How do I open the Compare Prices grid?

Two ways: click the 'Compare Prices' tab at the top of the calculator card on the home page, or navigate directly to /tools/compare-prices. The standalone page is also linked from the main navigation under 'Tools'.

Can I share my comparison with teammates?

Yes — the page URL captures the current state. Send the link in Slack and your teammate sees the same grid. Useful for procurement and architecture-review meetings.

Is the data live or cached?

Live from OpenRouter (prices) and a blended Arena AI + Artificial Analysis pipeline (quality), refreshed on a 60-minute incremental cache. So the grid is at most an hour stale.

Where do I go after the grid to project monthly cost?

Once you've picked a winner, go to /tools/api-cost-estimator and plug in the model + your expected monthly token volume. The estimator does the per-1M math against your real workload mix.

Fast vs Reasoning Tier in the Compare Prices Grid

Why a Within-Tier Comparison Beats Cross-Tier

TokenRate's new Compare Prices grid puts every model's per-token rates, context window, and quality score in a single side-by-side view. The point: stop flipping between provider pricing pages and OpenRouter tabs. You pick a provider dropdown, check the models you want, repeat for each provider, and the grid stacks every pick into one comparison table. Once you've picked your tier — Fast vs Reasoning — the next question is which **specific** Fast vs Reasoning model. Cross-tier comparisons (flagship vs fast) are usually a budgeting question. Within-tier comparisons are routing questions: "of the models built for the same workload class, which is the best fit for mine?" This guide grids Claude Haiku 4.5, GPT-4o mini, DeepSeek R1, OpenAI o3-mini side-by-side in /tools/compare-prices. See also: filter LLM models by tier, cost, quality, Value column vs tokens-per-dollar, and how to pick an LLM by quality score and cost.

Fast vs Reasoning Tier Defined

Fast vs Reasoning tier on TokenRate means: fast tier is built for high-volume throughput at the lowest per-token rate the provider offers. Input prices typically span $0.150 to $1.10 per 1M tokens within the tier. Quality scores span 55 to 73. So even within the tier, the Value column will diverge — which is the whole point of comparing within-tier instead of just defaulting to whichever model is most familiar.

The Fast vs Reasoning Models, Compared

**Claude Haiku 4.5** (Anthropic): $1.00 / $5.00, 200K ctx, Q65, value 65. **GPT-4o mini** (OpenAI): $0.150 / $0.600, 128K ctx, Q55, value 366.7. **DeepSeek R1** (DeepSeek): $0.550 / $2.19, 128K ctx, Q73, value 132.7. **OpenAI o3-mini** (OpenAI): $1.10 / $4.40, 200K ctx, Q72, value 65.5. All of these appear in the Compare Prices grid under their respective provider dropdowns. Tick all of them and the grid renders the cross-provider tier comparison in seconds.

When to Pick Each Fast vs Reasoning Model

**Claude Haiku 4.5**: pick when traffic volume is high enough that the per-token savings dominate ($1.00 input is hard to beat). **GPT-4o mini**: pick when traffic volume is high enough that the per-token savings dominate ($0.150 input is hard to beat). **DeepSeek R1**: pick when the task involves multi-step planning or math where chain-of-thought pays for itself. **OpenAI o3-mini**: pick when the task involves multi-step planning or math where chain-of-thought pays for itself. The picks aren't mutually exclusive — many production stacks route different traffic types to different Fast vs Reasoning models within the same week. For routing pattern guidance, see multi-model routing with quality scores.

Operationalizing the Fast vs Reasoning Pick

Once you've shortlisted within the Fast vs Reasoning tier in /tools/compare-prices, plug your token volume into /tools/api-cost-estimator for monthly cost projection. A common mistake: assuming Fast vs Reasoning models all behave the same on output cost. The grid makes the spread obvious — output costs across the Fast vs Reasoning tier in this guide span $0.600 to $5.00 per 1M, a 8.3× spread. Pricing is pulled live from OpenRouter's models endpoint and revalidated every 60 minutes via Next.js's incremental cache, so the grid you see is at most an hour stale. Quality scores blend Arena AI Elo with Artificial Analysis intelligence-index data on the same cadence. Run the comparison live at /tools/compare-prices, then bookmark the URL for next month's price audit.