Free tool
LLM pricing comparison
Every major model, per-million-token pricing, context window, modalities — sortable and bookmarkable.
← Back to free tools
| Notes | |||||||
|---|---|---|---|---|---|---|---|
| Llama 3.1 8B (Groq) | Groq | $0.050 | $0.080 | 20.0M | 128K | text | Lightning-fast on Groq's LPU hardware. |
| Gemini 1.5 Flash | $0.075 | $0.30 | 13.3M | 1M | textvisionaudio | ||
| Gemini 2.0 Flash | $0.10 | $0.40 | 10.0M | 1M | textvisionaudio | ||
| GPT-4o mini | OpenAI | $0.15 | $0.60 | 6.7M | 128K | textvision | |
| Mistral Small 3 | Mistral | $0.20 | $0.60 | 5.0M | 32K | text | |
| DeepSeek V3 | DeepSeek | $0.27 | $1.10 | 3.7M | 128K | text | Off-peak (UTC 16:30–00:30) is 50% cheaper. |
| GPT-4.1 mini | OpenAI | $0.40 | $1.60 | 2.5M | 1M | textvision | |
| DeepSeek R1 | DeepSeek | $0.55 | $2.19 | 1.8M | 128K | text | Reasoning model — outputs include chain-of-thought. |
| Llama 3.3 70B (Groq) | Groq | $0.59 | $0.79 | 1.7M | 128K | text | Open-weight model. Pricing + speed depend on host. |
| Claude Haiku 4.5 | Anthropic | $0.80 | $4 | 1.3M | 200K | textvision | |
| o3-mini | OpenAI | $1.10 | $4.40 | 909K | 200K | text | |
| Gemini 1.5 Pro | $1.25 | $5 | 800K | 2M | textvisionaudio | 2M context — the largest of any production model. | |
| GPT-4.1 | OpenAI | $2 | $8 | 500K | 1M | textvision | |
| Grok-2 | xAI | $2 | $10 | 500K | 128K | textvision | |
| Mistral Large 2 | Mistral | $2 | $6 | 500K | 128K | textvision | |
| GPT-4o | OpenAI | $2.50 | $10 | 400K | 128K | textvision | |
| Claude Sonnet 4.6 | Anthropic | $3 | $15 | 333K | 200K | textvision | |
| Claude 3.5 Sonnet | Anthropic | $3 | $15 | 333K | 200K | textvision | Older but still popular for cost-stability reasons. |
| Grok-3 | xAI | $3 | $15 | 333K | 1M | textvision | |
| o1 | OpenAI | $15 | $60 | 67K | 200K | text | Reasoning tokens billed but hidden from output. |
| Claude Opus 4.7 | Anthropic | $15 | $75 | 67K | 1M | textvision | Cache write 1.25× input price. Extended thinking optional. JSON via prefill or tool-use trick. |
Last verified · 21 models shown · Data also available as JSON.
Source: provider pricing pages, May 2026. Prices can change — verify on each provider’s site for production use.
Want to track these costs on your actual traffic? Try Tokenwise — one line of code, $19/mo.