CostWall Step 2 of 4

Stop AI overspend in the gateway you already run

CostWall turns each workload's numbers into budgets, caps and cheaper routes, written in your gateway's own format. Runaway agents stop before the bill does.

  • Lower cost on every workload, with each lever priced before you switch
  • Budgets, daily caps, cost per agent run and a kill switch
  • Nothing new in your request path: we write your gateway's config
Cut AI costs today: CostWall Lite, free →Not sure? Talk to us
1CostAssessSee every AI workload, its cost and its gaps. 2You are hereCostWallStop overspend in the gateway you already run. 3CostProtectAI governance: keep every workload within your rules. 4CostProofSee the savings on your real bill.

Where it fits in AICost.ai

Builds onUses the workloads and prices from CostAssess, or one free QuickStart.
FeedsEach rule is approved and versioned in CostProtect; CostProof checks the savings on your real bill.

What you get

Lower cost per outcome

Caching, batching, routing and right-sized models, each priced by the engines before you change anything.

No surprise bills

Monthly and daily budgets, cost per agent run, turn and retry caps, emergency stop.

Enforced where your AI runs

Native config for LiteLLM, Cloudflare, Azure APIM and Kong. Our run guard covers only what gateways cannot.

Proof each rule works

Test calls show every limit blocks before you rely on it.

How it works

  1. Price the workload

    From CostAssess, the 54 workflow library, the designer or a two-minute QuickStart.

  2. Generate the policy

    Budget, daily cap, cost per run, turn cap, approved and fallback models, caching.

  3. Deploy

    Download for your gateway (Lite) or push with one approval (Pro).

  4. Verify

    Probe calls confirm each rule blocks; the result is kept as evidence.

Works with what you already run

  • LiteLLM
  • Cloudflare AI Gateway
  • Azure API Management
  • Kong
  • Portkey
  • AWS Bedrock
  • OpenAI spend limits
  • Anthropic workspace limits

CostWall: Lite, Pro and Enterprise

Lite
$0
free

Policy downloads for LiteLLM, Cloudflare and more

Pro
$49 / $199 / $499
per workload a month

Caps per agent run, daily caps, kill switch

Enterprise
from $4,500
a month, about 25 workloads

Runs in your own network

Every plan includes all four products. Pro is billed only when CostProof shows savings of at least 5x the fee. See full pricing →

CostWall

Assess it. Wall it. Protect it. Prove it.

Cut AI costs today: CostWall Lite, free →See the 54 workflows
AICost.ai pricing data keeps our calculations accurate across top AI and cloud vendors · last updated 2026-10-24

Methodology

  • All prices are USD per 1 million tokens, current as of 2026-10-24.
  • Vendor-published values have no mark. Inferred/extrapolated values are marked with * and listed below.
  • Batch API discounts are 50% off standard rates across providers that offer Batch mode.
  • Prompt caching discounts vary by provider (typically 80-90% off cached input tokens).
  • Regional data-residency surcharges (Anthropic 1.1x, OpenAI 1.1x, Google regional tiers) are NOT included in base rates.
  • Long-context pricing tiers apply when input exceeds model threshold.
  • Embedding prices are input-only (no output tokens generated).

Primary sources

Last-verified date is the most recent successful daily snapshot (aicost_pricing_snapshots) or, when no snapshot exists yet, the latest successful crawler run (aicost_crawler_runs). 10 of 10 vendors are currently verified. Aggregator services (TokenCost, AI Pricing Guru, etc.) are not listed.

Anthropic
2026-10-24
https://www.anthropic.com/pricing
Daily snapshot since Sep 2023 · 710 days captured
Anthropic Docs
2026-10-24
https://platform.claude.com/docs/en/about-claude/pricing
Daily snapshot since Sep 2023 · 710 days captured
OpenAI
2026-10-24
https://openai.com/api/pricing/
Daily snapshot since Sep 2023 · 711 days captured
Google AI
2026-10-24
https://ai.google.dev/gemini-api/docs/pricing
Daily snapshot since Dec 2023 · 686 days captured
Google Vertex
2026-10-24
https://cloud.google.com/vertex-ai/generative-ai/pricing
Daily snapshot since Dec 2023 · 686 days captured
DeepSeek
2026-10-24
https://api-docs.deepseek.com/quick_start/pricing
Daily snapshot since May 2024 · 625 days captured
xAI
2026-10-24
https://x.ai/api
Daily snapshot since Nov 2024 · 543 days captured
Mistral
2026-10-24
https://mistral.ai/pricing
Daily snapshot since Dec 2023 · 684 days captured
Cohere
2026-10-24
https://cohere.com/pricing
Daily snapshot since Sep 2023 · 710 days captured
Voyage AI
2026-10-24
https://docs.voyageai.com/docs/pricing

Inferred values (marked with * in calculator tables)

Derived from industry conventions, not directly published by the vendor. Typical conventions: cached input = 10% of base (90% off), Batch API = 50% of base (50% off).

Vendor / Model Field Why it’s inferred
Anthropic — Claude Sonnet 4.6 cachedInput Derived at 10% of input rate — Anthropic publishes 90% cache-hit discount on this tier.
Anthropic — Claude Sonnet 4.5 cachedInput Derived at 10% of input rate; same 90% cache-hit convention as Sonnet 4.6.
Anthropic — Claude Sonnet 4.5 batchInput Derived at 50% of standard input — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Sonnet 4.5 batchOutput Derived at 50% of standard output — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Haiku 4.5 cachedInput Derived at 10% of input rate — Anthropic 90% cache-hit discount convention.
OpenAI — GPT-5.4 Mini cachedInput Derived at 10% of input — OpenAI documents automatic 90% discount on cache hits across GPT-5.x tier.
OpenAI — GPT-5.4 Nano cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Nano batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Nano batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Pro batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.2 cachedInput Derived at 10% of input; no residency uplift.
OpenAI — GPT-5.2 batchInput Derived at 50% of input.
OpenAI — GPT-5.2 batchOutput Derived at 50% of output.
OpenAI — GPT-5 cachedInput Derived at 10% of input.
OpenAI — GPT-5 batchInput Derived at 50% of input.
OpenAI — GPT-5 batchOutput Derived at 50% of output.
OpenAI — GPT-5.5 Pro cachedInput Derived at 10% of input — OpenAI does not publish a cached rate for *-pro models; using the family convention.
OpenAI — GPT-5.5 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5.5 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5.2 Pro cachedInput Derived at 10% of input — pro-tier convention.
OpenAI — GPT-5.2 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5.2 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5.1 batchInput Derived at 50% of input.
OpenAI — GPT-5.1 batchOutput Derived at 50% of output.
OpenAI — GPT-5 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5 Nano cachedInput Derived at 10% of input.
OpenAI — GPT-5 Nano batchInput Derived at 50% of input.
OpenAI — GPT-5 Nano batchOutput Derived at 50% of output.
Google — Gemini 3 Flash cachedInput Derived at 10% of input — Google caching discount convention ~90%.
Google — Gemini 3.1 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
Google — Gemini 3.1 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 3.1 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Pro cachedInput Derived at 10% of input.
Google — Gemini 2.5 Flash cachedInput Derived at 10% of input.
Google — Gemini 2.5 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
Google — Gemini 2.5 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
xAI — Grok 4 (legacy) cachedInput Extrapolated at 25% of base.

Pricing is cross-verified against the LiteLLM community registry when available. Daily snapshots are kept in aicost_pricing_snapshots; every change is logged to aicost_price_changelog with old & new values for full audit trail. Read the full methodology →