3k calls/month
Cheapest option for your usage
Llama 3.1 8B
GroqPer API call$0.000090
Per day$0.0090
Per month$0.2700
Per year$3.29
Input vs output cost split
Input 56%Output 44%
All models — 20 results
| Model | Provider | Context | $/1M in | $/1M out | /call | /month ↑ |
|---|---|---|---|---|---|---|
| 🏆Llama 3.1 8BUltra-fast + cheap | Groq | 128k | $0.0500 | $0.0800 | $0.000090 | $0.2700 |
| Gemini 1.5 Flash-8BCheapest option | 1M | $0.0375 | $0.1500 | $0.00011 | $0.3375 | |
| Gemini 1.5 Flash | 1M | $0.0750 | $0.3000 | $0.00022 | $0.6750 | |
| Mistral 7B | Mistral | 32k | $0.2500 | $0.2500 | $0.00038 | $1.13 |
| GPT-4o mini | OpenAI | 128k | $0.1500 | $0.6000 | $0.00045 | $1.35 |
| Claude 3 Haiku | Anthropic | 200k | $0.2500 | $1.25 | $0.00088 | $2.63 |
| Llama 3.1 70B | Groq | 128k | $0.5900 | $0.7900 | $0.00098 | $2.96 |
| Mixtral 8x7B | Mistral | 32k | $0.7000 | $0.7000 | $0.0010 | $3.15 |
| GPT-3.5 Turbo | OpenAI | 16k | $0.5000 | $1.50 | $0.0013 | $3.75 |
| Mistral Small | Mistral | 32k | $1.00 | $3.00 | $0.0025 | $7.50 |
| Claude 3.5 Haiku | Anthropic | 200k | $0.8000 | $4.00 | $0.0028 | $8.40 |
| Llama 3.1 405B | Groq | 128k | $3.00 | $3.00 | $0.0045 | $13.50 |
| GPT-4o | OpenAI | 128k | $2.50 | $10.00 | $0.0075 | $22.50 |
| Mistral Large 2 | Mistral | 128k | $3.00 | $9.00 | $0.0075 | $22.50 |
| Gemini 1.5 Pro | 1M | $3.50 | $10.50 | $0.0088 | $26.25 | |
| o1-miniReasoning model | OpenAI | 128k | $3.00 | $12.00 | $0.0090 | $27.00 |
| Claude 3.5 Sonnet | Anthropic | 200k | $3.00 | $15.00 | $0.0105 | $31.50 |
| GPT-4 Turbo | OpenAI | 128k | $10.00 | $30.00 | $0.0250 | $75.00 |
| o1Reasoning model | OpenAI | 128k | $15.00 | $60.00 | $0.0450 | $135 |
| Claude 3 Opus | Anthropic | 200k | $15.00 | $75.00 | $0.0525 | $158 |
⚠ Prices are approximate — verify at each provider's pricing page before budgeting.All prices in USD per 1M tokens.Calculation: 1,000 input + 500 output tokens × 100 calls/day.