DeepSeek V3.2 deepseek/deepseek-v3.2
Served by 17 providers. Cheapest: Atlas Cloud at $0.29 blended /1M tokens. The most expensive listing costs 11.6× as much for the same model.
| Provider | Type | Input /1M | Output /1M | Cached input | Blended | Context | Notes | Source |
|---|---|---|---|---|---|---|---|---|
| Atlas Cloud deepseek-ai/deepseek-v3.2 |
Inference hosts | $0.26 | $0.38 | $0.13 | $0.29 | 164k | fp8 |
✓ src 2026-09-18 |
| DeepInfra deepseek-ai/DeepSeek-V3.2 |
Inference hosts | $0.26 | $0.38 | $0.13 | $0.29 | 164k | fp4 |
✓ src src2 2026-09-18 |
| SiliconFlow deepseek-ai/DeepSeek-V3.2 |
Inference hosts | $0.259 | $0.42 | — | $0.299 | 164k | fp8 not listed on siliconflow.com/pricing; price as shown by OpenRouter for its SiliconFlow endpoint |
2° src 2026-09-18 |
| Featherless deepseek-ai/DeepSeek-V3.2 |
Inference hosts | $0.264 | $0.41 | $0.06 | $0.30 | 131k | Developer-plan per-token rate; model_class deepseek-v3.2; also usable flat-rate on $25/mo Chat plan (32K ctx, human chat only) |
✓ src src2 src3 2026-09-18 |
| Novita AI deepseek/deepseek-v3.2 |
Inference hosts | $0.269 | $0.40 | $0.135 | $0.302 | 164k |
✓ src src2 2026-09-18 |
|
| OpenRouter deepseek/deepseek-v3.2 |
LLM routers | $0.269 | $0.40 | $0.135 | $0.302 | 164k | api modality text->text |
✓ src 2026-09-18 |
| Requesty novita/deepseek/deepseek-v3.2 |
LLM routers | $0.269 | $0.40 | $0.135 | $0.302 | 164k | fp8 upstream route novita; geo global; 1 other upstream routes listed (input $0.56-$0.56/M); API list price; Requesty's 5% markup on model cost (pricing page) is not included |
✓ src 2026-09-18 |
| GMI Cloud Inference Engine deepseek-ai/DeepSeek-V3.2 |
Inference hosts | $0.29 | $0.43 | — | $0.325 | — | list price; currently discounted to $0.2088 in / $0.3096 out (28% off, effective 2026-04-10); from GMI console public pricing API (console is client-rendered; docs say prices live in console Model Hub) |
✓ src src2 2026-09-18 |
| Venice.ai API deepseek-v3.2 |
Inference hosts | $0.33 | $0.48 | $0.16 | $0.367 | 160k |
✓ src src2 2026-09-18 |
|
| DigitalOcean deepseek-3.2 |
Inference hosts | $0.25 | $0.80 | $0.075 | $0.388 | 164k |
✓ src src2 2026-09-18 |
|
| FriendliAI deepseek-ai/DeepSeek-V3.2 |
Inference hosts | $0.50 | $1.50 | $0.25 | $0.75 | 164k | context from pricing page embedded model data |
✓ src 2026-09-18 |
| Google Vertex AI (Gemini Enterprise Agent Platform) | Hyperscaler AI platforms | $0.56 | $1.68 | $0.056 | $0.84 | — | batch −50% Managed MaaS API. Batch $0.28/$0.84. |
✓ src 2026-09-18 |
| Microsoft Foundry (Azure AI Foundry / Azure OpenAI) DeepSeek-V3.2 |
Hyperscaler AI platforms | $0.58 | $1.68 | — | $0.855 | — | Global Standard, Azure Retail Prices API meter 'V3.2 Inp glbl Tokens' (eastus); API meter is per 1K tokens, multiplied by 1000 (unit conversion only) |
✓ src src2 2026-09-18 |
| Amazon Bedrock deepseek.v3.2 |
Hyperscaler AI platforms | $0.62 | $1.85 | — | $0.927 | 164k | batch −50% |
✓ src src2 2026-09-18 |
| Chutes deepseek-ai/DeepSeek-V3.2-TEE |
Inference hosts | $1 | $1 | $0.10 | $1 | 131k | fp8 TEE (confidential compute); upstream weights deepseek-ai/DeepSeek-V3.2 |
✓ src src2 2026-09-18 |
| Inference.net deepseek-v3.2 |
Inference hosts | $0.70 | $2 | $0.35 | $1.02 | 164k | https://inference.net/models shows the same figures |
✓ src 2026-09-18 |
| SambaNova Cloud (SambaCloud) DeepSeek-V3.2 |
Inference hosts | $3 | $4.50 | — | $3.38 | 32k | Preview model; context 32k |
✓ src src2 2026-09-18 |
✓ from the provider's own pricing page · ◐ partly confirmed there · 2° third-party source. Router prices may exclude the router's own fees; see each router's page.