AI / LLM
AI/LLM-Modelle & Preise
836 getrackte Modelle — Input/Output je 1 Mio. Token + Context-Window, nach Output-Preis sortiert. Quelle: LiteLLM-Preisdaten, jeweils zur offiziellen Preisseite verlinkt.
| Modell | Provider | Input $/1M | Output $/1M | Context | Quelle |
|---|---|---|---|---|---|
| gpt-4-turbo | openai | $10.00 | $30.00 | 128.000 | Pricing |
| gpt-4-turbo-2024-04-09 | openai | $10.00 | $30.00 | 128.000 | Pricing |
| gpt-4-turbo-preview | openai | $10.00 | $30.00 | 128.000 | Pricing |
| gpt-5.5 | openai | $5.00 | $30.00 | 1.050.000 | Pricing |
| gpt-5.5-2026-04-23 | openai | $5.00 | $30.00 | 1.050.000 | Pricing |
| gpt-5.6 | openai | $5.00 | $30.00 | 1.050.000 | Pricing |
| gpt-5.6-sol | openai | $5.00 | $30.00 | 1.050.000 | Pricing |
| ft:gpt-4-0613 | openai | $30.00 | $60.00 | 8.192 | Pricing |
| gpt-4 | openai | $30.00 | $60.00 | 8.192 | Pricing |
| gpt-4-0314 | openai | $30.00 | $60.00 | 8.192 | Pricing |
| gpt-4-0613 | openai | $30.00 | $60.00 | 8.192 | Pricing |
| o1 | openai | $15.00 | $60.00 | 200.000 | Pricing |
| o1-2024-12-17 | openai | $15.00 | $60.00 | 200.000 | Pricing |
| chat-bison | palm | $0.13 | $0.13 | 8.192 | |
| chat-bison-001 | palm | $0.13 | $0.13 | 8.192 | |
| llama-3.1-8b-instruct | perplexity | $0.20 | $0.20 | 131.072 | Pricing |
| mistral-7b-instruct | perplexity | $0.07 | $0.28 | 4.096 | Pricing |
| mixtral-8x7b-instruct | perplexity | $0.07 | $0.28 | 4.096 | Pricing |
| pplx-7b-chat | perplexity | $0.07 | $0.28 | 8.192 | Pricing |
| pplx-7b-online | perplexity | $0.00 | $0.28 | 4.096 | Pricing |
| sonar-small-chat | perplexity | $0.07 | $0.28 | 16.384 | Pricing |
| sonar-small-online | perplexity | $0.00 | $0.28 | 12.000 | Pricing |
| llama-3.1-70b-instruct | perplexity | $1.00 | $1.00 | 131.072 | Pricing |
| sonar | perplexity | $1.00 | $1.00 | 128.000 | Pricing |
| codellama-34b-instruct | perplexity | $0.35 | $1.40 | 16.384 | Pricing |
| sonar-medium-chat | perplexity | $0.60 | $1.80 | 16.384 | Pricing |
| sonar-medium-online | perplexity | $0.00 | $1.80 | 12.000 | Pricing |
| codellama-70b-instruct | perplexity | $0.70 | $2.80 | 16.384 | Pricing |
| llama-2-70b-chat | perplexity | $0.70 | $2.80 | 4.096 | Pricing |
| pplx-70b-chat | perplexity | $0.70 | $2.80 | 4.096 | Pricing |
| pplx-70b-online | perplexity | $0.00 | $2.80 | 4.096 | Pricing |
| sonar-reasoning | perplexity | $1.00 | $5.00 | 128.000 | Pricing |
| sonar-deep-research | perplexity | $2.00 | $8.00 | 128.000 | Pricing |
| sonar-reasoning-pro | perplexity | $2.00 | $8.00 | 128.000 | Pricing |
| sonar-pro | perplexity | $3.00 | $15.00 | 200.000 | Pricing |
| gpt-oss-20b | replicate | $0.09 | $0.36 | — | |
| Meta-Llama-3.2-1B-Instruct | sambanova | $0.04 | $0.08 | 16.384 | |
| Meta-Llama-3.2-3B-Instruct | sambanova | $0.08 | $0.16 | 4.096 | |
| Meta-Llama-3.1-8B-Instruct | sambanova | $0.10 | $0.20 | 16.384 | |
| Meta-Llama-Guard-3-8B | sambanova | $0.30 | $0.30 | 16.384 | |
| Llama-4-Scout-17B-16E-Instruct | sambanova | $0.40 | $0.70 | 8.192 | |
| Qwen3-32B | sambanova | $0.40 | $0.80 | 8.192 | |
| QwQ-32B | sambanova | $0.50 | $1.00 | 16.384 | |
| MiniMax-M2.7 | sambanova | $0.30 | $1.20 | 204.800 | |
| Meta-Llama-3.3-70B-Instruct | sambanova | $0.60 | $1.20 | 131.072 | |
| DeepSeek-R1-Distill-Llama-70B | sambanova | $0.70 | $1.40 | 131.072 | |
| Llama-4-Maverick-17B-128E-Instruct | sambanova | $0.63 | $1.80 | 131.072 | |
| DeepSeek-V3-0324 | sambanova | $3.00 | $4.50 | 32.768 | |
| DeepSeek-V3.1 | sambanova | $3.00 | $4.50 | 32.768 | |
| gpt-oss-120b | sambanova | $3.00 | $4.50 | 131.072 |