Sortable price and context-window comparison across current chat model options.
| Model | Provider | $ / 1M input | $ / 1M output | Context window |
|---|---|---|---|---|
| Gemini 1.5 Flash | $0.075 | $0.30 | 1,000,000 | |
| GPT-3.5 Turbo | OpenAI | $0.500 | $1.50 | 16,385 |
| Llama 3.1 70B | Meta (hosted) | $0.590 | $0.79 | 128,000 |
| Claude Haiku | Anthropic | $0.800 | $4.00 | 200,000 |
| Gemini 1.5 Pro | $1.250 | $5.00 | 2,000,000 | |
| GPT-4o | OpenAI | $2.500 | $10.00 | 128,000 |
| Claude Sonnet | Anthropic | $3.000 | $15.00 | 200,000 |
| GPT-4 Turbo | OpenAI | $10.000 | $30.00 | 128,000 |
| Claude Opus | Anthropic | $15.000 | $75.00 | 200,000 |
Click a column header to sort. Pricing is illustrative and drifts as providers update their price sheets — verify against the provider's current pricing page before budgeting. See the Token Counter to estimate cost for your own prompts.
Picking a model usually comes down to price and context window before anything else. This table puts current chat models side by side, sortable by whichever column matters most for your use case.