AI / LLM
AI/LLM models & prices
835 getrackte Modelle — Input/Output je 1 Mio. Token + Context-Window, nach Output-Preis sortiert. Source: LiteLLM price data, each linked to the official pricing page.
| Model | Provider | Input $/1M | Output $/1M | Context | Source |
|---|---|---|---|---|---|
| Meta-Llama-3.1-405B-Instruct | sambanova | $5.00 | $10.00 | 16,384 | |
| Qwen2-Audio-7B-Instruct | sambanova | $0.50 | $100.00 | 4,096 | |
| together-ai-up-to-4b | together_ai | $0.10 | $0.10 | — | |
| together-ai-4.1b-8b | together_ai | $0.20 | $0.20 | — | |
| together-ai-8.1b-21b | together_ai | $0.30 | $0.30 | 1,000 | |
| together-ai-21.1b-41b | together_ai | $0.80 | $0.80 | — | |
| together-ai-41.1b-80b | together_ai | $0.90 | $0.90 | — | |
| together-ai-81.1b-110b | together_ai | $1.80 | $1.80 | — | |
| titan-embed-text-v2 | vercel_ai_gateway | $0.02 | $0.00 | — | |
| embed-v4.0 | vercel_ai_gateway | $0.12 | $0.00 | — | |
| codestral-embed | vercel_ai_gateway | $0.15 | $0.00 | — | |
| mistral-embed | vercel_ai_gateway | $0.10 | $0.00 | — | |
| ministral-3b | vercel_ai_gateway | $0.04 | $0.04 | 128,000 | |
| llama-3-8b | vercel_ai_gateway | $0.05 | $0.08 | 8,192 | |
| llama-3.1-8b | vercel_ai_gateway | $0.05 | $0.08 | 131,000 | |
| llama-3.2-1b | vercel_ai_gateway | $0.10 | $0.10 | 128,000 | |
| ministral-8b | vercel_ai_gateway | $0.10 | $0.10 | 128,000 | |
| nova-micro | vercel_ai_gateway | $0.04 | $0.14 | 128,000 | |
| llama-3.2-3b | vercel_ai_gateway | $0.15 | $0.15 | 128,000 | |
| pixtral-12b | vercel_ai_gateway | $0.15 | $0.15 | 128,000 | |
| llama-3.2-11b | vercel_ai_gateway | $0.16 | $0.16 | 128,000 | |
| gemma-2-9b | vercel_ai_gateway | $0.20 | $0.20 | 8,192 | |
| qwen-3-14b | vercel_ai_gateway | $0.08 | $0.24 | 40,960 | |
| nova-lite | vercel_ai_gateway | $0.06 | $0.24 | 300,000 | |
| devstral-small | vercel_ai_gateway | $0.07 | $0.28 | 128,000 | |
| qwen-3-30b | vercel_ai_gateway | $0.10 | $0.30 | 40,960 | |
| qwen-3-32b | vercel_ai_gateway | $0.10 | $0.30 | 40,960 | |
| gemini-2.0-flash-lite | vercel_ai_gateway | $0.08 | $0.30 | 1,048,576 | |
| llama-4-scout | vercel_ai_gateway | $0.10 | $0.30 | 131,072 | |
| mistral-small | vercel_ai_gateway | $0.10 | $0.30 | 32,000 | |
| gpt-4.1-nano | vercel_ai_gateway | $0.10 | $0.40 | 1,047,576 | |
| grok-3-mini | vercel_ai_gateway | $0.30 | $0.50 | 131,072 | |
| qwen-3-235b | vercel_ai_gateway | $0.20 | $0.60 | 40,960 | |
| command-r | vercel_ai_gateway | $0.15 | $0.60 | 128,000 | |
| gemini-2.0-flash | vercel_ai_gateway | $0.15 | $0.60 | 1,048,576 | |
| llama-4-maverick | vercel_ai_gateway | $0.20 | $0.60 | 131,072 | |
| gpt-4o-mini | vercel_ai_gateway | $0.15 | $0.60 | 128,000 | |
| llama-3.1-70b | vercel_ai_gateway | $0.72 | $0.72 | 128,000 | |
| llama-3.2-90b | vercel_ai_gateway | $0.72 | $0.72 | 128,000 | |
| llama-3.3-70b | vercel_ai_gateway | $0.72 | $0.72 | 128,000 | |
| llama-3-70b | vercel_ai_gateway | $0.59 | $0.79 | 8,192 | |
| mistral-saba-24b | vercel_ai_gateway | $0.79 | $0.79 | 32,768 | |
| deepseek-v3 | vercel_ai_gateway | $0.90 | $0.90 | 128,000 | |
| codestral | vercel_ai_gateway | $0.30 | $0.90 | 256,000 | |
| deepseek-r1-distill-llama-70b | vercel_ai_gateway | $0.75 | $0.99 | 131,072 | |
| mercury-coder-small | vercel_ai_gateway | $0.25 | $1.00 | 32,000 | |
| sonar | vercel_ai_gateway | $1.00 | $1.00 | 127,000 | |
| glm-4.5-air | vercel_ai_gateway | $0.20 | $1.10 | 128,000 | |
| mixtral-8x22b-instruct | vercel_ai_gateway | $1.20 | $1.20 | 65,536 | |
| morph-v3-fast | vercel_ai_gateway | $0.80 | $1.20 | 32,768 |