Pick up to 3 models and compare input cost, output cost, context window, speed, and more. The best value in each row is highlighted. Share your comparison with a link.
Providers advertise input cost because it is the smaller of the two, and output tokens are typically priced three to five times higher. What you actually pay depends on your ratio: a summariser sends a lot and returns a little, so input dominates; an agent that writes code inverts that completely. Read both columns together, weighted the way your own work is weighted, and treat any single headline figure as marketing.
A million-token window means a million tokens fit, not that quality holds across them. Retrieval accuracy degrades well before the limit on every model, and you pay for every token you send on every turn — a long conversation re-bills its own history. Treat the window as headroom that saves you from chunking, and assume real quality lives comfortably inside it.
Published scores come from different harnesses, different prompt scaffolds and often different attempt budgets. A two-point difference on a coding benchmark tells you far less than a five-times price difference or a latency difference you can feel. Use scores to rule models out, not to rank the survivors.
Throughput — tokens per second once a model starts — is not the same as time to first token, and reasoning models can sit silent for a long time before either. If the model sits in an interactive loop, the wait before the first character is the number that decides whether people keep using it.
Compare three models, not ten: the one you use now, the obvious upgrade, and the obvious cheaper option. If the upgrade is not clearly better on the axis you care about, stay put. If the cheaper option is within a few points on that axis, run a week of real work through it before assuming you need the expensive one. Every comparison here is shareable — the model selection travels in the URL.
Best cheap AI for broad day-to-day work — now with 1M context.
The best all-around budget model for most teams. Faster than its predecessor, cheaper, and with a 1M context window that outclasses every other budget option.
Google's Pro model — 1M context and native multimodal input at $2/$12.
A capable research model and still Google's current Pro tier, but no longer the long-context leader: its 1M-token window matches Claude Opus 5.5 and is slightly below the GPT-6 family's 1.05M. Choose it for Google Workspace integration and multimodal input; for most research, Claude Opus 5.5 or GPT-6.1 Sol are stronger at a similar price.
Retired May 15, 2026 — replaced by Grok 4.6 and Grok 4.7.
Retired: xAI shut down the grok-4-0709 API on May 15, 2026. It was a strong coding model at launch, at $3/$15 with a 256K window; earlier versions of this page listed $2/$6 and 2M tokens in error. Use Grok 4.7 instead.
Share this comparison