Topic
LLM APIs
The model endpoints themselves: pricing, context windows, rate limits and the gateways in front of them.
Measured 2026-W36 · 2026-08-31 · google.com, gl=us
2026-W36
The shape of this topic
Queries measured
226
every week
AI Overview coverage
50.4%
corpus average 50.8%
Organic results
8.7
average per query
Weekly churn
14%
of the top 10 changes
Google answers llm apis queries itself less often than average — 50.4 against 50.8 percent across the corpus.
Citations
Who Google cites here
Rankings
Who ranks here
The gap
Cited more often than ranked
| Domain | Citations | Page-one finishes | Gap |
|---|---|---|---|
| docs.cloud.google.com | 17 | 0 | +17 |
| cloudflare.com | 17 | 0 | +17 |
| mistral.com | 16 | 0 | +16 |
| ai.google.dev | 16 | 0 | +16 |
| docs.together-ai.com | 15 | 0 | +15 |
| vllm.io | 15 | 0 | +15 |
| en.wikipedia.org | 12 | 0 | +12 |
These domains earn a place in Google's own answer more often than they earn a place on page one. Whatever gets a source into an AI Overview, it is not only ranking.
Intent
By what the searcher wants
| Intent | Queries | AI Overview |
|---|---|---|
| commercial | 73 | 37.0% |
| informational | 99 | 72.7% |
| comparison | 28 | 39.3% |
| navigational | 14 | 14.3% |
| support | 12 | 16.7% |
Intent is assigned when the query enters the corpus, not inferred afterwards, so this split is stable from week to week.
Blocks
Result features
Index
Queries in this topic
best llm apisllm apis comparisonllm apis for beginnersopen source llm apisllm apis pricing comparisonhow does llm apis workhow to use Claude APIClaude API not workingis Claude API freeClaude API exampleClaude API tutorialClaude API reviewClaude API apiClaude API pythonClaude API best practicesClaude API alternativesClaude API documentationOpenAI API pythonOpenAI API exampleis OpenAI API freeOpenAI API pricingOpenAI API reviewOpenAI API alternativesOpenAI API best practicesOpenAI API apiOpenAI API tutorialOpenAI API rate limitshow to use OpenAI APIwhat is OpenAI APIis Gemini API freeGemini API tutorialGemini API pricingwhat is Gemini APIGemini API documentationhow to use Gemini APIGemini API best practicesGemini API alternativesGemini API pythonGemini API reviewGemini API apiGemini API examplehow to use Mistral APIMistral API reviewMistral API tutorialMistral API pricingMistral API alternativesMistral API not workingMistral API best practicesis Mistral API freewhat is Mistral APIMistral API exampleMistral API pythonMistral API documentationis Cohere API freeCohere API pricingCohere API not workingCohere API documentationCohere API alternativesCohere API pythonCohere API apiCohere API best practicesCohere API examplehow to use Cohere APIwhat is Cohere APICohere API tutorialGroq pythonGroq apiis Groq freeGroq reviewwhat is GroqGroq rate limitsGroq examplehow to use GroqGroq alternativesGroq not workingGroq documentationGroq best practicesTogether AI exampleis Together AI freeTogether AI documentationTogether AI tutorialwhat is Together AITogether AI rate limitsTogether AI apiTogether AI not workingTogether AI alternativesTogether AI pythonTogether AI pricingFireworks AI alternativeswhat is Fireworks AIFireworks AI pricingFireworks AI exampleFireworks AI best practicesFireworks AI pythonFireworks AI rate limitsis Fireworks AI freehow to use Fireworks AIFireworks AI tutorialFireworks AI not workingFireworks AI documentationOpenRouter apiOpenRouter not workinghow to use OpenRouterwhat is OpenRouterOpenRouter documentationOpenRouter pricingOpenRouter rate limitsOpenRouter alternativesOpenRouter tutorialOpenRouter pythonOpenRouter reviewis OpenRouter freeLiteLLM rate limitsLiteLLM not workingwhat is LiteLLMis LiteLLM freeLiteLLM pythonLiteLLM documentationLiteLLM best practicesLiteLLM exampleLiteLLM apiLiteLLM tutorialBedrock reviewis Bedrock freeBedrock rate limitsBedrock pythonBedrock pricingBedrock alternativesBedrock tutorialBedrock best practicesBedrock not workingwhat is BedrockBedrock exampleBedrock apiVertex AI documentationis Vertex AI freeVertex AI pricingVertex AI tutorialwhat is Vertex AIVertex AI best practicesVertex AI reviewVertex AI alternativesVertex AI rate limitsVertex AI apihow to use Vertex AIVertex AI exampleis Azure OpenAI freeAzure OpenAI documentationAzure OpenAI apiAzure OpenAI rate limitsAzure OpenAI reviewhow to use Azure OpenAIAzure OpenAI alternativesAzure OpenAI not workingAzure OpenAI pythonAzure OpenAI best practiceswhat is Azure OpenAIAzure OpenAI pricingis Ollama freeOllama not workingOllama best practicesOllama alternativeshow to use OllamaOllama pythonwhat is OllamaOllama apiOllama reviewOllama pricingOllama documentationvLLM pricingvLLM apiis vLLM freevLLM examplevLLM documentationwhat is vLLMhow to use vLLMvLLM tutorialvLLM pythonvLLM alternativesvLLM best practicesReplicate reviewReplicate alternativesReplicate apiReplicate pricingReplicate not workingwhat is Replicatehow to use ReplicateReplicate pythonReplicate best practicesClaude API vs OpenAI APIClaude API vs Mistral APIOpenAI API vs Gemini APIOpenAI API vs Cohere APIGemini API vs Mistral APIMistral API vs Cohere APIMistral API vs Together AICohere API vs GroqCohere API vs Fireworks AIGroq vs Together AIGroq vs OpenRouterTogether AI vs Fireworks AITogether AI vs LiteLLMFireworks AI vs OpenRouterFireworks AI vs BedrockOpenRouter vs LiteLLMOpenRouter vs Vertex AILiteLLM vs Azure OpenAIBedrock vs Vertex AIBedrock vs OllamaVertex AI vs Azure OpenAIAzure OpenAI vs OllamaAzure OpenAI vs ReplicateOllama vs vLLMvLLM vs Replicate
API
Measure a topic of your own
Pick your queries, run them on a schedule, keep what comes back. That is the whole method — the endpoint below returns the overview, its citations and the organic results together.
curl --request GET \
--url 'https://serpens.p.rapidapi.com/api/v1/search_ai_overview?q=best%20llm%20apis&gl=us&hl=en&format=json' \
--header 'x-rapidapi-host: serpens.p.rapidapi.com' \
--header 'x-rapidapi-key: YOUR_KEY'Start measuring
Free tier, no card. Same endpoint that produced every number on this page.