See Scope Architect on your own project. Get a walkthrough →
AI RESOURCES

Model pricing for coding agents

Benchmarks rank models. This ranks what they cost to run in a loop — grouped by the job you’d actually hire them for.

218 models · provider list rates · synced daily

Hardest reasoning, highest cost. Worth it for architecture, gnarly debugging, and one-shot work you cannot babysit.

Why you'd pick it
Claude Opus 5anthropic/claude-opus-5The default when the task is ambiguous or the blast radius is large. Best at holding a big refactor in its head without losing the thread.1M$5.00$25.00$0.500Full
Claude Fable 5anthropic/claude-fable-5Priced well above its siblings — reach for it when output quality matters more than throughput.1M$10.00$50.00$1.00
GPT 5.6 Solopenai/gpt-5.6-solStrong general reasoning with a very large context window. A solid alternative when you want a second opinion from outside the Anthropic family.1.1M$2.00$10.00$0.200Partial
GPT 5.6 Terraopenai/gpt-5.6-terraSame generation as Sol with a different balance; worth A/B-ing on your own workload rather than trusting a leaderboard.1.1M$2.00$12.00$0.200Partial
GPT 5.5 Proopenai/gpt-5.5-proPriced for deliberation, not throughput. Use it on the one hard problem, not the loop around it.1M$30.00$180.00
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-previewCheap for a frontier model and very long context — good for tasks that need to read a lot before writing a little.1M$2.00$12.00$0.200Partial
Grok 4.6spacexai/grok-4.6Competitive on price for its tier. Worth testing if your work is heavy on tool-calling.500K$2.00$6.00$0.500
Kimi K3moonshotai/kimi-k3Frontier-class at a mid-tier price, though less proven in agent harnesses than the majors.1M$3.00$15.00$0.300Full