Please generate a table listing the top 10 models from OpenRouter's monthly rankings,…
- User
Please generate a table listing the top 10 models from OpenRouter's monthly rankings, along with the amount of tokens used and the estimated costs for the used tokens reported by the stats.
Assistant
Based on the search results, here is a table of the top 10 models from OpenRouter's monthly rankings, along with their token usage and estimated costs:
Rank Model Monthly Tokens Used Estimated Cost Notes 1 Anthropic: Claude 3.7 Sonnet 43.5B tokens ~652.5M 4% of total traffic, leading in Programming category [1][4] 2 Google: Gemini 2.0 Flash 34.8B tokens ~13M 7% of total traffic [1] 3 Google: Gemini 2.5 Pro Not specified Not specified Gaining ground on Claude [4] 4 OpenAI: GPT-4o-mini Not specified ~0.6/M tokens Dominated weekly rankings [4] 5 DeepSeek: DeepSeek V3 Not specified ~1.10/M output Significantly cheaper than Claude [15] 6 Optimus Alpha Not specified Free (currently) Trending free model [4] 7 Meta: Llama-3-70b-instruct Not specified ~0.79/M tokens Popular open-source model [13] 8 OpenAI: GPT-4o Not specified ~10/M tokens Premium model [13] 9 Anthropic: Claude 3.5 Sonnet Not specified ~15/M output Previous generation of Claude [15] 10 Google: Gemini 1.5 Flash Not specified Not specified Still used by some users [6] Note: The estimated costs are calculated based on the token pricing information available in the search results. For Claude 3.7 Sonnet, the cost estimate assumes a similar pricing structure to Claude 3.5 Sonnet (15/M tokens) and is presented as a range since the exact split between input and output tokens is not specified. The actual costs may vary significantly depending on the ratio of input to output tokens and any special pricing arrangements.
For the Programming category specifically, Claude 3.7 Sonnet was the top performer in monthly rankings, while GPT-4o-mini dominated the weekly rankings despite Quasar Alpha's brief appearance as a free option[4]. The rankings can shift rapidly as new models are introduced, with free models like Optimus Alpha gaining momentum[4].
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.