LLM-API-Preistabelle
Listenpreise pro 1 Million Tokens. Klicken Sie auf eine Spalte zum Sortieren oder auf ein Modell, um seinen Kostenrechner zu öffnen.
| Features | ||||||
|---|---|---|---|---|---|---|
| Claude Fable 5.2 | Anthropic | $8.00 | $0.20 | $40.00 | 1M | ReasoningBatch |
| Claude Opus 5.5 | Anthropic | $4.00 | $0.20 | $20.00 | 1M | ReasoningBatch |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $0.10 | $10.00 | 1M | ReasoningBatch |
| Claude Haiku 4.5 | Anthropic | $1.00 | $0.10 | $5.00 | 195K | ReasoningBatch |
| Claude Haiku 5.5 | Anthropic | $0.10 | $0.01 | $0.50 | 1M | ReasoningBatch |
| GPT-6.2 Astra | OpenAI | $8.00 | $0.40 | $40.00 | 1.05M | ReasoningBatch |
| GPT-6.2 Sol | OpenAI | $2.00 | $0.10 | $10.00 | 1.05M | ReasoningBatch |
| o3 | OpenAI | $2.00 | $0.50 | $8.00 | 195K | ReasoningBatch |
| GPT-6.1 Terra | OpenAI | $1.00 | $0.05 | $5.00 | 1.05M | ReasoningBatch |
| GPT-4o mini | OpenAI | $0.15 | $0.075 | $0.60 | 125K | Batch |
| gpt-oss-120b | OpenAI · Together | $0.15 | — | $0.60 | 128K | Reasoningoffen |
| GPT-6 Luna | OpenAI | $0.10 | $0.01 | $0.50 | 1.05M | ReasoningBatch |
| gpt-oss-20b | OpenAI · Together | $0.05 | — | $0.20 | 128K | Reasoningoffen |
| Gemini 4 Neon | $3.00 | $0.15 | $15.00 | 1M | ReasoningBatch | |
| Gemini 4 Carbon | $2.00 | $0.10 | $10.00 | 1M | ReasoningBatch | |
| Gemini 4 Hydrogen | $1.50 | $0.075 | $7.50 | 1M | ReasoningBatch | |
| Gemini 3.8 Flash | $0.75 | $0.075 | $3.75 | 1M | ReasoningBatch | |
| Gemini 3.5 Flash-Lite | $0.30 | $0.03 | $2.50 | 1M | ReasoningBatch | |
| DeepSeek V4 Pro | DeepSeek | $1.32 | $0.044 | $3.96 | 1M | Reasoning |
| DeepSeek V4 Pro (open weights) | DeepSeek · DeepInfra | $1.30 | $0.10 | $2.60 | 1.05M | Reasoningoffen |
| DeepSeek R1-0528 | DeepSeek · DeepInfra | $0.50 | $0.35 | $2.15 | 160K | Reasoningoffen |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $0.006 | $1.20 | 1M | Reasoning |
| DeepSeek V3.2 | DeepSeek · DeepInfra | $0.26 | $0.13 | $0.38 | 160K | Reasoningoffen |
| DeepSeek V4 Flash (open weights) | DeepSeek · DeepInfra | $0.09 | $0.018 | $0.18 | 1.05M | Reasoningoffen |
| Grok 4.7 | xAI | $2.00 | $0.50 | $6.00 | 488K | Reasoning |
| Grok 4.3 | xAI | $1.25 | $0.20 | $2.50 | 1M | Reasoning |
| Grok 4.20 (non-reasoning) | xAI | $1.25 | $0.20 | $2.50 | 1M | |
| Grok Build 0.1 | xAI | $1.00 | $0.20 | $2.00 | 488K | Reasoning |
| Llama 3.3 70B Instruct | Meta · DeepInfra | $0.10 | — | $0.32 | 128K | offen |
| Llama 4 Scout 17B-16E | Meta · DeepInfra | $0.10 | — | $0.30 | 320K | offen |
| Llama 3.1 8B Instruct | Meta · DeepInfra | $0.02 | — | $0.04 | 128K | offen |
| Qwen3.5-397B-A17B | Alibaba · DeepInfra | $0.45 | $0.22 | $3.00 | 256K | Reasoningoffen |
| Qwen3-235B-A22B-Instruct-2507 | Alibaba · DeepInfra | $0.09 | — | $0.55 | 256K | offen |
| Qwen3 32B | Alibaba · DeepInfra | $0.08 | — | $0.28 | 40K | Reasoningoffen |
| Mistral Small 3.2 24B | Mistral · DeepInfra | $0.075 | — | $0.20 | 128K | offen |
USD pro 1 Mio. Tokens, Standard-Kontextstufe. Open-Weight-Preise sind typische Preise von Serverless-Hostern.
Weitere KI-Kostenrechner
$/token
LLM-API- & Agent-Kostenrechner
Kosten pro Anfrage, Monat und Jahr für über 30 Modelle vergleichen, inklusive Caching, Batch und Multi-Turn-Agents.
Rechner öffnen →GBGPU- & VRAM-Rechner
Sehen Sie genau, wie viel VRAM ein Modell braucht (Gewichte + KV-Cache + Overhead) und auf welche GPUs oder Macs es passt.
Rechner öffnen →$/minVoice-Agent-Kostenrechner
Kosten pro Minute und pro Anruf für Voice-Agent-Stacks aus STT + LLM + TTS + Telefonie.
Rechner öffnen →break-evenAPI vs. Self-Hosting: Break-Even
Finden Sie das monatliche Token-Volumen, ab dem eine gemietete dedizierte GPU günstiger ist als Abrechnung pro Token.
Rechner öffnen →