codai

Radical transparency

What we actually paid per million tokens.

Computed live from the last 7 days of real traffic on ai.codai.ro. No list prices, no “starting from” footnotes — the blended cost users actually got. Other gateways treat their routing as a black box. We treat it as the product.

Overall blended cost · all tiers · last 7 days

$4.67/M tokens

From 11,225,362,854 tokens across 77,321 requests.

Per tier

Small

Chat, factual lookup, single-function code.

$5.75/M

77%

67,248 requests · 7,052,904,874 tokens · $40585.62 total

Routes to: Claude Haiku 4.5 · Gemini Flash · Gemini Flash-Lite

Medium

Multi-step reasoning, code generation, refactors.

$1.85/M

4%

9,591 requests · 1,233,415,170 tokens · $2283.87 total

Routes to: Claude Sonnet 4.6 · GPT-5-mini · Gemini Pro · GPT-5.4-mini

Large

Frontier-grade architecture, long context, agentic loops.

$2.16/M

0%

279 requests · 9,901,080 tokens · $21.43 total

Routes to: Claude Opus 4.7 · GPT-5 · GPT-5.5 · Gemini 3.1 Pro

Vision

Multimodal requests with image content — auto-routed to Gemini 2.5 Pro.

$3.67/M

0%

203 requests · 267,834 tokens · $0.98 total

Routes to: Gemini 2.5 Pro

Note: 2,928,873,896 tokens (18,116 requests, $9548.07) came from upstream models not yet labelled by tier (claude-opus-4-8, text-embedding-3-large). Counted in the overall total above, not in any tier card.

How we keep the number honest

  • →Every request hits a classifier (Claude Haiku 4.5) that picks the cheapest tier that can handle it. We bias toward small. Requests with max_tokens ≤ 200 skip the classifier entirely and go straight to small.
  • →Opt in to FrugalGPT cascading with x-codai-cascade: verify: small tier answers first, a medium-tier verifier vets the reply, and we only escalate when the verifier rejects. Saves 40–60% on ambiguous prompts.
  • →Every response carries x-codai-routed-to so you can see which upstream actually ran. No black-box routing.
  • →Sticky-cache session routing: pass x-codai-session-id and follow-up turns land on the same upstream so the provider's prompt cache hits. Free latency + cost wins.

Numbers refresh every 10 minutes from the live usage_events table. Last computed 18 Jul 2026, 20:26 UTC.