AI API Router Directory

Amazon Polly is AWS's text-to-speech service, billed monthly per character of text converted to speech or Speech Marks. Published rates per 1 million characters are $4.00 Standard, $16.00 Neural, $100.00 Long-Form and $30.00 Generative (GovCloud US: $4.80 Standard, $19.20 Neural). The free tier includes 5 million Standard characters per month plus 1 million Neural, 500,000 Long-Form and 100,000 Generative characters per month for the first 12 months.

Up to $200 in AWS Free Tier credits for new customers (from July 15, 2025), applicable to eligible services including Polly; AWS states $100 in credits immediately plus up to $100 more earned, on a free plan lasting 6 months with credits expiring 12 months after account creation.

Deepgram sells speech-to-text, text-to-speech and voice-agent APIs on pay-as-you-go terms with a $200 free credit and no credit card required at sign-up. Speech-to-text is billed per minute: Nova-3 is $0.0043/min pre-recorded monolingual and $0.0052/min multilingual (about $0.29 and $0.35 per hour streaming), while Flux for real-time agents is $0.0065/min English and $0.0078/min multilingual under limited-time promotional rates. Text-to-speech runs from $0.0150/1k characters (Aura-1) to $0.0450/1k characters (Flux TTS), and the Voice Agent API starts at $0.050/min.

$200 free credit on the Pay As You Go plan, stated on deepgram.com/pricing as 'Free $200 Credit then pay-as-you-go' with 'No credit card required' and 'No minimums. No expiration.'

Speechmatics is a speech-to-text API (real-time WebSocket and async batch) with NLP insights (summaries, intents, sentiment). Self-serve Free and Pro plans: new sign-ups get a $100 credit grant (1 credit = $1) with no card required; Pro adds pay-as-you-go billing with volume discounts above 500 hours/month; Enterprise is contract-based with on-prem/on-device deployment. Rates start around $0.129/hr (2026 pricing page snippet); legacy free tier was 8 hours/month.

Official docs: new sign-ups receive a $100 credit grant at no cost (1 credit = $1 USD), usable on Free at no charge and drawn down first on Pro — direct 1:1 credit value. (Pre-Accounts before 2026-08-01 receive an additional one-time $25 transition credit.)

You.com Search API: real-time LLM-ready web + news search (you-search), plus Contents, Research, Answer, and Finance Research APIs. Free keyless MCP access at 100 queries/day; new API accounts start with $100 in complimentary credits (no card); per-usage credit billing for higher tiers.

$100 in complimentary credits granted to new API accounts at you.com/platform, no credit card required (one-time).

Gladia is a speech-to-text API for real-time streaming and async transcription in 100+ languages with speaker diarization, word-level timestamps, and automatic language detection. Prepaid credit wallet: Starter $0.61/hr async, $0.75/hr real-time; Growth from $0.20/hr async and $0.25/hr real-time (volume-committed); Enterprise custom. New accounts get 50€ in one-time free credits.

50€ one-time free credit grant (no monthly reset); ≈ $54 at ~1.08 EUR/USD. Per Gladia FAQ, roughly 80+ hours of async or 60+ hours of real-time transcription at current rates.

Context7 (Upstash): library/developer-docs search API — find up-to-date documentation snippets for libraries, frameworks, and codebases. API key optional: anonymous access has low shared rate limits; free API key (ctx7sk) at context7.com/dashboard raises limits. Not a general web search.

Free tier exists (anon + free API key) but Context7 publishes no public per-query price, so value cannot be quantified honestly.

Exa: neural web search API for AI agents — keyword + semantic search over a 70B+ document index, plus Deep Search, Contents, and Agent products. 10 QPS free, 25 QPS pay-as-you-go; SOC 2 Type II; ~$120 total credits per year free (20 at signup + 10/month).

Free tier is $20 one-time + $10/month credits (>$120/yr total) — recurring monthly value is $10 but free credits exceed the $10 search budget at $7/1k requests, so not expressed as a single clean USD figure.

AssemblyAI sells speech-to-text, speech understanding and voice agent APIs with pay-as-you-go hourly pricing and no credit card required to start. The free tier is published as up to 185 hours of pre-recorded transcription and up to 333 hours of streaming transcription. Published rates are $0.15 per hour for Universal-2 (99 languages) and $0.21 per hour for Universal-3.5 Pro (18 languages with native code switching), while realtime runs at $0.15 per hour for Universal-Streaming (English) and multilingual, or $0.45 per hour for Universal-3.5 Pro Realtime. The Voice Agent API is $4.50 per hour ($0.075 per minute) with every feature included, and the Dictation API is $0.62 per hour.

Free tier is stated as up to 185 hours of pre-recorded transcription and up to 333 hours of streaming transcription with no credit card required; valued at the lowest published pre-recorded rate (Universal-2 at $0.15 per hour) this is about $27.75, an estimate because AssemblyAI publishes hours rather than a USD credit (assemblyai.com/pricing, checked 2026-09-16).

Grok X Search (xAI): x_search tool enabling Grok models to run keyword/semantic search, user search, and thread fetch over real-time X (Twitter) data; usable via xAI SDK, OpenAI-compatible Responses API, or Vercel AI SDK. Billed at $5 per 1,000 tool calls (changes Sep 21, 2026 to $5/1k posts + $10/1k profiles fetched); new xAI API accounts get $25 promotional credits; no free tier specific to X Search.

New console.x.ai accounts receive $25 promotional API credits usable against model + X Search usage (one-time).

Tavily: search API purpose-built for AI agents — basic (1 credit) and advanced (2 credits) search, extract, map, crawl, and Research (dynamic credits). Free 1,000 credits/month refreshed on the 1st, no card; pay-as-you-go $0.008/credit; monthly plans $30-$100+ at $0.0075-$0.005/credit; enterprise custom. Free for students program.

1,000 free credits/month × $0.008/credit PAYG rate = $8.00/month equivalent (basic searches).

Brave Search API: real-time web search (LLM-optimized context, news, images, videos) and Answers endpoint, powered by Brave's independent index of 30B+ pages. 50 req/s capacity on search; $5 free credits auto-applied monthly; credit card required as anti-fraud. SOC 2 Type II attested, zero-data-retention options.

$5 free credit auto-applied to account every month (per brave.com/search/api and API dashboard pricing page).

Firecrawl: web-to-LLM-context platform — scrape, crawl, map, search, extract, and browser Interact APIs. Credits-based: 1 credit = 1 page (scrape/crawl/map); search costs 2 credits per 10 results. Free 1,000 credits/month (500 searches) with no card; paid subs from $16-19/mo with pay-as-you-go overage in $5 increments (paid plans only).

Free 1,000 credits/mo ≈ 500 searches (2 credits per 10 results) or 1,000 pages; Firecrawl publishes no per-search dollar price for the free allocation, so value left null.

Serper: fast (1-2s) Google SERP API — web, news, images, places, scholar, patents, videos, shopping, autocomplete as structured JSON. Credit-based prepaid billing: 2,500 free credits on signup, $1.00/1k base dropping to $0.30/1k at volume; credits valid 6 months; failed requests not billed. (Official pricing page is 404 — figures corroborated across multiple independent 2026 sources.)

2,500 free signup credits × $1.00/1k base rate ≈ $2.50 (one-time, credits expire in 6 months).

Cartesia provides Sonic text to speech, Ink speech to text and Managed Agents voice agents, priced through credits and prepaid agent minutes with unlimited workspace seats on every plan. The Free plan costs $0 and includes 20,000 credits per month (about 27 minutes of Sonic-3.6 text to speech) plus $1 of prepaid agent minutes; Pro is $5 per month with 100,000 credits, Startup is $49 per month with 1.25M credits, and Scale is $299 per month with 8M credits. Agent calls bill at $0.06 per minute on every tier, and telephony is $0.014 per minute when using a Cartesia-provided phone number.

Free plan grants 20,000 credits per month (about 27 minutes of Sonic-3.6 text to speech) plus $1 of prepaid agent minutes; the credits are worth about $1.00 at the Pro plan rate of $5 per 100,000 credits, giving roughly $2.00 combined, an estimate because Cartesia does not price the free allowance in USD (cartesia.ai/pricing, checked 2026-09-16).

ElevenLabs is a voice AI platform whose API covers text to speech, speech to text, sound effects, voice design, music and dubbing from one shared monthly credit pool. The Free plan costs $0 and includes 10,000 credits per month; paid plans start at Starter ($6/month, 30,000 credits) and rise to Creator ($22/month, 121,000 credits), Pro ($99/month, 600,000 credits), Scale ($299/month, 1,800,000 credits with 3 seats) and Business ($990/month, 6,000,000 credits with 10 seats). For V2 Multilingual models 1 text character equals 1 credit, while V2 Flash/Turbo English and V2.5 Flash/Turbo Multilingual cost 0.5 to 1 credit per character on API usage; speech to text is metered at 330 credits per minute.

Free plan is published as 10,000 credits per month at $0; valued at the Starter plan rate ($6 per 30,000 credits) this is about $2.00 per month, an estimate because ElevenLabs does not price the free allowance in USD (elevenlabs.io/pricing, checked 2026-09-16).

Rev AI (rev.com API) offers machine transcription (Reverb/Reverb Turbo), translation, summarization and voice agents, plus human transcription. Pay-as-you-go API with free signup credits equivalent to 5 hours of Reverb ASR (usable on all products); volume-based pricing; enterprise options with dedicated account management.

Free credits equivalent to 5 hours of Reverb ASR (official pricing page). At Reverb's published rate of $0.20/hour (via pricing-page search snippet), 5h ≈ $1.00.

SearchAPI: Google/Bing/Bing/30+ engines SERP API — structured JSON results in seconds; billed only for successful 200-status searches; 100 free requests at signup (no card); prepaid subscription plans $40-$5,000/mo (Developer 10k searches at $4/1k down to Octo 5M at $1/1k); rate limit = 20% of plan credits/hour; up to $2M legal protection guarantee.

100 free signup requests × $0.004/search (Developer plan rate $4/1k) ≈ $0.40 one-time value.

Fish Audio (fish.audio) is a voice AI platform offering text-to-speech, speech-to-text, voice cloning and real-time streaming through a web app, REST API and SDKs, billed per million UTF-8 bytes rather than per character. Its developer pricing page lists s2.1-pro, s2-pro and s1 at $15.00 per million UTF-8 bytes (about 180,000 English words or 12 hours of speech), ASR transcribe-1 at $0.36 per audio hour and voice-design-1 at $0.01 per successful request, and states there are no subscription fees or monthly minimums for API access. A free counterpart model, s2.1-pro-free, is priced at $0.00 per million UTF-8 bytes with the same quality and 83-language coverage as the paid model but without time-to-first-audio or deployment-slot guarantees.

s2.1-pro-free is priced at $0.00 per 1M UTF-8 bytes in the official pricing table on docs.fish.audio — a free model rather than a cash credit, subject to fair-use limits and without TTFA or DPA guarantees (checked 2026-09-16).

Google Programmable Search Engine (Custom Search JSON API): programmatic web/image search results from a configured Programmable Search Engine. 100 free queries/day, $5 per 1,000 additional queries up to 10k/day. IMPORTANT: service discontinues January 1, 2027 and is not available to new customers — legacy pricing applies only to existing customers.

Free tier is 100 queries/day ≈ 3,000/mo × $5/1k ≈ ~$15/mo equivalent if fully used, but the free allotment resets daily and is capped at 100/day; not a purchased credit grant, so left null.

Inworld AI is a voice AI platform for interactive agents, combining TTS, STT, and LLM into a unified credit system for games and real-time voice agents. Monthly plans allocate credits usable across all products; higher tiers add volume discounts and higher limits. Detailed plan pricing is rendered dynamically on the pricing page (not captured).

Plan credit amounts and USD values are rendered by JavaScript on the pricing page and were not captured; no reliable USD quantification.

Linkup: production web search API for AI — Search (sub-200ms to ~30s ranked results/answers), Fetch (clean markdown), Research (async deep reports), Tasks, Extract. 4,000 free queries; per-request pricing $0.001-$0.006 for search, $0.25-$2.50 for research; SOC 2 Type II on all tiers, ZDR on Enterprise; $5,000 startup credit program.

4,000 free queries; at $0.005-0.006/query that is ~$20-24 of value, but the free grant is a fixed query count (not credits) so left null for honesty.

Ollama (ollama.com) is primarily a local runtime for open models - the ollama.com pricing page lists a Free plan at $0 whose first feature is "Run models locally" and states plainly that "Local models are always free" - and it also operates a cloud API for models too large for local hardware. The cloud side is priced per million tokens with a published table (for example gpt-oss:20b at $0.07 input / $0.30 output, gemma4 at $0.14 / $0.40, deepseek-v4.1-flash at $0.15 / $0.60 and kimi-k3 at $3.00 / $15.00), with higher peak pricing between 12:00 and 18:00 UTC Monday to Friday. Paid plans bundle usage credits: Pro is $20/mo including $60 of usage, Max is $100/mo including $300, and Team is $500/mo including $1,000 of shared credits, while Free accounts receive a starter amount of usage on a smaller set of starter models and can add credits to unlock all models.

No free tier stated on official pages (checked 2026-09-16): the Ollama Free plan lists "Starter usage credits included" and "Includes access to starter models" at $0, but no dollar or token amount is published; local model usage is stated to be always free.

web search provider (API). Same API key as Ollama Cloud (from ollama.com/settings/keys) 1 model tracked (curated from provider docs).

A free tier is available; the exact credit value is not quantified.

web search provider (API). Same API key as Perplexity (pplx-...) 5 models tracked (via OpenRouter catalog).

A free tier is available; the exact credit value is not quantified.