Cheapest verified cached-input token prices
Rank published cache-read or cached-input prices per 1M tokens. Models without a verified cached-input rate are excluded.
10 currently eligible offerings · Latest source verification:
How this ranking works
Only verified USD input/output quotes qualify. Sorted by the published cache-read or cached-input rate per 1M tokens. Models without that verified field are excluded; cache-write charges and eligibility conditions can still apply. Equal values share a rank; slug order only breaks display ties. Affiliate status never affects order.
Coverage is our database, not every API on the market. Default non-batch tiers apply, including DeepSeek peak rates and fixed OpenRouter backend quotes. Cache-write costs, long-context surcharges, optional tools, hosting conditions and tokenizers can change your bill. Compare all tiers and source terms before choosing.
| Rank | Model / Provider | Input / 1M | Output / 1M | Cached input / 1M | Last verified / Source |
|---|---|---|---|---|---|
| 1 | Amazon Nova Micro · Bedrock us-east-1Amazon Bedrock | $0.035 | $0.14 | $0.0088 | Official source |
| 2 | Amazon Nova Lite · Bedrock us-east-1Amazon Bedrock | $0.06 | $0.24 | $0.015 | Official source |
| 3 | Gemini 3.1 Flash-LiteGoogle | $0.25 | $1.50 | $0.025 | Official source |
| 4 | DeepSeek V4 ProDeepSeek | $1.32 | $3.96 | $0.044 | Official source |
| 5 | Amazon Nova 2.0 Lite · Bedrock us-east-1Amazon Bedrock | $0.33 | $2.75 | $0.0825 | Official source |
| 6 | Amazon Nova Pro · Bedrock us-east-1Amazon Bedrock | $0.80 | $3.20 | $0.20 | Official source |
| 6 | Grok 4.3xAI | $1.25 | $2.50 | $0.20 | Official source |
| 8 | Grok 4.5xAI | $2.00 | $6.00 | $0.30 | Official source |
| 9 | Grok 4.6xAI | $2.00 | $6.00 | $0.50 | Official source |
| 10 | Amazon Nova Premier · Bedrock us-east-1Amazon Bedrock | $2.50 | $12.50 | $0.625 | Official source |
Your workload may change the ranking
Set your actual input and output volumes to compare total costs.
Open cost calculatorCompare models