LLM API pricing
DeepSeek v3.2 vs gpt-oss-120b: price per 1M tokens
Updated 2026-10-14
DeepSeek v3.2 costs $0.62 / $1.85 per 1M input/output tokens (Amazon Bedrock (regional)) vs $0.15 / $0.6 for gpt-oss-120b (Amazon Bedrock (regional)). Blended 3:1, DeepSeek v3.2 is +253% vs gpt-oss-120b.
DeepSeek v3.2 by channel
| Channel | Input | Output | Cache read | Paid with |
|---|---|---|---|---|
| Amazon Bedrock (regional) | $0.62 | $1.85 | n/a | AWS credits |
gpt-oss-120b by channel
| Channel | Input | Output | Cache read | Paid with |
|---|---|---|---|---|
| Amazon Bedrock (regional) | $0.15 | $0.6 | n/a | AWS credits |
Worked examples (monthly bill at list price)
| Workload | DeepSeek v3.2 | gpt-oss-120b | Difference |
|---|---|---|---|
| Support chatbot: 100,000 × 1,000 in / 300 out | $117.50 | $33.00 | +256% |
| RAG over docs: 50,000 × 4,000 in / 500 out | $170.25 | $45.00 | +278% |
| Coding agent: 200,000 × 20,000 in / 2,000 out | $3,220.00 | $840.00 | +283% |
Tokens per $25,000 of credits
- DeepSeek v3.2 via Amazon Bedrock (regional) (AWS credits): 26.95B tokens
- gpt-oss-120b via Amazon Bedrock (regional) (AWS credits): 95.24B tokens
More
Cost calculator
Monthly bill: $117.5
Paid with AWS credits: 212.8 months of runway.
Related cost calculators
- Amazon Bedrock AgentCore Pricing Calculator · Runtime, Gateway, Memory & Policy Costs
- Bedrock Pricing Calculator · AI Model & Tool Cost Estimator
- Amazon SageMaker AI Pricing Calculator · On-Demand Studio, Training & Inference
Prices and credit amounts are estimates and may change. Check AWS for current terms.