache read $0.09$0.96—361,170ms
 Redpill
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
deepseek/deepseek-v3.2Source: RedPill data
Data from RedPill
164K$1.00$1.00———
 RequestyInference by Googlevertex/deepseek-v3.2Source: Requesty data
Data from Requesty
164K$0.56cache read $0.056$1.68———
 Vercel
policy notes
AI Gateway uses zero data retention by default — Vercel AI Gateway security & compliance documentation It permanently deletes your prompts and responses after requests complete. — Vercel AI Gateway security & compliance documentation requests only route to providers with verified ZDR agreements — Vercel AI Gateway security & compliance documentation The provider allowlist lets team owners restrict which AI providers can serve requests through AI Gateway — Vercel AI Gateway security & compliance documentation Vercel may store, process and transmit your information outside of your country of residence, which may have different data protection laws and may not offer the same level of protection or guarantees as in your country or the country where you initially provided the information. — Vercel privacy policy Sources: Vercel AI Gateway security & compliance documentation, Vercel privacy policy
deepseek/deepseek-v3.2Sources: Models.dev data, Vercel AI Gateway data
Data from Vercel AI Gateway
Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
128K$0.62$1.85———
 Wavespeeddeepseek/deepseek-v3.2Source: WaveSpeed AI data
Data from WaveSpeed AI
164K$0.29cache read $0.03$0.43———
 Zenmuxdeepseek/deepseek-v3.2Sources: Models.dev data, ZenMux data
Data from ZenMux
Fields by sourceFrom Models.dev: max completion tokens, supports function calling, supports system messages, supports vision, max input tokens, max output tokens, supports image input
128K$0.293cache read $0.0293$0.4395———
 Abacusdeepseek-ai/DeepSeek-V3.2Source: Models.dev data
Data from Models.dev
128K$0.27$0.40———
 Alibaba Cloud (China)siliconflow/deepseek-v3.2Source: Models.dev data
Data from Models.dev
164K$0.27$0.42———
 Aviandeepseek/deepseek-v3.2Source: Avian.io Models data
Data from Avian.io Models
164K$0.23cache read $0.012$0.33———
 Chutes
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
deepseek-ai/DeepSeek-V3.2-TEE · tee · fp8Sources: Chutes data, Models.dev data
Data from Chutes
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, max input tokens, max output tokens, supports image input
131K$1.00cache read $0.10$1.00———
 DeepInfradeepseek-ai/DeepSeek-V3.2 · fp4Sources: DeepInfra data, LiteLLM data, Models.dev data
Data from DeepInfra
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, supports prompt caching, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, cache-read priceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image input
164K$0.26cache read $0.13$0.38———
 Digitaloceandeepseek-3.2Source: Models.dev data
Data from Models.dev
164K$0.50cache read $0.15$1.60———
 Fireworks AIdeepseek-v3p2Sources: GenAI Prices data, LiteLLM data
Data from GenAI Prices
Fields by sourceFrom LiteLLM: max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, supports reasoning, max input tokens, max output tokens
164K$0.56cache read $0.28$1.68———
 Gmiclouddeepseek-ai/DeepSeek-V3.2Sources: GMI Cloud data, LiteLLM data
Data from GMI Cloud
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, max input tokens, max output tokens, currency, last updated, input tokens, output tokens
164K$0.28$0.40———
 Ionetdeepseek-ai/DeepSeek-V3.2Source: IO Intelligence (io.net) data
Data from IO Intelligence (io.net)
164K$1.5018cache read $0.7509$2.2539—0.009129.067ms
 Llmgateway Providersdeepinfra/deepseek-v3.2Source: Models.dev data
Data from Models.dev
160K$0.26cache read $0.13$0.38———
 Merge Gatewaydeepseek/deepseek-v3.2Source: Models.dev data
Data from Models.dev
128K$0.28cache read $0.13$0.40———
 Netminddeepseek-ai/DeepSeek-V3.2Source: NetMind.AI
Data from NetMind.AI
160K$0.27$0.40———
 Novita AInovita/deepseek/deepseek-v3.2 · fp8Source: LiteLLM data
Data from LiteLLM
164K$0.269cache read $0.1345$0.40———
 Ofoxdeepseek/deepseek-v3.2Source: Models.dev data
Data from Models.dev
128K$0.29cache read $0.06$0.43———
 Phala
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
deepseek/deepseek-v3.2Source: Models.dev data
Data from Models.dev
164K$1.00cache read $0.50$1.00———
 Poenovita/deepseek-v3.2Source: Models.dev data
Data from Models.dev
128K$0.2626cache read $0.1313$0.3838———
 Qiniudeepseek/deepseek-v3.2-251201 · 251201Sources: Models.dev data, Qiniu AI data, Qiniu AI Model Plaza Pricing
Data from Qiniu AI
Fields by sourceFrom Qiniu AI Model Plaza Pricing: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, rate limits, currency, unit, last updated, input tokens, output tokens, cache-read price, input tokens batch, output tokens batchFrom Models.dev: supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
128K
CN¥2.00cache read CN¥0.20batch CN¥1.008
≈ $0.2988 USD (compared by USD value)
CN¥3.00batch CN¥1.512
≈ $0.4482 USD (compared by USD value)
———
 Runcratedeepseek-ai/DeepSeek-V3.2Source: Models.dev data
Data from Models.dev
164K$0.273cache read $0.1365$0.399———
 SambaNovasambanova/DeepSeek-V3.2Source: LiteLLM data
Data from LiteLLM
33K$3.00$4.50———
 SiliconFlowdeepseek-ai/DeepSeek-V3.2 · fp8Sources: Models.dev data, SiliconFlow data
Data from SiliconFlow
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, input tokens, output tokens, cache-read price, currency, currency basis, last updated
164K$0.27cache read $0.135$0.42———
 Siliconflow CnPro/deepseek-ai/DeepSeek-V3.2Source: Models.dev data
Data from Models.dev
164K$0.5978cache read $0.0598$0.8967———
 Tencent Lkeapdeepseek-v3.2Source: Tencent Cloud LKEAP Pricing
Data from Tencent Cloud LKEAP Pricing
Not published by the provider
CN¥2.00
≈ $0.2988 USD (compared by USD value)
CN¥3.00
≈ $0.4482 USD (compared by USD value)
———
 Tensorxdeepseek/deepseek-v3.2Source: Models.dev data
Data from Models.dev
164K$0.30cache read $0.075$0.50cache write $0.375———
 Tokengodeepseek/deepseek-v3.2Source: Models.dev data
Data from Models.dev
128K$0.2174cache read $0.06$0.326———
 Venice
private, per Venice.ai
Data privacy: private Source: Venice.ai
policy notes
privacy classification: private — Venice privacy documentation
deepseek-v3.2Source: Venice.ai data
Data from Venice.ai
160K$0.33cache read $0.16$0.48———
 Vivgriddeepseek-v3.2Source: Models.dev data
Data from Models.dev
128K$0.28cache read $0.03$0.42———

6 listings without a price are hidden.

Select any dotted value, label or icon to see where it comes from and how it is measured. How this data works