Modellverzeichnis
Entdecke Live-Verfügbarkeit, Preise, Endpoint-Support und Modell-Detailseiten.
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.
Mehr erfahrenAlle Modelle
85 Modelle gefunden| Modell | Offiziell | Unser Preis | Rabatt | Kontext | Latenz | Gesundheitswert |
|---|---|---|---|---|---|---|
 gpt-6-astraOpenAINew release | Input$10per 1M tokensOutput$50per 1M tokensCache$1per 1M tokens | Input$8per 1M tokensOutput$40per 1M tokensCache$0.8per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-6-solOpenAINew release | Input$2per 1M tokensOutput$10per 1M tokensCache$0.2per 1M tokens | Input$1.6per 1M tokensOutput$8per 1M tokensCache$0.16per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-6-lunaOpenAINew release | Input$0.1per 1M tokensOutput$0.5per 1M tokensCache$0.01per 1M tokens | Input$0.08per 1M tokensOutput$0.4per 1M tokensCache$0.008per 1M tokens | -20.0% ↓ | — | 600ms | |
 claude-opus-5-5AnthropicNew release | Input$4per 1M tokensOutput$20per 1M tokensCache—per 1M tokens | Input$3.2per 1M tokensOutput$16per 1M tokensCache—per 1M tokens | -20.0% ↓ | — | 600ms | |
 typesafe/jev-1.13TypeSafe AIHOT | Input$0.042per 1M tokensOutput$0per 1M tokensCache—per 1M tokens | Input$0.0336per 1M tokensOutput$0per 1M tokensCache—per 1M tokens | -20.0% ↓ | — | 600ms | |
 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 | |
| claude-fable-5.1AnthropicNew release | Input$10per 1M tokensOutput$50per 1M tokensCache$0.25per 1M tokens | Input$8per 1M tokensOutput$40per 1M tokensCache$0.2per 1M tokens | -20.0% ↓ | — | 600ms | |
| claude-fable-5Anthropic · ClaudeHOT | Input$10per 1M tokensOutput$50per 1M tokensCache$1per 1M tokens | Input$9per 1M tokensOutput$45per 1M tokensCache$0.9per 1M tokens | -10.0% ↓ | 1M | 600ms | |
 seedance-2.5ByteDance · SeedanceHOT | from$0.084per second | from$0.084per second | -0.0% ↓ | — | 600ms | |
| seedance-2.0-proByteDance · SeedanceHOT | from$0.041312per second | from$0.037181per second | -10.0% ↓ | — | 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 | |
| gpt-5.6-solOpenAI · GPTHOT | Input$4per 1M tokensOutput$24per 1M tokensCache$0.4per 1M tokens | Input$3.2per 1M tokensOutput$19.2per 1M tokensCache$0.32per 1M tokens | -20.0% ↓ | 1M | 600ms | |
 glm-5.3Zhipu AI · GLMNew release | Input$1.4per 1M tokensOutput$4.4per 1M tokensCache$0.26per 1M tokens | Input$1.12per 1M tokensOutput$3.52per 1M tokensCache$0.208per 1M tokens | -20.0% ↓ | 1M | 600ms | |
 kimi-k3Moonshot AI · KimiHOT | Input$3per 1M tokensOutput$15per 1M tokensCache$0.3per 1M tokens | Input$2.4per 1M tokensOutput$12per 1M tokensCache$0.24per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| gpt-image-2.5-flareOpenAINew release | Input$5per 1M tokensOutput$30per 1M tokensCache$2per 1M tokens | Input$4per 1M tokensOutput$24per 1M tokensCache$1.6per 1M tokens | -20.0% ↓ | — | 600ms | |
 qwen3.8-max-primeQwenNew release | Input$5per 1M tokensOutput$15per 1M tokensCache$0.625per 1M tokens | Input$4per 1M tokensOutput$12per 1M tokensCache$0.5per 1M tokens | -20.0% ↓ | — | 600ms | |
| glm-5.3-primeZ.aiNew release | Input$3.5per 1M tokensOutput$11per 1M tokensCache—per 1M tokens | Input$2.8per 1M tokensOutput$8.8per 1M tokensCache—per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-6-luna-proOpenAINew release | Input$0.125per 1M tokensOutput$0.625per 1M tokensCache$0.0125per 1M tokens | Input$0.1per 1M tokensOutput$0.5per 1M tokensCache$0.01per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-image-2.5-sunburstOpenAINew release | Input$5per 1M tokensOutput$30per 1M tokensCache—per 1M tokens | Input$4per 1M tokensOutput$24per 1M tokensCache—per 1M tokens | -20.0% ↓ | — | 600ms | |
| claude-opus-5Anthropic · ClaudeHOT | Input$5per 1M tokensOutput$25per 1M tokensCache$0.5per 1M tokens | Input$4per 1M tokensOutput$20per 1M tokensCache$0.4per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| claude-sonnet-5Anthropic · ClaudeHOT | Input$2per 1M tokensOutput$10per 1M tokensCache$0.2per 1M tokens | Input$1.6per 1M tokensOutput$8per 1M tokensCache$0.16per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| claude-opus-4-8Anthropic · ClaudeHOT | Input$5per 1M tokensOutput$25per 1M tokensCache$0.5per 1M tokens | Input$4per 1M tokensOutput$20per 1M tokensCache$0.4per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| claude-opus-4-7Anthropic · ClaudeHOT | Input$5per 1M tokensOutput$25per 1M tokensCache$0.5per 1M tokens | Input$4per 1M tokensOutput$20per 1M tokensCache$0.4per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| claude-sonnet-4-6Anthropic · ClaudeHOT | Input$3per 1M tokensOutput$15per 1M tokensCache$0.3per 1M tokens | Input$2.4per 1M tokensOutput$12per 1M tokensCache$0.24per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| claude-haiku-4-5-20251001Anthropic · ClaudeHOT | Input$1per 1M tokensOutput$5per 1M tokensCache$0.1per 1M tokens | Input$0.8per 1M tokensOutput$4per 1M tokensCache$0.08per 1M tokens | -20.0% ↓ | 200K | 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 | |
| seedance-2.0-fastByteDance · Seedance | from$0.031705per second | from$0.028535per second | -10.0% ↓ | — | 600ms | |
| seedance-2.0-miniByteDance · Seedance | from$0.020176per second | from$0.018158per second | -10.0% ↓ | — | 600ms | |
| claude-opus-4-6Anthropic · Claude | Input$5per 1M tokensOutput$25per 1M tokensCache$0.5per 1M tokens | Input$4per 1M tokensOutput$20per 1M tokensCache$0.4per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| gpt-4o-brOpenAI | Input$2.5per 1M tokensOutput$10per 1M tokensCache$1.25per 1M tokens | Input$2per 1M tokensOutput$8per 1M tokensCache$1per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-4o-mini-brOpenAI | Input$0.15per 1M tokensOutput$0.6per 1M tokensCache$0.08per 1M tokens | Input$0.12per 1M tokensOutput$0.48per 1M tokensCache$0.064per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-4.1-mini-brOpenAI | Input$0.4per 1M tokensOutput$1.6per 1M tokensCache$0.1per 1M tokens | Input$0.32per 1M tokensOutput$1.28per 1M tokensCache$0.08per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-4.1-mini-fkOpenAI | Input$0.4per 1M tokensOutput$1.6per 1M tokensCache$0.1per 1M tokens | Input$0.32per 1M tokensOutput$1.28per 1M tokensCache$0.08per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-5.4-nano-fkOpenAI | Input$0.2per 1M tokensOutput$1.25per 1M tokensCache$0.02per 1M tokens | Input$0.16per 1M tokensOutput$1per 1M tokensCache$0.016per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-5.6-luna-fkOpenAI | Input$0.2per 1M tokensOutput$1.2per 1M tokensCache$0.02per 1M tokens | Input$0.16per 1M tokensOutput$0.96per 1M tokensCache$0.016per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-5.4-fkOpenAI | Input$2.5per 1M tokensOutput$15per 1M tokensCache$0.25per 1M tokens | Input$2per 1M tokensOutput$12per 1M tokensCache$0.2per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-5-mini-fkOpenAI | Input$0.25per 1M tokensOutput$2per 1M tokensCache$0.025per 1M tokens | Input$0.2per 1M tokensOutput$1.6per 1M tokensCache$0.02per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-5.4-mini-fkOpenAI | Input$0.75per 1M tokensOutput$4.5per 1M tokensCache$0.075per 1M tokens | Input$0.6per 1M tokensOutput$3.6per 1M tokensCache$0.06per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-5.5-fkOpenAI | Input$5per 1M tokensOutput$30per 1M tokensCache$0.5per 1M tokens | Input$4per 1M tokensOutput$24per 1M tokensCache$0.4per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-4o-fkOpenAI | Input$2.5per 1M tokensOutput$10per 1M tokensCache$1.25per 1M tokens | Input$2per 1M tokensOutput$8per 1M tokensCache$1per 1M tokens | -20.0% ↓ | — | 600ms | |
| gpt-5.6-sol-fkOpenAI | Input$5per 1M tokensOutput$30per 1M tokensCache$0.5per 1M tokens | Input$4per 1M tokensOutput$24per 1M tokensCache$0.4per 1M tokens | -20.0% ↓ | — | 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 | |
| glm-5.2Zhipu AI · GLM | Input$1.4per 1M tokensOutput$4.4per 1M tokensCache$0.26per 1M tokens | Input$1.12per 1M tokensOutput$3.52per 1M tokensCache$0.208per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| glm-5.1Zhipu AI · GLM | Input$1.4per 1M tokensOutput$4.4per 1M tokensCache$0.26per 1M tokens | Input$1.12per 1M tokensOutput$3.52per 1M tokensCache$0.208per 1M tokens | -20.0% ↓ | 205K | 600ms | |
| glm-5Zhipu AI · GLM | Input$1per 1M tokensOutput$3.2per 1M tokensCache$0.2per 1M tokens | Input$0.8per 1M tokensOutput$2.56per 1M tokensCache$0.16per 1M tokens | -20.0% ↓ | 205K | 600ms | |
| glm-5-turboZhipu AI · GLM | Input$1.2per 1M tokensOutput$4per 1M tokensCache$0.24per 1M tokens | Input$0.96per 1M tokensOutput$3.2per 1M tokensCache$0.192per 1M tokens | -20.0% ↓ | 205K | 600ms | |
| glm-4.7Zhipu AI · GLM | Input$0.6per 1M tokensOutput$2.2per 1M tokensCache$0.11per 1M tokens | Input$0.48per 1M tokensOutput$1.76per 1M tokensCache$0.088per 1M tokens | -20.0% ↓ | 205K | 600ms | |
| gpt-5.6-lunaOpenAI · GPT | Input$0.2per 1M tokensOutput$1.2per 1M tokensCache$0.02per 1M tokens | Input$0.16per 1M tokensOutput$0.96per 1M tokensCache$0.016per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| gpt-5.5OpenAI · GPT | Input$5per 1M tokensOutput$30per 1M tokensCache$0.5per 1M tokens | Input$4per 1M tokensOutput$24per 1M tokensCache$0.4per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| gpt-4o-miniOpenAI · GPT | Input$0.15per 1M tokensOutput$0.6per 1M tokensCache$0.08per 1M tokens | Input$0.12per 1M tokensOutput$0.48per 1M tokensCache$0.064per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| gpt-5.4-miniOpenAI · GPT | Input$0.75per 1M tokensOutput$4.5per 1M tokensCache$0.075per 1M tokens | Input$0.6per 1M tokensOutput$3.6per 1M tokensCache$0.06per 1M tokens | -20.0% ↓ | 400K | 600ms | |
| gpt-5.6-terraOpenAI · GPT | Input$2per 1M tokensOutput$12per 1M tokensCache$0.2per 1M tokens | Input$1.6per 1M tokensOutput$9.6per 1M tokensCache$0.16per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| gpt-5.4OpenAI · GPT | Input$2.5per 1M tokensOutput$15per 1M tokensCache$0.25per 1M tokens | Input$2per 1M tokensOutput$12per 1M tokensCache$0.2per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| gpt-image-2OpenAI · GPT | $0.011per image | $0.0088per image | -20.0% ↓ | — | 600ms | |
| gpt-5-miniOpenAI · GPT | Input$0.25per 1M tokensOutput$2per 1M tokensCache$0.025per 1M tokens | Input$0.2per 1M tokensOutput$1.6per 1M tokensCache$0.02per 1M tokens | -20.0% ↓ | 400K | 600ms | |
| gpt-5.4-nanoOpenAI · GPT | Input$0.2per 1M tokensOutput$1.25per 1M tokensCache$0.02per 1M tokens | Input$0.16per 1M tokensOutput$1per 1M tokensCache$0.016per 1M tokens | -20.0% ↓ | 400K | 600ms | |
| gpt-4oOpenAI · GPT | Input$2.5per 1M tokensOutput$10per 1M tokensCache$1.25per 1M tokens | Input$2per 1M tokensOutput$8per 1M tokensCache$1per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| gpt-4.1-miniOpenAI · GPT | Input$0.4per 1M tokensOutput$1.6per 1M tokensCache$0.1per 1M tokens | Input$0.32per 1M tokensOutput$1.28per 1M tokensCache$0.08per 1M tokens | -20.0% ↓ | 1M | 600ms | |
 grok-imagine-image-proxAI · Grok | $0.05per image | $0.04per image | -20.0% ↓ | — | 600ms | |
| grok-imagine-video-1.5xAI · Grok | $0.11per second | $0.088per second | -20.0% ↓ | — | 600ms | |
| grok-imagine-videoxAI · Grok | $0.09per second | $0.072per second | -20.0% ↓ | — | 600ms | |
| kimi-k2.6Moonshot AI · Kimi | Input$0.95per 1M tokensOutput$4per 1M tokensCache$0.16per 1M tokens | Input$0.76per 1M tokensOutput$3.2per 1M tokensCache$0.128per 1M tokens | -20.0% ↓ | 262K | 600ms | |
| kimi-k2.5Moonshot AI · Kimi | Input$0.6per 1M tokensOutput$3per 1M tokensCache$0.1per 1M tokens | Input$0.48per 1M tokensOutput$2.4per 1M tokensCache$0.08per 1M tokens | -20.0% ↓ | 262K | 600ms | |
 macaron-v1-coding-ventiMacaron · Macaron | Input$5.2per 1M tokensOutput$18.2per 1M tokensCache$1.3per 1M tokens | Input$4.16per 1M tokensOutput$14.56per 1M tokensCache$1.04per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| macaron-v1-ventiMacaron · Macaron | Input$7per 1M tokensOutput$25per 1M tokensCache$2per 1M tokens | Input$5.6per 1M tokensOutput$20per 1M tokensCache$1.6per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| macaron-v1-tallMacaron · Macaron | Input$1.8per 1M tokensOutput$10per 1M tokensCache$0.2per 1M tokens | Input$1.44per 1M tokensOutput$8per 1M tokensCache$0.16per 1M tokens | -20.0% ↓ | 262K | 600ms | |
 MiniMax-H3MiniMax · MiniMax | from$0.08per second | from$0.08per second | -0.0% ↓ | — | 600ms | |
| minimax-m2.7MiniMax · MiniMax | Input$0.3per 1M tokensOutput$1.2per 1M tokensCache$0.06per 1M tokens | Input$0.24per 1M tokensOutput$0.96per 1M tokensCache$0.048per 1M tokens | -20.0% ↓ | 205K | 600ms | |
| minimax-m2.5MiniMax · MiniMax | Input$0.3per 1M tokensOutput$1.2per 1M tokensCache$0.03per 1M tokens | Input$0.24per 1M tokensOutput$0.96per 1M tokensCache$0.024per 1M tokens | -20.0% ↓ | 205K | 600ms | |
| minimax-m2MiniMax · MiniMax | Input$0.3per 1M tokensOutput$1.2per 1M tokensCache$0.3per 1M tokens | Input$0.24per 1M tokensOutput$0.96per 1M tokensCache$0.24per 1M tokens | -20.0% ↓ | 205K | 600ms | |
| qwen3.8-maxAlibaba · Qwen | Input$2per 1M tokensOutput$6per 1M tokensCache$0.25per 1M tokens | Input$1.6per 1M tokensOutput$4.8per 1M tokensCache$0.2per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| qwen3.7-maxAlibaba · Qwen | Input$2.5per 1M tokensOutput$2.5per 1M tokensCache—per 1M tokens | Input$2per 1M tokensOutput$2per 1M tokensCache—per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| qwen3.7-plusAlibaba · Qwen | Input$0.4per 1M tokensOutput$1.6per 1M tokensCache$0.08per 1M tokens | Input$0.32per 1M tokensOutput$1.28per 1M tokensCache$0.064per 1M tokens | -20.0% ↓ | 256K | 600ms | |
| qwen3.6-max-previewAlibaba · Qwen | Input$1.3per 1M tokensOutput$7.8per 1M tokensCache$0.13per 1M tokens | Input$1.04per 1M tokensOutput$6.24per 1M tokensCache$0.104per 1M tokens | -20.0% ↓ | 1M | 600ms | |
| qwen3.6-plusAlibaba · Qwen | Input$0.5per 1M tokensOutput$3per 1M tokensCache$0.05per 1M tokens | Input$0.4per 1M tokensOutput$2.4per 1M tokensCache$0.04per 1M tokens | -20.0% ↓ | 256K | 600ms | |
| qwen3.5-27bAlibaba · Qwen | Input$0.3per 1M tokensOutput$2.4per 1M tokensCache—per 1M tokens | Input$0.24per 1M tokensOutput$1.92per 1M tokensCache—per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| qwen3.5-397b-a17bAlibaba · Qwen | Input$0.588per 1M tokensOutput$3.528per 1M tokensCache—per 1M tokens | Input$0.4704per 1M tokensOutput$2.8224per 1M tokensCache—per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| qwen3.5-plusAlibaba · Qwen | Input$0.4per 1M tokensOutput$2.4per 1M tokensCache$0.04per 1M tokens | Input$0.32per 1M tokensOutput$1.92per 1M tokensCache$0.032per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| qwen3.5-flashAlibaba · Qwen | Input$0.1per 1M tokensOutput$0.4per 1M tokensCache—per 1M tokens | Input$0.08per 1M tokensOutput$0.32per 1M tokensCache—per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| qwen3.5-35b-a3bAlibaba · Qwen | Input$0.245per 1M tokensOutput$1.96per 1M tokensCache—per 1M tokens | Input$0.196per 1M tokensOutput$1.568per 1M tokensCache—per 1M tokens | -20.0% ↓ | 128K | 600ms | |
| seedance-2.0ByteDance · Seedance | from$0.041312per second | from$0.037181per second | -10.0% ↓ | — | 600ms | |
 sonilo-video-to-musicSonilo · Sonilo | $0.009per request | $0.0072per request | -20.0% ↓ | — | 600ms |