# Generated from data/providers.json — do not edit by hand.
providers:
  - slug: "google-gemini"
    name: "Google Gemini API (AI Studio)"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Gemini 2.5 Flash, 2.5 Flash-Lite, 2.5 Pro (limited), embeddings, TTS models"
    rate_limits: "Varies by model, roughly 5-30 req/min and 20-500 req/day depending on model"
    notes: "Free-tier prompts/outputs may be used by Google to improve its products when used outside the UK/CH/EEA/EU"
    best_for: "The only frontier-class model with a genuine free tier"
    modalities: ["text", "vision", "embeddings", "audio"]
    models_free: ["gemini-2.5-flash", "gemini-2.5-flash-lite", "gemini-2.5-pro"]
    expires: null
    docs_url: "https://ai.google.dev/gemini-api/docs/rate-limits"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://generativelanguage.googleapis.com/v1beta/openai/"
    verified: true
    last_verified: "2026-07-11"
  - slug: "groq"
    name: "Groq"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Open-weight models (Llama, Qwen, GPT-OSS) plus Whisper, no credit card required"
    rate_limits: "e.g. llama-3.1-8b-instant: 30 RPM/14.4K RPD/6K TPM/500K TPD; llama-3.3-70b-versatile: 30 RPM/1K RPD/12K TPM/100K TPD; qwen3-32b: 60 RPM/1K RPD/6K TPM/500K TPD; similar for GPT-OSS and Whisper models"
    notes: "Limits apply at the organization level, not per API key. Phone verification required at signup"
    best_for: "Lowest-latency inference for open-weight models"
    modalities: ["text", "audio"]
    models_free: ["llama-3.3-70b-versatile", "llama-3.1-8b-instant", "openai/gpt-oss-120b", "openai/gpt-oss-20b", "whisper-large-v3-turbo", "whisper-large-v3"]
    expires: null
    docs_url: "https://console.groq.com/docs/rate-limits"
    phone_required: true
    card_required: false
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://api.groq.com/openai/v1"
    verified: true
    last_verified: "2026-07-11"
  - slug: "openrouter"
    name: "OpenRouter"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "20+ models with a :free suffix, single API across many providers"
    rate_limits: "20 req/min; 50 req/day under 10 credits purchased lifetime, 1000 req/day once 10+ credits purchased (one-time, not a subscription)"
    notes: "ToS (Apr 2026) prohibits resale or building a competing service on the free models; a private proxy for personal use is fine"
    best_for: "Widest model selection behind one no-card key"
    modalities: ["text", "vision"]
    models_free: ["cohere/north-mini-code:free", "google/gemma-4-26b-a4b-it:free", "google/gemma-4-31b-it:free", "inclusionai/ling-3.0-flash:free", "nvidia/nemotron-3-nano-30b-a3b:free", "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "openai/gpt-oss-20b:free", "poolside/laguna-s-2.1:free"]
    expires: null
    docs_url: "https://openrouter.ai/docs/api-reference/limits"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://openrouter.ai/api/v1"
    verified: true
    last_verified: "2026-07-11"
  - slug: "cloudflare-workers-ai"
    name: "Cloudflare Workers AI"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "10,000 Neurons/day, all account plans"
    rate_limits: "30+ models: LLMs (Llama, Mistral, DeepSeek, Qwen...), embeddings, image, audio"
    notes: "Resets daily at 00:00 UTC; overage on a Workers Paid plan bills at $0.011/1,000 Neurons"
    best_for: "Highest free daily volume for a real side project"
    modalities: ["text", "embeddings", "image", "audio"]
    models_free: ["@cf/meta/llama-3.3-70b-instruct-fp8-fast", "@cf/meta/llama-3.1-8b-instruct", "@cf/mistralai/mistral-small-3.1-24b-instruct", "@cf/qwen/qwen2.5-coder-32b-instruct", "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "@cf/google/gemma-3-12b-it"]
    expires: null
    docs_url: "https://developers.cloudflare.com/workers-ai/platform/pricing/"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1"
    verified: true
    last_verified: "2026-07-11"
  - slug: "github-models"
    name: "GitHub Models"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Included with any GitHub account via the Copilot tier"
    rate_limits: "Copilot Free: ~15 RPM / 150 RPD on \"low\" tier models, 8K input / 4K output tokens per request. Higher Copilot tiers raise the ceiling"
    notes: "Scoped by GitHub to experimentation/prototyping, not production traffic"
    best_for: "Zero extra signup if you already have a GitHub account"
    modalities: ["text"]
    models_free: ["cohere/cohere-command-a", "deepseek/deepseek-r1", "deepseek/deepseek-r1-0528", "meta/llama-3.2-11b-vision-instruct", "meta/llama-3.2-90b-vision-instruct", "microsoft/phi-4", "mistral-ai/codestral-2501", "openai/gpt-4.1"]
    expires: null
    docs_url: "https://docs.github.com/en/github-models/prototyping-with-ai-models"
    phone_required: false
    card_required: false
    commercial_ok: false
    openai_compatible: true
    openai_base_url: "https://models.github.ai/inference"
    verified: true
    last_verified: "2026-07-11"
  - slug: "cohere"
    name: "Cohere"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Trial (evaluation) API keys covering chat, embed and rerank"
    rate_limits: "1,000 API calls/month total; 20 req/min chat; 2,000 inputs/min embed; 10 req/min rerank"
    notes: "Explicitly for evaluation only — Cohere's terms prohibit production/commercial use on a trial key"
    best_for: "Free embeddings and rerank for RAG prototypes"
    modalities: ["text", "embeddings", "rerank"]
    models_free: ["command-a-03-2025", "command-r-plus-08-2024", "command-r-08-2024", "command-r7b-12-2024", "embed-v4.0", "rerank-v3.5"]
    expires: null
    docs_url: "https://docs.cohere.com/docs/rate-limits"
    phone_required: false
    card_required: false
    commercial_ok: false
    openai_compatible: true
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "cerebras"
    name: "Cerebras"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Access to all Cerebras-hosted models"
    rate_limits: "Officially published per-model: 5 RPM / 30,000 TPM / 1,000,000 TPH / 1,000,000 TPD (e.g. gpt-oss-120b, zai-glm-4.7, gemma-4-31b); limits vary by model"
    notes: "Free tier includes community support (Discord) only; paid Developer tier gives \"10x higher\" rate limits"
    best_for: "Fastest tokens/sec on wafer-scale hardware"
    modalities: ["text"]
    models_free: ["gpt-oss-120b", "zai-glm-4.7", "gemma-4-31b"]
    expires: null
    docs_url: "https://inference-docs.cerebras.ai/support/rate-limits"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://api.cerebras.ai/v1"
    verified: true
    last_verified: "2026-07-11"
  - slug: "mistral"
    name: "Mistral (La Plateforme)"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "\"Restrictive\" free tier explicitly for \"try and explore\" — official docs say to upgrade for \"actual projects and production use\""
    rate_limits: "Not published publicly; exact caps only visible in-console after login (admin.mistral.ai)"
    notes: "Phone verification required to activate; free tier is opt-in for data training"
    best_for: "European models to prototype against before upgrading"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://docs.mistral.ai/admin/billing-usage/usage-limits"
    phone_required: true
    card_required: null
    commercial_ok: false
    openai_compatible: null
    openai_base_url: null
    verified: true
    last_verified: "2026-07-12"
  - slug: "huggingface"
    name: "HuggingFace"
    category: "ongoing"
    free_type: "recurring-credit"
    free_tier: "Free CPU Basic + ZeroGPU for Spaces; Inference Providers has a monthly credit ($0.10/mo on Free plan, $2.00/mo on PRO/Team/Enterprise)"
    rate_limits: "No RPM/TPM published, only credit amounts"
    notes: "Credits only apply with \"Routed by Hugging Face\" billing, not with a Custom Provider Key"
    best_for: "Router access to many open-weight providers under one key"
    modalities: ["text", "image", "audio", "embeddings"]
    models_free: null
    expires: null
    docs_url: "https://huggingface.co/docs/inference-providers/en/pricing"
    phone_required: null
    card_required: false
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://router.huggingface.co/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "siliconflow"
    name: "SiliconFlow"
    category: "ongoing"
    free_type: "perpetual"
    free_tier: "Several models permanently free (e.g. Qwen2.5-7B-Instruct and others) at $0 cost, plus a $1 welcome credit for paid models"
    rate_limits: "Fixed per-model limits for free models; generic docs cite ranges of 1,000-10,000 RPM and 50,000-5,000,000 TPM depending on model tier — exact limits shown in-account"
    notes: "Signup requires SMS phone verification. Full \"real-name authentication\" (needed for recharging/billing) requires a mainland China, Hong Kong/Macao, or Taiwan ID document — this may limit full access for users without one, though basic use of free models appears reachable with standard account verification"
    best_for: "Permanently-free open models, no trial clock"
    modalities: ["text", "embeddings"]
    models_free: null
    expires: null
    docs_url: "https://docs.siliconflow.cn/en/userguide/rate-limits/rate-limit-and-upgradation"
    phone_required: true
    card_required: null
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://api.siliconflow.com/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "zai-glm"
    name: "Z.ai (Zhipu AI / GLM)"
    category: "ongoing"
    free_type: "perpetual"
    free_tier: "GLM-4.5-Flash, GLM-4.7-Flash (text), and GLM-4.6V-Flash (vision) are officially listed as $0 cost (input, cached input, and output) on a permanent basis"
    rate_limits: "Not specified with concrete RPM/TPM figures in public docs"
    notes: "Terms of Use prohibit using the service to \"develop, train, or improve\" competing algorithms or models — otherwise general use, including commercial, isn't restricted"
    best_for: "A permanently-free model with no trial clock"
    modalities: ["text", "vision"]
    models_free: ["glm-4.7-flash", "glm-4.5-flash", "glm-4.6v-flash"]
    expires: null
    docs_url: "https://docs.z.ai/guides/overview/pricing"
    phone_required: false
    card_required: null
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://api.z.ai/api/paas/v4/"
    verified: true
    last_verified: "2026-07-30"
  - slug: "ibm-watsonx"
    name: "IBM watsonx.ai (Lite plan)"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Lite plan: 300,000 tokens/month for foundation model inference, 20 CUH/month for ML tooling, 100 pages/month of document text extraction"
    rate_limits: "2 inference requests per second (explicitly documented for the Lite plan)"
    notes: "Lite plan doesn't support fine-tuning of foundation or custom models; 1-day idle deployment timeout. Never expires or bills while inside quota, but a payment method (with a nominal ~$1 authorization hold) is required at signup"
    best_for: "Governed enterprise inference with a monthly free quota"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://www.ibm.com/docs/en/watsonx/saas?topic=cloud-watsonxai-runtime-plans"
    phone_required: null
    card_required: true
    commercial_ok: null
    openai_compatible: true
    openai_base_url: null
    verified: true
    last_verified: "2026-07-11"
  - slug: "ovhcloud-ai-endpoints"
    name: "OVHcloud AI Endpoints"
    category: "ongoing"
    free_type: "perpetual"
    free_tier: "Several open-weight models in the catalog (e.g. Qwen3Guard) listed as $0 per token, permanently, via two access modes: anonymous (no account) and authenticated (API key tied to a Public Cloud project)"
    rate_limits: "Anonymous access: 2 requests/min per IP per model. Authenticated (API key): 400 requests/min per project per model. Exceeding either returns HTTP 429"
    notes: "European provider (France), relevant for EU data-sovereignty/GDPR-conscious use. The authenticated tier needs a valid payment method on the project (though \"Free\" models themselves don't charge); anonymous access needs neither an account nor a card. A separate general $200 Public Cloud trial voucher also exists but is unrelated to this permanent free-model tier"
    best_for: "EU-hosted, no-account access to open models"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/"
    phone_required: null
    card_required: true
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1"
    verified: true
    last_verified: "2026-07-11"
  - slug: "fireworks-ai"
    name: "Fireworks AI"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$1 trial credit"
    rate_limits: "Various open-weight models"
    notes: "Default monthly spend cap of $50 for new accounts; no card needed to activate the $1 credit, card needed once it's spent"
    best_for: "Fast hosted open models to trial with $1"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://docs.fireworks.ai/faq-new/billing-pricing/"
    phone_required: null
    card_required: false
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://api.fireworks.ai/inference/v1"
    verified: true
    last_verified: "2026-07-11"
  - slug: "baseten"
    name: "Baseten"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$30 trial credit"
    rate_limits: "Any supported model, compute-based pricing"
    notes: "No documented expiration date publicly"
    best_for: "Largest trial credit here for building something bigger"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://www.baseten.co/pricing/"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://inference.baseten.co/v1"
    verified: true
    last_verified: "2026-07-11"
  - slug: "nebius"
    name: "Nebius AI Studio"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$1 trial credit, valid for 30 days"
    rate_limits: "Various open-weight models"
    notes: "Product renamed to \"Nebius Token Factory\"; a bank card is required to set up billing"
    best_for: "Cheap open-model inference after a $1 trial"
    modalities: ["text"]
    models_free: null
    expires: "30 days"
    docs_url: "https://docs.tokenfactory.nebius.com"
    phone_required: false
    card_required: true
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://api.tokenfactory.nebius.com/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "novita"
    name: "Novita AI"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$1 free credit on signup"
    rate_limits: "Various open-weight models"
    notes: "Corrected from a previously listed \"$0.50/year\" figure, which does not appear on any official Novita domain; a separate referral program (\"Give $10, Earn $10\") also exists"
    best_for: "A quick $1 to trial open-weight models"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://novita.ai/pricing"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: true
    openai_base_url: null
    verified: true
    last_verified: "2026-07-11"
  - slug: "ai21"
    name: "AI21 Labs"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$10 trial credit, valid 3 months"
    rate_limits: "Jamba Large/Mini: 10 RPS / 200 RPM by default"
    notes: "Card not required for the trial credit itself, required once it expires"
    best_for: "Jamba long-context models on a $10 trial"
    modalities: ["text"]
    models_free: null
    expires: "3 months"
    docs_url: "https://docs.ai21.com/docs/usage-cost"
    phone_required: null
    card_required: false
    commercial_ok: null
    openai_compatible: null
    openai_base_url: null
    verified: true
    last_verified: "2026-07-11"
  - slug: "nlpcloud"
    name: "NLP Cloud"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$15 trial credit"
    rate_limits: "Variable by model, no numeric RPM/TPM published"
    notes: "Corrected: the official registration page does not ask for a phone number, contradicting the earlier listing"
    best_for: "NLP tasks (NER, classification, summarization) on a $15 trial"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://nlpcloud.com/pricing.html"
    phone_required: false
    card_required: true
    commercial_ok: true
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "alibaba-model-studio"
    name: "Alibaba Cloud (Model Studio)"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "1,000,000 tokens (example figure, varies by model), international/Singapore region only"
    rate_limits: "Qwen open & proprietary models"
    notes: "Excludes batch processing, context caching, fine-tuning, and dedicated deployment"
    best_for: "Qwen models with a large free token quota (Singapore region)"
    modalities: ["text"]
    models_free: null
    expires: "30-90 days"
    docs_url: "https://www.alibabacloud.com/help/en/model-studio/new-free-quota"
    phone_required: null
    card_required: false
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "modal"
    name: "Modal"
    category: "trial"
    free_type: "recurring-credit"
    free_tier: "$30/month recurring credit (Starter plan)"
    rate_limits: "Starter: 100 containers + 10 GPU concurrency, 5 crons, 1-day log retention"
    notes: "Corrected from a previously listed \"$5-30/month\" range; this is a recurring monthly credit, not a one-time trial. Modal is serverless compute you deploy models on, not a hosted model API"
    best_for: "Self-hosting open models on free monthly GPU credit"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://modal.com/pricing"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "sambanova"
    name: "SambaNova Cloud"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Rate-limited free tier (applies when no payment method is linked) across all models"
    rate_limits: "Free Tier: 20 RPM / 20 RPD / 200,000 TPD across all models; Developer Tier (card required): 60-240 RPM depending on model"
    notes: "Free Tier applies when no payment method is linked to the account; SambaCloud ToS grants a commercial license (no evaluation-only clause). The previously-listed \"$5 / 3 months\" trial could not be re-confirmed on official pages (2026-07-30)."
    best_for: "Fast open models on a rate-limited free tier"
    modalities: ["text"]
    models_free: ["DeepSeek-V3.1", "Meta-Llama-3.3-70B-Instruct", "gpt-oss-120b"]
    expires: null
    docs_url: "https://cloud.sambanova.ai/plans"
    phone_required: null
    card_required: false
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://api.sambanova.ai/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "scaleway"
    name: "Scaleway Generative APIs"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "1,000,000 tokens free + 60 min Whisper transcription; billing starts at token 1,000,001"
    rate_limits: "Gemma, Llama, Mistral, Qwen"
    notes: "European provider (France). Free allowance is a one-time token bucket, not time-limited"
    best_for: "EU-hosted open models with 1M free tokens"
    modalities: ["text", "audio"]
    models_free: ["llama-3.3-70b-instruct", "qwen3-235b-a22b-instruct-2507", "mistral-small-3.2-24b-instruct-2506", "deepseek-r1-distill-llama-70b", "gemma-3-27b-it", "qwen2.5-coder-32b-instruct"]
    expires: null
    docs_url: "https://www.scaleway.com/en/pricing/model-as-a-service/"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://api.scaleway.ai/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "nvidia-nim"
    name: "NVIDIA NIM"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "Trial credit, phone verification required"
    rate_limits: "Some models have reduced context windows on the free trial"
    notes: "\"Evaluation only, not production\" per NVIDIA's own Trial Terms of Service — NVIDIA may discontinue the trial at any time with no continuity obligation"
    best_for: "Trialling NVIDIA-optimized models (evaluation only)"
    modalities: ["text"]
    models_free: ["01-ai/yi-large", "adept/fuyu-8b", "ai21labs/jamba-1.5-large-instruct", "aisingapore/sea-lion-7b-instruct", "baai/bge-m3", "bigcode/starcoder2-15b", "databricks/dbrx-instruct", "deepseek-ai/deepseek-coder-6.7b-instruct"]
    expires: null
    docs_url: "https://build.nvidia.com/"
    phone_required: true
    card_required: null
    commercial_ok: false
    openai_compatible: true
    openai_base_url: "https://integrate.api.nvidia.com/v1"
    verified: true
    last_verified: "2026-07-11"
  - slug: "vercel-ai-gateway"
    name: "Vercel AI Gateway"
    category: "trial"
    free_type: "recurring-credit"
    free_tier: "Free tier with a monthly free credit covering a subset of models at lower rate limits"
    rate_limits: "Free tier is rate-limited per model (HTTP 429 on exceed), lower than paid; routes to many providers rather than hosting models itself"
    notes: "Free tier and its monthly-credit behaviour are confirmed in Vercel's own docs; the specific \"$5/month\" figure circulating in community posts is not stated there. Once you purchase credits, your account moves to the paid tier and the monthly free credit no longer applies."
    best_for: "One key across many providers with a free monthly credit"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://vercel.com/docs/ai-gateway/pricing"
    phone_required: null
    card_required: false
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://ai-gateway.vercel.sh/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "jina-ai"
    name: "Jina AI"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "10M free tokens (one-time) across all models — embeddings (v3/v4), rerankers, classifier; plus a keyless Reader (r.jina.ai) for basic use"
    rate_limits: "Free key: 100 RPM / 100k TPM for embeddings & reranker (2 concurrent); keyless Reader 20 RPM"
    notes: "The 10M-token balance is a one-time grant that does not replenish; the keyless Reader is genuinely ongoing. Hosted API is commercial-OK and data is not used for training. No card required."
    best_for: "Free embeddings & rerank behind an OpenAI-compatible endpoint"
    modalities: ["text", "image", "embeddings", "rerank"]
    models_free: null
    expires: null
    docs_url: "https://jina.ai/embeddings/"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://api.jina.ai/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "deepgram"
    name: "Deepgram"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$200 free credit on signup (no card, no expiration) — Nova speech-to-text and Aura text-to-speech at pay-as-you-go rates"
    rate_limits: "STT pre-recorded up to 50 concurrent; STT streaming up to 150; TTS REST up to 15; TTS streaming up to 45"
    notes: "No card and no expiration on the credit. Data catch: the Model Improvement Program is opt-OUT — send mip_opt_out=true per request to keep your data out of training. Native REST/WebSocket API, not OpenAI-compatible."
    best_for: "Biggest free credit here, for speech (STT/TTS)"
    modalities: ["audio"]
    models_free: null
    expires: null
    docs_url: "https://deepgram.com/pricing"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "assemblyai"
    name: "AssemblyAI"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$50 free credit on signup (no card) — pre-recorded & streaming speech-to-text, Speech Understanding, and an OpenAI-compatible LLM Gateway (25+ models)"
    rate_limits: "Free tier: 5 parallel transcriptions; streaming 5 new streams/min; global 20k requests / 5 min"
    notes: "One-time credit, not renewing. Catch: the default model differs between free and paid accounts — set speech_models explicitly to avoid cost jumps on upgrade. Only the LLM Gateway is OpenAI-compatible."
    best_for: "Free speech-to-text plus an OpenAI-compatible LLM gateway"
    modalities: ["audio", "text"]
    models_free: null
    expires: null
    docs_url: "https://www.assemblyai.com/pricing"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://llm-gateway.assemblyai.com/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "mixedbread"
    name: "Mixedbread"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "Starter plan: $5 one-time credit (no card) — embeddings (mxbai-embed-large-v1), reranking, and multimodal search over PDF/image/doc/code"
    rate_limits: "Starter plan: 100 requests/min"
    notes: "Free credit is usage-based and non-renewing; usage-based pricing applies afterward. Native REST API, not documented as OpenAI-compatible. No card required."
    best_for: "No-card embeddings & rerank credit"
    modalities: ["text", "embeddings", "rerank", "image"]
    models_free: null
    expires: null
    docs_url: "https://www.mixedbread.com/pricing"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "clarifai"
    name: "Clarifai"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "One-time $5 credit across serverless models (GPT-OSS-120B, Claude, Llama), vision, embeddings and image generation"
    rate_limits: "15 requests/second global default (CONN_THROTTLED on exceed)"
    notes: "Catch: SMS phone verification is required to claim the $5. Credit is one-time and expires 30 days after grant; a card is required to recharge afterward."
    best_for: "Multimodal (LLM + vision) models on a $5 credit"
    modalities: ["text", "vision", "embeddings", "image"]
    models_free: null
    expires: "30 days"
    docs_url: "https://docs.clarifai.com/control/account-billing/"
    phone_required: true
    card_required: false
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://api.clarifai.com/v2/ext/openai/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "arli-ai"
    name: "Arli AI"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Free plan ($0): access to all text LLMs (Gemma, Qwen, etc.), capped at ~5 requests per 2-day window, 12K context, 1 request at a time"
    rate_limits: "1 request at a time; ~5 requests per 2 days across all models; max 12K context; delayed responses"
    notes: "Free tier is for testing only — very restrictive. Provider advertises zero-log / no data retention. Card requirement for the free tier is not stated on the pricing page."
    best_for: "A permanently-free (heavily rate-limited) test tier"
    modalities: ["text"]
    models_free: null
    expires: null
    docs_url: "https://www.arliai.com/pricing"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://api.arliai.com/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "ollama-cloud"
    name: "Ollama Cloud"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "$0 Free plan: access to cloud-hosted open models (Qwen, GPT-OSS, DeepSeek, etc.) via API"
    rate_limits: "Session limits reset every 5 hours and weekly limits every 7 days; 1 concurrent cloud model on the free plan (exact token caps not published)"
    notes: "First-party — Ollama hosts the cloud models. Requires an ollama.com account + API key (`ollama signin`); the free plan is for light usage, Pro ($20/mo) raises limits. No card required."
    best_for: "Cloud-hosted open models with the Ollama workflow, no card"
    modalities: ["text", "vision"]
    models_free: ["deepseek-v4-flash", "deepseek-v4-pro", "gemma4:31b", "glm-5.1", "glm-5.2", "gpt-oss:120b", "gpt-oss:20b", "kimi-k2.5"]
    expires: null
    docs_url: "https://docs.ollama.com/cloud"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: true
    openai_base_url: "https://ollama.com/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "ai-horde"
    name: "AI Horde"
    category: "ongoing"
    free_type: "perpetual"
    free_tier: "Free crowdsourced text & image generation; anonymous API key '0000000000' (no registration), or register to earn kudos for priority"
    rate_limits: "Queue-based priority via kudos (no fixed quota); anonymous requests get lowest priority under load"
    notes: "Community-powered volunteer network — model availability and speed vary with worker supply, so it is not a fixed-SLA service. No card, no phone. Kudos never expire and cannot be sold."
    best_for: "Anonymous, no-signup free generation (variable speed)"
    modalities: ["text", "image"]
    models_free: null
    expires: null
    docs_url: "https://aihorde.net/"
    phone_required: false
    card_required: false
    commercial_ok: null
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "modelscope"
    name: "ModelScope (API-Inference)"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "~2,000 free API calls/day across open-weight models (Qwen3, DeepSeek, GLM, Llama, etc.) via API-Inference"
    rate_limits: "~2,000 calls/day; concurrency/QPS caps applied and dynamically adjusted"
    notes: "Alibaba's model hub — a different product from Alibaba Model Studio. Requires a ModelScope account bound to an Alibaba Cloud account with real-name (ID) verification — a practical barrier for non-China users. Explicitly non-commercial (\"for developers to experience\"). No card."
    best_for: "Free daily calls to many open models (real-name verification required)"
    modalities: ["text", "vision"]
    models_free: ["LLM-Research/Llama-4-Maverick-17B-128E-Instruct", "MedAIBase/AntAngelMed", "MiniMax/MiniMax-M1-80k", "MusePublic/Qwen-Image-Edit", "OpenGVLab/InternVL3_5-241B-A28B", "PaddlePaddle/ERNIE-4.5-0.3B-PT", "Qwen/Qwen-Image-Edit", "Shanghai_AI_Laboratory/Intern-S1"]
    expires: null
    docs_url: "https://www.modelscope.cn/docs/model-service/API-Inference/intro"
    phone_required: null
    card_required: false
    commercial_ok: false
    openai_compatible: true
    openai_base_url: "https://api-inference.modelscope.cn/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "pollinations"
    name: "Pollinations.ai"
    category: "ongoing"
    free_type: "perpetual"
    free_tier: "Free hosted image models (Flux, Turbo, Stable Diffusion) via a simple GET URL; also text and audio. No signup required to start"
    rate_limits: "Anonymous ~1 request / 15s; free registration (Seed tier) ~1 request / 5s"
    notes: "Anonymous free images may carry a watermark (since 2025); free registration removes it via the nologo parameter. No card, no phone. Commercial use is not explicitly guaranteed in the docs."
    best_for: "No-signup free image generation (Flux/SD)"
    modalities: ["image", "text", "audio"]
    models_free: ["openai-fast"]
    expires: null
    docs_url: "https://github.com/pollinations/pollinations/blob/master/APIDOCS.md"
    phone_required: false
    card_required: false
    commercial_ok: null
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "runware"
    name: "Runware"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$2 in signup credits across first-party image models (FLUX.1/FLUX.2, Stable Diffusion 3, SDXL) on the Sonic Inference Engine — hundreds to thousands of generations"
    rate_limits: "Not publicly specified; per-account concurrency applies"
    notes: "The $2 requires signup with a business email (personal/free-mail domains may be rejected); one-time, non-renewing. No watermark, no card, commercial use allowed. The OpenAI-compatible endpoint is chat-only, not for images."
    best_for: "Fast image models with a $2 no-card credit"
    modalities: ["image"]
    models_free: null
    expires: null
    docs_url: "https://runware.ai/pricing"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "pinecone-inference"
    name: "Pinecone Inference"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Starter (free) plan: 5M tokens/mo for embedding models (llama-text-embed-v2, multilingual-e5-large) and 500 requests/mo for the bge-reranker-v2-m3 rerank model"
    rate_limits: "5M embedding tokens/mo; 500 rerank requests/mo on Starter"
    notes: "Free rerank limited to bge-reranker-v2-m3; overages are pay-as-you-go. Not OpenAI-compatible. No card required."
    best_for: "Free embeddings + rerank for RAG (5M tokens/mo)"
    modalities: ["embeddings", "rerank"]
    models_free: null
    expires: null
    docs_url: "https://www.pinecone.io/pricing/"
    phone_required: null
    card_required: false
    commercial_ok: null
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "twelve-labs"
    name: "Twelve Labs (Marengo Embed)"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Free plan: the Marengo Embed API for all input types (video, audio, image, text) at no cost, plus ~600 min indexing"
    rate_limits: "Embed video/audio: 3,000 RPD, 25 RPM; embed text/image: 3,000 RPD, 600 RPM"
    notes: "No credit card for the Free plan, but indexed data expires after 90 days unless upgraded. Marengo produces multimodal embeddings. Not OpenAI-compatible."
    best_for: "Free multimodal (video/audio/image/text) embeddings"
    modalities: ["embeddings", "vision", "audio", "text"]
    models_free: null
    expires: null
    docs_url: "https://www.twelvelabs.io/pricing"
    phone_required: null
    card_required: false
    commercial_ok: null
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "ocr-space"
    name: "OCR.space"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "25,000 conversions/month (Engine 1 & 2) plus 2,500 Engine 3 conversions/month; max 1 MB file, PDFs up to 3 pages"
    rate_limits: "500 requests per day per IP address"
    notes: "Free searchable-PDF output carries a watermark (raw text extraction is unrestricted); the free key needs only an email, no card. Commercial use permitted."
    best_for: "Classic free OCR (25k conversions/mo, no card)"
    modalities: ["ocr", "text"]
    models_free: null
    expires: null
    docs_url: "https://ocr.space/OCRAPI"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "llamaparse"
    name: "LlamaParse (LlamaCloud)"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "Free plan: 10,000 credits/month (~10,000 pages in balanced parse mode at 1 credit/page)"
    rate_limits: "5 concurrent jobs; 1 project; 5 indexes on the free plan"
    notes: "Credit-based (1,000 credits = $1.25); premium parse modes consume more credits per page. No card required. Document parsing for RAG (LlamaIndex)."
    best_for: "Free document parsing for RAG (~10k pages/mo)"
    modalities: ["ocr", "text"]
    models_free: null
    expires: null
    docs_url: "https://www.llamaindex.ai/pricing"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "nanonets"
    name: "Nanonets"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "$50 in free credits on signup (one-time) across data-extraction / OCR workflows"
    rate_limits: "Up to 3 users on the free credit"
    notes: "One-time signup credit, not renewing; no credit card required to start. Paid plans start at $100/month afterwards."
    best_for: "Document extraction on a $50 no-card credit"
    modalities: ["ocr", "text"]
    models_free: null
    expires: null
    docs_url: "https://nanonets.com/pricing"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "moondream"
    name: "Moondream Cloud"
    category: "ongoing"
    free_type: "recurring-credit"
    free_tier: "$5/month usage credits in every workspace (Free plan) for the Moondream vision model — caption, query (VQA), detect, point"
    rate_limits: "Bounded by the $5/month credit"
    notes: "Recurring $5/month credit; card requirement not stated on the pricing page; commercial terms not specified. OpenAI-compatible endpoint."
    best_for: "Tiny vision model, OpenAI-compatible, monthly free credit"
    modalities: ["vision"]
    models_free: null
    expires: null
    docs_url: "https://moondream.ai/pricing"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://api.moondream.ai/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "speechmatics"
    name: "Speechmatics"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "3,000 minutes (50 hours)/month speech-to-text + 1,000,000 characters (~20 hrs)/month text-to-speech"
    rate_limits: "2 concurrent real-time sessions on the free plan"
    notes: "No credit card required to start; add a card only when you exceed the free limit. Recurring monthly allowance covering both STT and TTS. Commercial-use permission not explicitly stated on the pricing page."
    best_for: "Best free STT tier (50 hrs/mo, no card)"
    modalities: ["audio"]
    models_free: null
    expires: null
    docs_url: "https://www.speechmatics.com/pricing"
    phone_required: null
    card_required: false
    commercial_ok: null
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "speechify"
    name: "Speechify API"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "50,000 characters/month TTS (hard cap) + 60 min/month voice agents"
    rate_limits: "3 concurrent calls; hard cap pauses at the limit (no overages)"
    notes: "Commercial use is allowed on the free tier. No credit card required. Hard monthly cap that pauses at the limit."
    best_for: "Free commercial TTS (50k chars/mo)"
    modalities: ["audio"]
    models_free: null
    expires: null
    docs_url: "https://speechify.ai/pricing"
    phone_required: false
    card_required: false
    commercial_ok: true
    openai_compatible: null
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "hume-ai"
    name: "Hume AI (Octave TTS)"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "10,000 characters/month TTS (~10 minutes) on the Free plan"
    rate_limits: "15 requests per minute"
    notes: "The free plan includes a commercial license; overage billed at $0.15/1,000 chars. No card stated as required to start. Not OpenAI-compatible."
    best_for: "Expressive TTS with a commercial free tier"
    modalities: ["audio"]
    models_free: null
    expires: null
    docs_url: "https://www.hume.ai/pricing"
    phone_required: null
    card_required: false
    commercial_ok: true
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "unreal-speech"
    name: "Unreal Speech"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "250,000 characters/month TTS (~6 hours of audio)"
    rate_limits: "Tiered endpoints for different text lengths; specific caps not documented"
    notes: "Commercial use allowed, but free-plan users must attribute Unreal Speech with a link when publishing audio. First-party REST endpoints. Card requirement not stated."
    best_for: "Largest free TTS (250k chars/mo, attribution)"
    modalities: ["audio"]
    models_free: null
    expires: null
    docs_url: "https://unrealspeech.com/pricing"
    phone_required: null
    card_required: null
    commercial_ok: true
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "elevenlabs"
    name: "ElevenLabs"
    category: "ongoing"
    free_type: "renewing-quota"
    free_tier: "10,000 credits/month shared across Text-to-Speech, Speech-to-Text and more (~10 min TTS/month)"
    rate_limits: "Concurrency tied to the Free plan (not numerically published)"
    notes: "The free tier is NON-COMMERCIAL only per the Terms of Use (a commercial license begins on paid Starter, $6/mo), and historically required attribution. API access is available on the free plan. No credit card to sign up."
    best_for: "Best-known TTS voices (free tier is non-commercial)"
    modalities: ["audio"]
    models_free: null
    expires: null
    docs_url: "https://elevenlabs.io/pricing"
    phone_required: false
    card_required: false
    commercial_ok: false
    openai_compatible: false
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "sarvam-ai"
    name: "Sarvam AI"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "₹100 in free credits on signup, usable across all APIs including the Sarvam-M chat/LLM API and speech (STT/TTS)"
    rate_limits: "Not published; bounded by the ₹100 credit"
    notes: "One-time signup credit shared across all APIs; card/phone requirement not stated on the docs. India-focused provider (pricing in INR), strong Indic-language models."
    best_for: "Indic-language chat + speech via one OpenAI-compatible key"
    modalities: ["text", "audio"]
    models_free: null
    expires: null
    docs_url: "https://docs.sarvam.ai/api/getting-started/pricing"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://api.sarvam.ai/v1"
    verified: true
    last_verified: "2026-07-30"
  - slug: "gladia"
    name: "Gladia"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "€50 in free credits on signup for speech-to-text (~80+ hrs pre-recorded or 60+ hrs real-time at current rates)"
    rate_limits: "Not published; bounded by the €50 credit"
    notes: "One-time grant with no monthly reset; prepaid model — top up once the credit is consumed. Card requirement not explicitly stated on the pricing page."
    best_for: "High-accuracy async + real-time transcription to trial"
    modalities: ["audio"]
    models_free: null
    expires: null
    docs_url: "https://www.gladia.io/pricing"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: null
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "rime"
    name: "Rime"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "3,000 free TTS minutes for every new account (Starter plan)"
    rate_limits: "Starter: 20 concurrent TTS generations"
    notes: "One-time allotment on signup; card requirement and commercial-use terms for the free minutes are not stated on the pricing page."
    best_for: "Low-latency conversational TTS to prototype"
    modalities: ["audio"]
    models_free: null
    expires: null
    docs_url: "https://rime.ai/pricing"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: null
    openai_base_url: null
    verified: true
    last_verified: "2026-07-30"
  - slug: "tencent-hunyuan"
    name: "Tencent Hunyuan"
    category: "trial"
    free_type: "trial-credit"
    free_tier: "1,000,000 free tokens for Hunyuan text LLMs (hunyuan-a13b, turbos, translation & vision models), plus a separate 1,000,000-token allotment for hunyuan-embedding"
    rate_limits: "Not published; bounded by the token package"
    notes: "Free resource package valid 1 year from activation; unused tokens expire. Tencent Cloud generally requires mainland-China real-name ID verification to activate — a practical barrier for non-China users. Commercial-use terms not stated on the free-quota page."
    best_for: "Chinese-language LLM workloads via an OpenAI-compatible endpoint"
    modalities: ["text", "vision", "embeddings"]
    models_free: null
    expires: "1 year"
    docs_url: "https://cloud.tencent.com/document/product/1729/97731"
    phone_required: null
    card_required: null
    commercial_ok: null
    openai_compatible: true
    openai_base_url: "https://api.hunyuan.cloud.tencent.com/v1"
    verified: true
    last_verified: "2026-07-30"