Ask for a model

Tell us the job. We’ll pick three.

Best overall, best on a budget and best regardless of price, with what each costs at your volume. No signup needed.

request.txt

I need help with , about , my budget is and what matters most is .

What we understoodSupport repliesany budgeta balance of quality and price20k a month
best_overall.txt
Best overall
  • Scores 67 on support, #12 of 30 models we track for this job.
  • $0.43 per 1,000 replies.
  • Also the cheapest model that passes our test for this job.
At 20k replies a month$8.50 a month
Passes our testOpen weightsProvisional score
best_premium.txt
Best premium pick
  • Scores 97 on support, the highest of 30 models we track for this job.
  • $7.00 per 1,000 replies: the extra $6.58 per 1,000 buys 30 more points.
  • Reads up to 1,049K tokens at once.
At 20k replies a month$140 a month
Passes our testProvisional score
RefineCheaperQuality firstMake it private

Also considered: Gemini 3.8 Flash (match 70, $2.63 per 1,000), Gemma 4 31B IT (match 69, $0.46 per 1,000), Claude Opus 5.5 (match 68, $14.00 per 1,000), GLM-5.3 (match 67, $3.86 per 1,000). 30 models were in the running.

alerts.txt
Model Menu will email you about this, plus the Friday letter. One click unsubscribes. We never sell or share your address.

How we pick

The ranking is a published formula, never a person’s choice and never paid for. We filter by the job, your budget and any hard needs such as open weights, then weigh quality and price by what you said matters most. Best overall is the top of that list. Best budget is the cheapest model that passes our test for the job. Best premium is the highest quality, whatever it costs.

Scores are provisional: they come from Arena and Epoch AI benchmarks until our own test rig runs. Prices are list prices, checked against OpenRouter where we can. Speed is not scored yet. See the methodology.