Models Directory
Discover live model availability, pricing, endpoint support, and model detail pages.
ReasoningCodingAgentsLong Context
Claude Opus 5.5
Claude Opus 5.5 is Anthropic's heaviest model — built for long, multi-step work that has to hold together. Deep reasoning, durable coding sessions, and agentic tool use, available on Flatkey with one key.
Learn MoreAll Models
7 models found| Model | Official | Our price | Discount | Context | Latency | Health score |
|---|---|---|---|---|---|---|
 deepseek-v4-1-flashDeepSeekNew release | Inputfrom$0.15per 1M tokensOutputfrom$0.6per 1M tokensCachefrom$0.003per 1M tokens | Inputfrom$0.12per 1M tokensOutputfrom$0.48per 1M tokensCachefrom$0.0024per 1M tokens | -20.0% ↓ | — | 600ms | |
| deepseek-v4-proDeepSeek · DeepSeekHOT | Inputfrom$0.66per 1M tokensOutputfrom$1.98per 1M tokensCachefrom$0.022per 1M tokens | Inputfrom$0.528per 1M tokensOutputfrom$1.584per 1M tokensCachefrom$0.0176per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| deepseek-v4-flashDeepSeek · DeepSeek | Inputfrom$0.22per 1M tokensOutputfrom$0.66per 1M tokensCachefrom$0.007per 1M tokens | Inputfrom$0.176per 1M tokensOutputfrom$0.528per 1M tokensCachefrom$0.0056per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| deepseek-v3.2-thinkingDeepSeek · DeepSeek | Input$0.29per 1M tokensOutput$0.42per 1M tokensCache$0.29per 1M tokens | Input$0.232per 1M tokensOutput$0.336per 1M tokensCache$0.232per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| deepseek-v3.2DeepSeek · DeepSeek | Input$0.266per 1M tokensOutput$0.444per 1M tokensCache$0.0266per 1M tokens | Input$0.2128per 1M tokensOutput$0.3552per 1M tokensCache$0.02128per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| deepseek-v3.1DeepSeek · DeepSeek | Input$0.21per 1M tokensOutput$0.79per 1M tokensCache$0.13per 1M tokens | Input$0.168per 1M tokensOutput$0.632per 1M tokensCache$0.104per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| deepseek-v3DeepSeek · DeepSeek | Input$0.4per 1M tokensOutput$1.3per 1M tokensCache$0.4per 1M tokens | Input$0.32per 1M tokensOutput$1.04per 1M tokensCache$0.32per 1M tokens | -20.0% ↓ | 128K | 600ms |