Dashboard

Live demo — see LLMIntel with a week of real traffic | LLMIntel<br>◷LLMIntel<br>API docs<br>A sample LLMIntel dashboard with a week of realistic traffic across three apps.<br>▦You’re viewing demo data — this is what LLMIntel looks like with a week of real traffic. Sign up and your own data appears minutes after your first instrumented call.<br>Get your API key →2-minute quickstart

Overview<br>Models you run

Need attention (≤90d / deprecated)

$0.05–5.32<br>Input $/1M spread

$0.4–16<br>Output $/1M spread

Lifecycle health<br>ModelStateRetirementmeta.llama3-1-405b-instruct-v1:0retiringin 21 days2026-07-28

Cost analysis<br>Pricing known for 6 of 6 models you run. Cheapest by input: gpt-5-nano-2025-08-07 at $0.05/1M.<br>Want cheaper/faster on-par alternatives for these models? See optimization →

Cost & usage<br>TodayLast 7 daysLast 30 daysMonth to dateLast monthCustom range<br>Times in UTC · 13 months of history on your plan · sample data — send telemetry to see your own, range-filtered

FiltersApp ▾<br>Env ▾<br>Providerallanthropic ($621)openai ($333)azure ($118)bedrock ($212)Modelallclaude-sonnet-4-5-20250929 ($621)gpt-5-2025-08-07 ($292)gpt-5-mini-2025-08-07 ($32)gpt-5-nano-2025-08-07 ($8)gpt-4o (2024-08-06) ($118)meta.llama3-1-405b-instruct-v1:0 ($212)Tagfeatureteamanycheckout ($604)search ($401)summarize ($188)

Spend trend<br>Stack byTotalApplicationEnvironmentModelProviderTag

$1,284.06<br>Tracked spend · last 30 days ▲ +9.9%

412,000<br>Requests ▲ +7.5%

96M<br>Total tokens ▲ +11%

$13.32<br>Blended rate · $/1M tokens

−$48.74<br>Caching savings (est.)· 27M cached

$212.40<br>At-risk spend · retiring ≤90d

Cost is frozen at ingest — priced from each model's rates at call time, so past spend never shifts. Window: last 30 days.<br>Telemetry up to Jul 7, 16:32 UTC · 8 min ago· Catalog checked 42 min ago<br>Responses getting longer<br>These models are returning more output per input token than their 30-day baseline — the usual cause of silent cost creep. Check prompts, max_tokens, and whether a cheaper or more concise model would do.<br>ModelNowBaselineDriftRequestsSpendclaude-sonnet-4-5-202509290.3×0.2×+38%101,040$620.86

At-risk spend<br>Dollars flowing through models that retire within 90 days. Migrate before the provider 4xxs you — see recommended replacements on each model page.<br>ModelRetirementSpendmeta.llama3-1-405b-instruct-v1:0in 21 days2026-07-28$212.40

Spend by source<br>Environment › Application — expand any row to drill in<br>Group byEnvironment › ApplicationApplication › API keyAPI key › EnvironmentFilter tagfeatureteamany valuecheckoutsearchsummarize<br>Environment › ApplicationRequestsTokensBlended $/1MCost/reqSpendShare▸prod379,00086M$13.16$0.0030$1,131.6688%Checkout Assistant261,00058M$12.77$0.0028$742.1158%Support Copilot118,00028M$13.96$0.0033$389.5530%▸staging33,00010M$14.65$0.0046$152.4012%Unassignedno app mapping33,00010M$14.65$0.0046$152.4012%<br>How is this allocated?Choose the root dimension with Group by ; the tree nests it over the next dimension in the rotation Environment → Application → API key . An application comes from the app tag your agent sends or the API key's app mapping; calls with neither show as Unassigned (map keys under Applications or send an app tag). Unattributed keys are usage recorded before per-key attribution shipped. Nothing is ever smeared across buckets, and the tree follows the active filters (including the tag filter above). Share is relative to the total spend in view.<br>Custom tag breakdowns<br>grouped by tag key<br>Tag: feature4 valuesfeatureRequestsTokensBlended $/1MCost/reqSpendSharecheckout214,00048M$12.51$0.0028$604.3247%search121,00028M$14.54$0.0033$401.1831%summarize54,00013M$14.68$0.0035$187.9615%Untaggedno feature tag23,0007.7M$11.77$0.0039$90.607%

Tag: team3 valuesteamRequestsTokensBlended $/1MCost/reqSpendSharegrowth268,00061M$12.75$0.0029$771.2460%platform144,00033M$13.70$0.0031$452.2235%Untaggedno team tag04.3M$14.09—$60.605%

Spend by model<br>ModelProviderRequestsInputOutputBlended $/1MCost/reqTokens/reqOut:inSpendclaude-sonnet-4-5-20250929Anthropic168,40031M14M cached<br>8.5M$15.64$0.00372360.3×$620.86gpt-5-2025-08-07OpenAI96,80022M9.0M cached<br>6.9M$9.98$0.00303030.3×$292.40gpt-5-mini-2025-08-07OpenAI74,30012M3.6M cached<br>3.4M$2.09$0.00042090.3×$32.40gpt-5-nano-2025-08-07OpenAI41,9005.6M1.5M$1.13$0.00021690.3×$8.00gpt-4o (2024-08-06)Azure AI Foundry22,6002.9M900k$31.05$0.00521680.3×$118.00meta.llama3-1-405b-instruct-v1:0AWS Bedrock8,000780k220k$212.40$0.02661250.3×$212.40

Optimization<br>Optimization<br>Analysis: Artificial Analysis · advisory<br>gpt-5-2025-08-07<br>GPT-5 miniinput −80% · output −80% · same capability class

Compare

meta.llama3-1-405b-instruct-v1:0<br>Claude Sonnet 4.5switch to anthropiccurrent model retiring ≤90d · higher capability class · context 2.5×

Compare