AI Model Comparison
GPT, Claude, Gemini and more — priced and sized side by side.
Picking a model means weighing price against context size, and the numbers live on a dozen different pricing pages. This llm benchmark comparison pulls the main chat models into one sortable table: input and output cost per million tokens and the context window, for OpenAI, Anthropic, Google, DeepSeek and others. Filter to one provider or sort by whichever column matters — cheapest input, cheapest output, or biggest context — to see gpt vs claude vs gemini at a glance before you commit.
| Gemini 1.5 Flash | $0.075 | $0.300 | 1M | |
| Gemini 2.0 Flash | $0.100 | $0.400 | 1M | |
| GPT-4o mini | OpenAI | $0.150 | $0.600 | 128K |
| Mistral Small | Mistral | $0.200 | $0.600 | 128K |
| Claude 3 Haiku | Anthropic | $0.250 | $1.250 | 200K |
| DeepSeek-V3 | DeepSeek | $0.270 | $1.100 | 64K |
| GPT-3.5 Turbo | OpenAI | $0.500 | $1.500 | 16K |
| DeepSeek-R1 | DeepSeek | $0.550 | $2.190 | 64K |
| Claude 3.5 Haiku | Anthropic | $0.800 | $4 | 200K |
| o3-mini | OpenAI | $1.100 | $4.400 | 200K |
| Gemini 1.5 Pro | $1.250 | $5 | 2M | |
| Grok 2 | xAI | $2 | $10 | 131K |
| Mistral Large | Mistral | $2 | $6 | 128K |
| GPT-4o | OpenAI | $2.500 | $10 | 128K |
| Claude Sonnet 4 | Anthropic | $3 | $15 | 200K |
| Claude 3.5 Sonnet | Anthropic | $3 | $15 | 200K |
| GPT-4 Turbo | OpenAI | $10 | $30 | 128K |
| o1 | OpenAI | $15 | $60 | 200K |
| Claude Opus 4 | Anthropic | $15 | $75 | 200K |
Prices are USD per 1M tokens, updated January 2026. List pay-as-you-go rates — verify with each provider before you budget. Context is the maximum input window.
How it works
- 1
Filter by provider
Show all models or narrow to one provider to compare a single family, like Claude Opus against Sonnet and Haiku.
- 2
Sort by what matters
Tap a column header to sort. Input price finds the cheapest prompt cost, output price the cheapest generation, context the biggest window. Tap again to reverse.
- 3
Read across the row
Each row gives the model, provider, input and output price per million tokens and the context size, so you can trade cost against capability without opening five pricing pages.
Instant & 100% private — nothing is uploaded
Every calculation runs locally in your browser. The prompts, token counts and numbers you enter stay on your own device and are never sent to a server — nothing is stored, logged or shared.
Frequently asked questions
- Which model is cheapest?
- Sort by input or output price to see. The lowest-cost options are usually the small models — GPT-4o mini, Claude 3.5 Haiku, Gemini Flash — which are a fraction of the flagship prices and fine for many tasks. Match the model to the job rather than defaulting to the biggest.
- Why compare input and output separately?
- Providers charge more for generated output than for the prompt they read, often several times more. A model with cheap input but pricey output suits long prompts with short answers; the reverse suits short prompts that generate a lot.
- What does context window mean?
- It is the maximum number of tokens the model can consider at once — your prompt plus its reply. A bigger window lets you feed in more documents or history, but you still pay per token for everything you send, so a large context is a capability, not a free lunch.
- Are these prices current?
- They come from a shared table dated on the page. Providers change pricing and release new models often, so treat the comparison as a starting point and confirm against each provider's own pricing page before you decide.
Important
For planning and estimates only. Prices come from a published rate table dated on the page; providers change pricing without notice, and token counts here are approximations. Confirm against the provider’s own pricing before you budget or commit.
More tools
More from the Hivly network
Free sister tools on our other sites.
