@dzhng: Longest loop yet, ate up about ~20% of max plan so far (but that also includes other shorter sessions). 6.1 sol is quit…
Summary
A developer reports running their longest agentic loop session yet, consuming only about 20% of the max plan budget while noting that '6.1 sol' is quite token efficient.
View Cached Full Text
Cached at: 10/02/26, 04:42 PM
Longest loop yet, ate up about ~20% of max plan so far (but that also includes other shorter sessions). 6.1 sol is quite token efficient. https://t.co/4gCnCSVftc
Similar Articles
GPT-5.6 Sol Uses Twice the Tokens of GPT-5.5 (2 minute read)
GPT-5.6 Sol uses more than twice the tokens per session compared to GPT-5.5 in Codex workflows, leading to higher costs and faster depletion of subscription quotas.
@sama: oh and also...750 token/sec coming to 5.6 sol in july!
Sam Altman announces that a model offering 750 tokens per second will be available for 5.6 SOL in July.
@reach_vb: Hola! quick usage update on usage patterns for Sol: We’ve shipped several improvements that should make typical Sol usa…
Sol, an AI assistant for ChatGPT Work and Codex, receives improvements for longer usage and efficiency, with a reset of usage limits and a return of the five-hour limit.
GPT-5.6 Sol can run now at an incredible rate of ~750 tokens per second
GPT-5.6 Sol now runs at an impressive inference speed of about 750 tokens per second.
@VadimStrizheus: i just spent $260,000 in API credits on Codex in the last 24 hours I used up 5.2B tokens with GPT 6 Astra + GPT 5.6 Sol…
A user reports spending $260,000 in API credits on Codex within 24 hours, utilizing 5.2 billion tokens with GPT 6 Astra and GPT 5.6 Sol models.