API pricing for 16 major LLM models. Input/output per million tokens, context windows, latency, and daily cost at 10K requests. CC BY 4.0.
Download CSV (16 models)| Model | Provider | Input | Output | Context | Speed | Daily Cost (10K req) |
|---|---|---|---|---|---|---|
| GPT-4o | OpenAI | $2.50 | $10.00 | 128K | Medium | $75 |
| GPT-4o-mini | OpenAI | $0.15 | $0.60 | 128K | Fast | $4.50 |
| Claude 3.5 Sonnet | Anthropic | $3.00 | $15.00 | 200K | Medium | $90 |
| Claude 3 Haiku | Anthropic | $0.25 | $1.25 | 200K | Fast | $7.50 |
| Gemini 1.5 Pro | $1.25 | $5.00 | 2M | Medium | $37.50 | |
| Gemini 1.5 Flash | $0.075 | $0.30 | 1M | Fast | $2.25 | |
| GPT-4 Turbo | OpenAI | $10.00 | $30.00 | 128K | Slow | $225 |
| o1 | OpenAI | $15.00 | $60.00 | 200K | Slow | $450 |
| Llama 3.1 70B | Meta/Groq | $0.59 | $0.79 | 128K | Very Fast | $14.40 |
| Llama 3.1 405B | Meta | $3.00 | $3.00 | 128K | Medium | $30 |
| DeepSeek V3 | DeepSeek | $0.27 | $1.10 | 128K | Fast | $8.20 |
| Mistral Large | Mistral | $2.00 | $6.00 | 128K | Medium | $45 |
| Command R+ | Cohere | $2.50 | $10.00 | 128K | Medium | $75 |
| Nova Pro | Amazon | $0.80 | $3.20 | 300K | Medium | $24 |
| Nova Lite | Amazon | $0.06 | $0.24 | 300K | Fast | $1.80 |
An autonomous AI agent making 10,000 API calls per day on GPT-4o costs $75/day ($2,250/month). The same workload on Gemini 1.5 Flash costs $2.25/day ($67/month). A spend firewall like sipi.bot monitors these costs in real time, blocking runaway agents before they drain your budget. The 33x price difference between the cheapest and most expensive models is why cost control is the #1 operational concern for agent builders in 2026.