2026-W41 (2026-10-05 to 2026-10-11): 66 field changes across 38 providers
| Date | Provider | Field | From | To |
|---|---|---|---|---|
| 2026-10-08 | Alibaba Cloud (Model Studio) | free tier | 1,000,000 tokens (example figure, varies by model), international/Singapore region only | Typically 1,000,000 tokens per model for new users, Singapore region (International deployment scope) only |
| 2026-10-08 | Alibaba Cloud (Model Studio) | rate limits | Qwen open & proprietary models | Per-model, account-level limits that apply equally to free-quota and paid calls (International): e.g. qwen-plus 600 RPM / 1,000,000 TPM; qwen-flash and qwen-turbo 600 RPM / 5,000,000 TPM; qwen3.6-plus and qwen3.7-plus 15,000 RPM / 5,000,000 TPM. HTTP 429 when a limit is exceeded; HTTP 403 when the free quota is exhausted |
| 2026-10-08 | Alibaba Cloud (Model Studio) | the catch | Excludes batch processing, context caching, fine-tuning, and dedicated deployment | Covers real-time inference only; excludes batch invocation, fine-tuning, model deployment, custom models, PAI-DSW and OSS fees. Account information must be completed before activation. One quota per account (shared with RAM users); re-registering does not grant a new one. |
| 2026-10-08 | Arli AI | 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 | Free plan ($0): text LLMs for testing, max 5 requests every 2 days per model, 12K context, 1 request at a time, delayed responses; no image generation |
| 2026-10-08 | Arli AI | rate limits | 1 request at a time; ~5 requests per 2 days across all models; max 12K context; delayed responses | 5 requests every 2 days per model; 1 request at a time; max 12K context tokens |
| 2026-10-08 | Baseten | rate limits | Model APIs are priced per token; dedicated deployments are priced by compute time (per minute) | Model APIs default (models with combined token limits): Basic (unverified) 15 RPM / 100,000 TPM; Basic (verified) 120 RPM / 500,000 TPM; HTTP 429 when exceeded |
| 2026-10-08 | Baseten | the catch | Basic is $0/month, pay as you go. Current pricing confirms new-account credits but does not publish an amount or expiration date | Basic is $0/month, pay as you go. Current pricing confirms new-account credits but does not publish an amount or expiration date. Model APIs are priced per token; dedicated deployments are priced by compute time. |
| 2026-10-08 | Camb.ai | free tier | 2,000 credits/month covering ~25K characters of MARS TTS, 125 min of STT, plus limited watermarked dubbing and translation (incl. 5 OCR pages) | Free plan: 5,000 credits one-time (no monthly renewal) across TTS, dubbing, speech and translation tools |
| 2026-10-08 | Camb.ai | rate limits | 500 chars/generation TTS, 15 min/generation STT; 2,000 credits/month | Not published by the provider; bounded by the one-time 5,000-credit grant |
| 2026-10-08 | Camb.ai | the catch | Uses its own MARS8 voice models (not OpenAI-compatible). Dubbing output on the free tier is watermarked. Card and commercial terms not stated on the pricing page. | Uses its own MARS voice models (not OpenAI-compatible). Free credits are a one-time grant, not monthly. Per-feature limits (characters per generation, watermarking) are not readable on the current pricing page. Card and commercial terms not stated on the pricing page. |
| 2026-10-08 | Camb.ai | free type | renewing-quota | trial-credit |
| 2026-10-08 | Cerebras | rate limits | Published Free Trial per-model limits: 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 | Published Free Trial limits for gpt-oss-120b and qwen-3.8-27b: 5 RPM / 30,000 uncached TPM / 90,000 total TPM / 1,000,000 TPH / 1,000,000 TPD; limits vary by model |
| 2026-10-08 | Clarifai | the catch | 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. Checked ToS (clarifai.com/company/terms, effective 2025-10-01) and billing docs (docs.clarifai.com/control/account-billing/) for commercial/production-use language. No clause restricts the $5 trial credit / Pay-As-You-Go tier to evaluation-only. The 'evaluation purposes only, not for production' language in §7.3 applies specifically to Beta Releases, not this plan. No explicit statement either way, so left null per contribution guidelines. | Could not be re-verified on 2026-10-08: docs.clarifai.com no longer resolves and www.clarifai.com does not respond. Nebius has announced that Clarifai's core team joined Nebius and that it licensed Clarifai's inference technology. Treat this entry as likely discontinued. Previously recorded: SMS phone verification to claim a one-time $5 credit that expired 30 days after grant. |
| 2026-10-08 | Cloudflare Workers AI | rate limits | 30+ models: LLMs (Llama, Mistral, DeepSeek, Qwen...), embeddings, image, audio | 10,000 Neurons/day (free allocation). Per-task request limits: text generation 300 requests/min (models that require Workers Paid: 20 requests/min per model); text embeddings 3,000/min; speech recognition, text-to-image, translation, image-to-text 720/min |
| 2026-10-08 | Contextual AI | rate limits | Bounded by the $25 credit balance | Not published by the provider (Rerank requests capped at 400,000 tokens each) |
| 2026-10-08 | Datalab (Marker / Surya) | rate limits | 10 requests/min on the free tier; per-page pricing (see datalab.to/pricing) | 25 requests/min on the free tier; per-page pricing (see datalab.to/pricing) |
| 2026-10-08 | Datalab (Marker / Surya) | the catch | Landing page still advertises a $5 signup credit, but the billing page describes the current free tier as a recurring monthly allowance ($20/mo work email, $10/mo personal, no card, 10 req/min) “designed to let you run a complete proof of concept before committing to a paid plan” — no explicit statement on commercial use of the hosted API. The self-hosted OSS weights carry a separate restriction (research/personal/startups under $2M ARR/funding). | Landing page still advertises a $5 signup credit, but the billing page describes the current free tier as a recurring monthly allowance ($20/mo work email, $10/mo personal, no card, 25 req/min) “designed to let you run a complete proof of concept before committing to a paid plan” — no explicit statement on commercial use of the hosted API. The self-hosted OSS weights carry a separate restriction (research/personal/startups under $2M ARR/funding). Signup does not require a phone number; checked via Google signup flow on 2026-10-02. |
| 2026-10-08 | Datalab (Marker / Surya) | phone requirement | unknown | no |
| 2026-10-08 | ElevenLabs | rate limits | Concurrency tied to the Free plan (not numerically published) | 2 concurrent requests on the Free plan |
| 2026-10-08 | ElevenLabs | the catch | 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. | The free tier is NON-COMMERCIAL only per the Terms of Use (commercial license starts on paid Starter, $6/mo); non-commercial use requires a personal email address. Free-plan credits do not roll over. API access is available on the free plan. No credit card to sign up. |
| 2026-10-08 | Fireworks AI | rate limits | Various open-weight models | 10 requests/min with no payment method or no credits; 6,000 RPM account-wide maximum once a payment method and active credits are on file |
| 2026-10-08 | Fish Audio | free tier | 8,000 credits/month (~7 min of generation, up to 500 characters per generation); TTS, STT and voice cloning | App Free plan: 8,000 credits/month (~7 min, up to 500 characters per generation). API: the s2.1-pro-free TTS model is $0 through 2026-11-30 under fair-use limits (pay-as-you-go API, no subscription) |
| 2026-10-08 | Fish Audio | rate limits | 500 characters per generation; 8,000 credits/month | API: 5 concurrent requests (Starter tier, <$100 paid); s2.1-pro-free under unpublished fair-use limits. App Free plan: 500 characters per generation, 8,000 credits/month |
| 2026-10-08 | Fish Audio | the catch | Free plan is personal, non-commercial only (commercial use requires a Premium subscription). No credit card required to sign up. | Free app plan is personal, non-commercial only (commercial use requires Premium). The $0 API model s2.1-pro-free is pitched for testing, prototyping and smaller businesses but has no TTFA/DPA guarantees. No credit card required for the Free plan. |
| 2026-10-08 | Gladia | rate limits | Not published; bounded by the €50 credit | 30 real-time and 25 async concurrent requests (Starter pay-as-you-go plan that carries the €50 credit) |
| 2026-10-08 | Google Gemini API (AI Studio) | rate limits | Varies by model: 5-30 RPM and 15-1,000 RPD (e.g. 2.5 Pro: 5 RPM/100 RPD; 2.5 Flash: 10/250; 2.5 Flash-Lite: 15/1,000; embeddings: 100 RPD; TTS: 15 RPD) | Per-model; Google no longer publishes the free-tier numbers in its public docs — they are shown only on the AI Studio rate-limit page after sign-in |
| 2026-10-08 | Groq | free tier | Open-weight models (Llama, Qwen, GPT-OSS) plus Whisper, no credit card required | Open-weight models (GPT-OSS, Qwen) plus Whisper, no credit card required |
| 2026-10-08 | Groq | 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; qwen/qwen3.6-27b: 30 RPM/1K RPD/8K TPM/200K TPD; similar for GPT-OSS and Whisper models | Free plan examples: openai/gpt-oss-120b, openai/gpt-oss-20b and qwen/qwen3.8-27b: 30 RPM/1K RPD/8K TPM/200K TPD; Whisper models: 20 RPM/2K RPD/7.2K audio seconds/hour and 28.8K/day; limits vary by model |
| 2026-10-08 | HuggingFace | 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) | Free CPU Basic + ZeroGPU for Spaces; Inference Providers has no included credit on the Free plan (credits must be purchased) — $2.00/mo is included only on PRO/Team/Enterprise |
| 2026-10-08 | Hume AI (Octave TTS) | free tier | 10,000 characters/month TTS (~10 minutes) on the Free plan | Free tier for Octave TTS and EVI; new accounts start with $20 in credits |
| 2026-10-08 | Hume AI (Octave TTS) | rate limits | 15 requests per minute | Rate set by subscription tier, numbers not published; max 5,000 characters per utterance and 5 generations per request |
| 2026-10-08 | Hume AI (Octave TTS) | the catch | 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. | Free and Starter tiers are non-commercial only (commercial use starts on Creator). The Free plan cannot buy overage, so going past it means upgrading. Not OpenAI-compatible. The former plan quota (10,000 characters/month) is no longer on a live official page: hume.ai/pricing redirected to the homepage on 2026-10-08. |
| 2026-10-08 | Hume AI (Octave TTS) | commercial-use terms | yes | no |
| 2026-10-08 | Jina AI | rate limits | Free key: 100 RPM / 100k TPM for embeddings & reranker (2 concurrent); keyless Reader 20 RPM | Free key: 100 RPM / 100k TPM for embeddings & reranker; Reader 20 RPM keyless, 500 RPM with a free key |
| 2026-10-08 | LlamaParse (LlamaCloud) | free tier | Free plan: 10,000 credits/month (~10,000 pages in balanced parse mode at 1 credit/page) | Free plan: 10,000 credits/month (up to ~10,000 pages at the cheapest parse tier, as low as 1 credit/page) |
| 2026-10-08 | Mistral (La Plateforme) | free tier | "Restrictive" free tier explicitly for "try and explore" — official docs say to upgrade for "actual projects and production use" | "Free mode" (default for new accounts): API keys with included monthly usage and the lowest limits, "intended for evaluation and prototyping" |
| 2026-10-08 | Mistral (La Plateforme) | rate limits | Not published publicly; exact caps only visible in-console after login (admin.mistral.ai) | Not published publicly; per-model requests/second, tokens/minute and tokens/month caps are shown only in-console (Admin Panel > API > Limits) |
| 2026-10-08 | Mistral (La Plateforme) | the catch | Phone verification required to activate; no credit card required. Free tier is opt-in for data training. | No credit card required. In Free mode Mistral may use your inputs and outputs to train its models unless you opt out in the Admin panel. Phone verification at signup was recorded in an earlier check; the current docs do not mention it. |
| 2026-10-08 | Modal | the catch | 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 The full $30/month credit requires adding a payment method (without one the free credit is $5/month). | Recurring monthly credit, not a one-time trial. Modal is serverless compute you deploy models on, not a hosted model API. A payment method on file is required to use Modal at all. |
| 2026-10-08 | ModelScope (API-Inference) | free tier | ~2,000 free API calls/day across open-weight models (Qwen3, DeepSeek, GLM, Llama, etc.) via API-Inference | Free API-Inference calls paid with daily 'Magicubes': 200/day for signing in + 50/day after linking an Alibaba Cloud account (do not roll over); calls cost ~0.5 / 1 / 2 Magicubes for lightweight / standard / flagship models |
| 2026-10-08 | ModelScope (API-Inference) | rate limits | ~2,000 calls/day; concurrency/QPS caps applied and dynamically adjusted | Bounded by the daily Magicubes: ~250/day from signing in and linking an Alibaba Cloud account, plus any earned by other actions (~125-500 calls depending on model tier); concurrency dynamically limited, single concurrency guaranteed |
| 2026-10-08 | Moondream Cloud | rate limits | Bounded by the $5/month credit | 2 requests/sec on the free tier (10 req/sec with ≥$10 account balance); usage bounded by the $5/month credit |
| 2026-10-08 | Moondream Cloud | the catch | Recurring $5/month credit, no credit card required (stated on the pricing page/blog). Commercial terms not specified. OpenAI-compatible endpoint. | Recurring $5/month credit, no credit card required. Per the Terms (§5.2), data is not used to train Moondream's generally available models. Commercial terms for the hosted API not specified. OpenAI-compatible endpoint. |
| 2026-10-08 | NVIDIA NIM | rate limits | Some models have reduced context windows on the free trial | Up to 40 requests/min and 10,000 requests/day; limits may vary by model and traffic from other users may cause throttling |
| 2026-10-08 | Nanonets | rate limits | Up to 3 users on the free credit | Not published by the provider |
| 2026-10-08 | Nebius AI Studio | rate limits | Various open-weight models | Default per-account RPM/TPM caps are shown in the Token Factory console and in response headers (not stated numerically in the docs; the docs' 60 RPM / 400,000 TPM baseline is labeled an illustrative example). Limits auto-scale: +20% per 15-minute window at >=80% usage, up to 20x the base |
| 2026-10-08 | Novita AI | free tier | $100 Sandbox credits, valid for 90 days | $100 promotional credits valid for 90 days for eligible Novita Agent Sandbox usage (CPU, RAM, storage), granted after an account-setup survey; Novita does not say they apply to Model API calls; the pricing page also lists a few LLMs as Free (e.g. Ling 3.1 Flash, Apodex 1.1 Mini) |
| 2026-10-08 | Novita AI | rate limits | Various open-weight models | Per model, by account tier. New/low-spend accounts are Tier T1 (monthly top-ups <= $50): typically 30 RPM and 50M TPM per model (a few models 50 RPM; some 2M-5M TPM). The Free-priced LLMs (Ling 3.1 Flash, Apodex 1.1 Mini) are 30 RPM / 50M TPM at T1 |
| 2026-10-08 | Novita AI | the catch | Official signup advertises $100 Sandbox credits valid for 90 days; no credit card required. Novita Terms of Service state that the Site and Marketplace Offerings may not be exploited for any commercial purpose without express prior written permission. | Signup advertises $100 Sandbox credits valid for 90 days; Novita's sandbox pricing doc describes them as credits for "eligible Novita Sandbox usage" and does not say they apply to Model API calls. No credit card required. Novita Terms of Service state that the Site and Marketplace Offerings may not be exploited for any commercial purpose without express prior written permission. |
| 2026-10-08 | Nutrient (Data Extraction API) | rate limits | 5,000 credits/month; per-page cost varies by parse mode (1-18 credits) | 5,000 credits/month; Parse costs 1-18 credits/page by mode (Extract 7-24) |
| 2026-10-08 | OCR.space | 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 | 25,000 conversions/month (Engine 1 & 2) plus 1,000 Engine 3 conversions/month; max 1 MB file, PDFs up to 3 pages |
| 2026-10-08 | OVHcloud AI Endpoints | free tier | Two Qwen3Guard models (Gen-8B and Gen-0.6B) are currently listed as Free in the catalog; access is available anonymously or with an API key tied to a Public Cloud project | Seven models are currently listed as Free: two Qwen3Guard moderation models, Stable Diffusion XL and four NVIDIA Riva TTS voices; access is available anonymously or with an API key tied to a Public Cloud project |
| 2026-10-08 | Ollama Cloud | free tier | $0 Free plan: access to cloud-hosted open models (Qwen, GPT-OSS, DeepSeek, etc.) via API | $0 Free plan: starter amount of cloud usage credits, limited to a smaller set of starter models; buying credits unlocks all cloud models |
| 2026-10-08 | Ollama Cloud | 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) | 1 concurrent request on the free plan; included usage resets monthly from signup date (dollar amount of starter credits not published) |
| 2026-10-08 | Ollama Cloud | the catch | 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. | First-party — Ollama hosts the cloud models. Requires an ollama.com account + API key. The old 5-hour session / weekly limits are gone: usage is now credit-based with a monthly reset; Pro ($20/mo) includes $60 of credits. Prompts/responses are not logged or trained on. Whether a card is required is not stated on the current pricing page. |
| 2026-10-08 | Ollama Cloud | card requirement | no | unknown |
| 2026-10-08 | OpenRouter | free tier | A rotating set of models with a :free suffix (~14 today; count fluctuates), single API across many providers | A rotating set of models with a :free suffix (16 on 2026-10-08; count fluctuates), single API across many providers |
| 2026-10-08 | SambaNova Cloud | the catch | 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). | 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). As of 2026-10-08 SambaNova's own pages disagree: the rate-limits doc still describes this no-card Free Tier, while the plans page says to add a payment method and buy credits before the first request. Needs a hands-on signup check. |
| 2026-10-08 | Scaleway Generative APIs | rate limits | Gemma, Llama, Mistral, Qwen | With a validated payment method: 300 RPM / 200k TPM per model; 600 RPM and higher TPM once identity is verified |
| 2026-10-08 | Scaleway Generative APIs | the catch | European provider (France). Free allowance is a one-time token bucket, not time-limited. The 1M free tokens need no card; adding a card + passing KYC unlocks the official rate limits. | European provider (France). Free allowance is a one-time token bucket, not time-limited. Official rate limits apply once a valid payment method is registered; identity verification raises them. |
| 2026-10-08 | SiliconFlow | 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 | China platform (siliconflow.cn): several models permanently free at ¥0 (e.g. Qwen/Qwen2.5-7B-Instruct, tencent/Hunyuan-MT-7B, BAAI embeddings and rerankers). The international platform (siliconflow.com) lists no $0 LLMs and gives $1 in free credits instead |
| 2026-10-08 | SiliconFlow | the catch | 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 | Free models live on the China platform and need real-name authentication to use all of them; accepted documents are a mainland ID card, HK/Macao or Taiwan travel permits, HK/Macao/Taiwan residence permits or a Chinese permanent-residence card for foreigners. Signup is by phone number; some virtual-carrier number ranges are blocked. |
| 2026-10-08 | Vercel AI Gateway | 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 | No numeric free-tier limit published: the free tier has a lower per-model limit than paid (HTTP 429 when exceeded); Vercel documents behavior, not numbers |
| 2026-10-08 | Vercel AI Gateway | the catch | The monthly $5 credit is stated in Vercel's own docs. Once you purchase credits, your account moves to the paid tier and the monthly free credit no longer applies. BYOK is not available on the free tier. | The monthly $5 credit is stated in Vercel's own docs. Once you purchase credits, your account moves to the paid tier and the monthly free credit no longer applies. BYOK is not available on the free tier. It routes requests to many providers rather than hosting models itself. |
| 2026-10-08 | Voyage AI | rate limits | Standard per-model RPM/TPM limits apply; the free-token allotment is the practical ceiling | No numeric limit published for accounts without a payment method. With a payment method (Tier 1, free tokens still apply), per model: voyage-4 / voyage-code-4 8M TPM, 2,000 RPM; voyage-4-large / voyage-context-4 3M TPM, 2,000 RPM; voyage-4-lite 16M TPM, 2,000 RPM; voyage-multimodal-3.5 2M TPM, 2,000 RPM; rerank-2.5 2M TPM, 2,000 RPM; rerank-2.5-lite 4M TPM, 2,000 RPM. HTTP 429 on exceed |
| 2026-10-08 | Z.ai (Zhipu AI / GLM) | the catch | Terms of Use prohibit using the service to "develop, train, or improve" competing algorithms or models — otherwise general use, including commercial, isn't restricted | Terms of Use prohibit using Z.ai to "develop, train, or enhance any algorithms, models, or technologies that directly or indirectly compete with us" — otherwise general use, including commercial, isn't restricted |
2026-W33 (2026-08-10 to 2026-08-16): 59 field changes across 32 providers
| Date | Provider | Field | From | To |
|---|---|---|---|---|
| 2026-08-14 | AI21 Labs | OpenAI compatibility | unknown | yes |
| 2026-08-14 | Cartesia | card requirement | unknown | no |
| 2026-08-14 | Contextual AI | card requirement | unknown | no |
| 2026-08-14 | Gladia | card requirement | unknown | no |
| 2026-08-14 | Gladia | OpenAI compatibility | unknown | no |
| 2026-08-14 | Jina AI | 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 | 10M free tokens (one-time) across all models — embeddings, rerankers, classifier; plus a keyless Reader (r.jina.ai) for basic use |
| 2026-08-14 | Mistral (La Plateforme) | the catch | Phone verification required to activate; free tier is opt-in for data training | Phone verification required to activate; no credit card required. Free tier is opt-in for data training. |
| 2026-08-14 | Mistral (La Plateforme) | card requirement | unknown | no |
| 2026-08-14 | Mistral (La Plateforme) | OpenAI compatibility | unknown | yes |
| 2026-08-14 | Modal | the catch | 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 | 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 The full $30/month credit requires adding a payment method (without one the free credit is $5/month). |
| 2026-08-14 | Modal | card requirement | unknown | yes |
| 2026-08-14 | Moondream Cloud | the catch | Recurring $5/month credit; card requirement not stated on the pricing page; commercial terms not specified. OpenAI-compatible endpoint. | Recurring $5/month credit, no credit card required (stated on the pricing page/blog). Commercial terms not specified. OpenAI-compatible endpoint. |
| 2026-08-14 | Moondream Cloud | card requirement | unknown | no |
| 2026-08-14 | NVIDIA NIM | card requirement | unknown | no |
| 2026-08-14 | Nanonets | the catch | One-time signup credit, not renewing; no credit card required to start. Paid plans start at $100/month afterwards. | One-time signup credit, not renewing (credits never expire); no credit card required to start. Paid plans start at $100/month afterwards. |
| 2026-08-14 | Poolside | free tier | Laguna XS 2.1 (33B) and Laguna S 2.1 (118B) are free in Preview via a self-serve developer API key | Laguna M.1 (225B) and Laguna XS.2 (33B, open-weights) are free for a limited time via a self-serve developer API key (also on OpenRouter) |
| 2026-08-14 | Poolside | the catch | Coding-focused models. Free access is Preview-stage and may change at general availability. Self-serve: create a free API key at platform.poolside.ai. OpenRouter is offered only as an alternative route. | Coding-focused models. Poolside describes the free access as 'free for a limited time' (not perpetual) and it may change at general availability. Self-serve key at platform.poolside.ai; OpenRouter is an alternative route. |
| 2026-08-14 | Poolside | free type | perpetual | trial-credit |
| 2026-08-14 | Poolside | card requirement | unknown | no |
| 2026-08-14 | Retell AI | the catch | $10 signup credit with full platform access. A voice-agent builder (orchestration), not a raw model API. Card terms not stated on the pricing page. | $10 signup credit with full platform access. A voice-agent builder (orchestration), not a raw model API. Retell’s Stripe case study describes capturing a card at signup for automatic billing once the free credits are used (a third-party review claims otherwise — treat card as required). |
| 2026-08-14 | Retell AI | card requirement | unknown | yes |
| 2026-08-14 | Rev AI | the catch | One-time signup grant (does not renew). High-accuracy English ASR. Card and commercial terms not stated on the pricing page. | One-time signup grant (does not renew). High-accuracy English ASR. No credit card required (stated on the signup page). Commercial terms not stated. |
| 2026-08-14 | Rev AI | card requirement | unknown | no |
| 2026-08-14 | Rime | the catch | One-time allotment on signup; card requirement and commercial-use terms for the free minutes are not stated on the pricing page. | One-time allotment on signup; no credit card required (stated on the pricing page). The pricing table shows ~800 free minutes (~800k characters) while the page’s own FAQ and the docs still say 3,000 — an internal inconsistency. Commercial-use terms not stated. |
| 2026-08-14 | Rime | card requirement | unknown | no |
| 2026-08-14 | Rime | OpenAI compatibility | unknown | no |
| 2026-08-14 | Sarvam AI | card requirement | unknown | no |
| 2026-08-14 | Scaleway Generative APIs | the catch | European provider (France). Free allowance is a one-time token bucket, not time-limited | European provider (France). Free allowance is a one-time token bucket, not time-limited. The 1M free tokens need no card; adding a card + passing KYC unlocks the official rate limits. |
| 2026-08-14 | Scaleway Generative APIs | card requirement | unknown | no |
| 2026-08-14 | SiliconFlow | card requirement | unknown | no |
| 2026-08-14 | Smallest.ai (Waves) | card requirement | unknown | no |
| 2026-08-14 | Speechify API | OpenAI compatibility | unknown | no |
| 2026-08-14 | Speechmatics | free tier | 3,000 minutes (50 hours)/month speech-to-text + 1,000,000 characters (~20 hrs)/month text-to-speech | $100 one-time usage credit (no card) covering Speech-to-Text and Text-to-Speech |
| 2026-08-14 | Speechmatics | rate limits | 2 concurrent real-time sessions on the free plan | 2 concurrent real-time STT sessions; 3 voice-agent conversations; 1 batch job/sec (bounded by the $100 credit) |
| 2026-08-14 | Speechmatics | the catch | 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. | One-time $100 credit, no card required — replaced the previous 3,000 min/month + 1M chars recurring allowance on 2026-07-31. Add a card when you move to Pro. Commercial-use permission not explicitly stated. |
| 2026-08-14 | Speechmatics | free type | renewing-quota | trial-credit |
| 2026-08-14 | Tencent Hunyuan | the catch | 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. | 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. Hunyuan is gradually migrating to TokenHub (the legacy platform is no longer adding new models). Commercial-use terms not stated on the free-quota page. |
| 2026-08-14 | Tencent Hunyuan | card requirement | unknown | no |
| 2026-08-14 | Typhoon (SCB 10X) | rate limits | No published quotas (beta service) | typhoon-asr-realtime: 100 reqs/minute (documented on the ASR page); LLM/OCR models: no published quotas (beta service) |
| 2026-08-14 | Typhoon (SCB 10X) | the catch | By SCB 10X, the venture arm of Siam Commercial Bank, focused on Thai-language models. Beta, provided as-is with no formal support; usage data is collected to improve the model; SCB claims no rights in outputs. Sign up for an API key at opentyphoon.ai. | By SCB 10X, the venture arm of Siam Commercial Bank, focused on Thai-language models. The free catalog spans LLMs (typhoon-v2.5-30b-a3b-instruct), OCR (typhoon-ocr family) and realtime Thai ASR (typhoon-asr-realtime, typhoon-isan-asr-realtime) — the hosted API is OpenAI-compatible, including audio transcriptions. Beta, provided as-is with no formal support; usage data is collected to improve the model; SCB claims no rights in outputs. Sign up for a free API key at opentyphoon.ai. |
| 2026-08-14 | Unreal Speech | the catch | 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. | Commercial use allowed, but free-plan users must attribute Unreal Speech with a link when publishing audio. First-party REST endpoints. No credit card required. |
| 2026-08-14 | Unreal Speech | card requirement | unknown | no |
| 2026-08-14 | Upstage | free tier | $10 in free credit on signup (no card) — Solar LLM (chat + embeddings) plus Document Parse / OCR / information extraction | Solar Pro 4 is free for a limited time (promo); otherwise the API is paid prepaid (commitment tiers from $100/mo) — Solar LLM (chat + embeddings) plus Document Parse / OCR / information extraction; Studio agents include 10 free runs |
| 2026-08-14 | Upstage | rate limits | Document Parse billed $0.01/page (+$0.03 for extract), drawn from the $10 credit | Document Parse billed $0.01/page (+$0.03 for extract); Tier 1 rate limits apply on prepaid tiers |
| 2026-08-14 | Upstage | the catch | No credit card required to receive the $10 credit; Studio agents also include 10 free runs. A separate institutional grant (up to 1 year of free Solar + Document Parse) exists for eligible organizations only. Credit validity period not stated. | The former $10 signup credit no longer appears on the pricing page (now prepaid commitment tiers from $100/mo). No card needed for the limited-time free model or the 10 free Studio runs; a separate institutional grant (up to 1 year of free Solar + Document Parse) exists for eligible organizations only. |
| 2026-08-14 | Vercel AI Gateway | free tier | Free tier with a monthly free credit covering a subset of models at lower rate limits | Free tier: $5/month credit covering a subset of models (Free Tier eligible models) at lower rate limits |
| 2026-08-14 | Vercel AI Gateway | the catch | 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. | The monthly $5 credit is stated in Vercel's own docs. Once you purchase credits, your account moves to the paid tier and the monthly free credit no longer applies. BYOK is not available on the free tier. |
| 2026-08-14 | Voicegain | rate limits | Bounded by the $50 credit; pay-as-you-go afterward | Bounded by the $50 credit; pay-as-you-go afterward (4 concurrent requests or 4 hours of audio/hour) |
| 2026-08-14 | Voyage AI | free tier | 200M free tokens on current embedding models (voyage-4, voyage-4-lite, voyage-context-4, voyage-code-3) and on rerankers (rerank-2.5 family); voyage-multimodal-3.5 gets 200M text tokens + 150B pixels — a large one-time complimentary allotment per model | 200M free tokens on current embedding models (voyage-4-large, voyage-4, voyage-4-lite, voyage-context-4, voyage-code-4) and on rerankers (rerank-2.5 family); voyage-multimodal-3.5 and voyage-multimodal-3 get 200M text tokens + 150B pixels — a large one-time complimentary allotment per model |
| 2026-08-14 | Z.ai (Zhipu AI / GLM) | card requirement | unknown | no |
| 2026-08-14 | lmnt | card requirement | unknown | no |
| 2026-08-13 | Datalab (Marker / Surya) | free tier | $5 in free credits for new accounts — OCR in 90+ languages, PDF-to-markdown, tables, forms and structured extraction | $20/month (work email) or $10/month (personal email) free usage allowance — OCR in 90+ languages, PDF-to-markdown, tables, forms and structured extraction |
| 2026-08-13 | Datalab (Marker / Surya) | rate limits | Per-page pricing and rate limits not published | 10 requests/min on the free tier; per-page pricing (see datalab.to/pricing) |
| 2026-08-13 | Datalab (Marker / Surya) | the catch | $5 signup credit. The hosted API wraps the well-regarded open-source Marker/Surya OCR engine. Card and commercial terms not stated on the docs. | Landing page still advertises a $5 signup credit, but the billing page describes the current free tier as a recurring monthly allowance ($20/mo work email, $10/mo personal, no card, 10 req/min) “designed to let you run a complete proof of concept before committing to a paid plan” — no explicit statement on commercial use of the hosted API. The self-hosted OSS weights carry a separate restriction (research/personal/startups under $2M ARR/funding). |
| 2026-08-13 | Datalab (Marker / Surya) | free type | trial-credit | recurring-credit |
| 2026-08-13 | Datalab (Marker / Surya) | card requirement | unknown | no |
| 2026-08-12 | Clarifai | the catch | 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. | 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. Checked ToS (clarifai.com/company/terms, effective 2025-10-01) and billing docs (docs.clarifai.com/control/account-billing/) for commercial/production-use language. No clause restricts the $5 trial credit / Pay-As-You-Go tier to evaluation-only. The 'evaluation purposes only, not for production' language in §7.3 applies specifically to Beta Releases, not this plan. No explicit statement either way, so left null per contribution guidelines. |
| 2026-08-11 | Novita AI | the catch | Official signup advertises $100 Sandbox credits valid for 90 days; no credit card required | Official signup advertises $100 Sandbox credits valid for 90 days; no credit card required. Novita Terms of Service state that the Site and Marketplace Offerings may not be exploited for any commercial purpose without express prior written permission. |
| 2026-08-11 | Novita AI | commercial-use terms | unknown | no |
2026-W32 (2026-08-03 to 2026-08-09): 9 field changes across 4 providers
| Date | Provider | Field | From | To |
|---|---|---|---|---|
| 2026-08-05 | Baseten | free tier | $30 trial credit | New accounts receive free credits; Baseten's current pricing page does not state the amount |
| 2026-08-05 | Baseten | rate limits | Any supported model, compute-based pricing | Model APIs are priced per token; dedicated deployments are priced by compute time (per minute) |
| 2026-08-05 | Baseten | the catch | No documented expiration date publicly | Basic is $0/month, pay as you go. Current pricing confirms new-account credits but does not publish an amount or expiration date |
| 2026-08-05 | Fireworks AI | the catch | Default monthly spend cap of $50 for new accounts; no card needed to activate the $1 credit, card needed once it's spent | Fireworks uses prepaid credits. After the $1 credit is exhausted, add a payment method and credits (or enable auto top-up) to continue; account limits can rise with spend |
| 2026-08-05 | Novita AI | free tier | $1 free credit on signup | $100 Sandbox credits, valid for 90 days |
| 2026-08-05 | Novita AI | the catch | 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 | Official signup advertises $100 Sandbox credits valid for 90 days; no credit card required |
| 2026-08-05 | Novita AI | card requirement | unknown | no |
| 2026-08-05 | OVHcloud AI Endpoints | 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) | Two Qwen3Guard models (Gen-8B and Gen-0.6B) are currently listed as Free in the catalog; access is available anonymously or with an API key tied to a Public Cloud project |
| 2026-08-05 | OVHcloud AI Endpoints | the catch | 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 | 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 free-model tier |
2026-W31 (2026-07-27 to 2026-08-02): 40 field changes across 16 providers
| Date | Provider | Field | From | To |
|---|---|---|---|---|
| 2026-08-02 | Cerebras | free tier | Access to all Cerebras-hosted models | $5 in free credits for new accounts, usable across all public models |
| 2026-08-02 | Cerebras | 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 | Published Free Trial per-model limits: 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 |
| 2026-08-02 | Cerebras | the catch | Free tier includes community support (Discord) only; paid Developer tier gives "10x higher" rate limits | A verified payment method is required to activate Playground/API access (no charge until you buy credits). Credits expire 30 days after grant; whether any free access persists past expiry is not stated |
| 2026-08-02 | Cerebras | free type | renewing-quota | trial-credit |
| 2026-08-02 | Cerebras | commercial-use terms | unknown | yes |
| 2026-08-02 | Cerebras | card requirement | unknown | yes |
| 2026-08-02 | Cloudflare Workers AI | the catch | Resets daily at 00:00 UTC; overage on a Workers Paid plan bills at $0.011/1,000 Neurons | Resets daily at 00:00 UTC; overage on a Workers Paid plan bills at $0.011/1,000 Neurons. A few models (e.g. Kimi K2.6/K2.7-code, GLM-5.2) now require a Workers Paid plan |
| 2026-08-02 | Google Gemini API (AI Studio) | rate limits | Varies by model, roughly 5-30 req/min and 20-500 req/day depending on model | Varies by model: 5-30 RPM and 15-1,000 RPD (e.g. 2.5 Pro: 5 RPM/100 RPD; 2.5 Flash: 10/250; 2.5 Flash-Lite: 15/1,000; embeddings: 100 RPD; TTS: 15 RPD) |
| 2026-08-02 | Google Gemini API (AI Studio) | the catch | Free-tier prompts/outputs may be used by Google to improve its products when used outside the UK/CH/EEA/EU | Free-tier prompts/outputs may be used by Google to improve its products outside the UK/CH/EEA/EU. Since the 2026-03-23 terms, only Paid Services may serve API clients to end users in the EEA/CH/UK |
| 2026-08-02 | Groq | 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 | 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; qwen/qwen3.6-27b: 30 RPM/1K RPD/8K TPM/200K TPD; similar for GPT-OSS and Whisper models |
| 2026-08-02 | OpenRouter | free tier | 20+ models with a :free suffix, single API across many providers | A rotating set of models with a :free suffix (~14 today; count fluctuates), single API across many providers |
| 2026-08-02 | OpenRouter | the catch | ToS (Apr 2026) prohibits resale or building a competing service on the free models; a private proxy for personal use is fine | ToS (Jul 2026) prohibits reselling API access or building a competing service — platform-wide, not just the free models; per-model terms still apply |
| 2026-07-31 | Upstage | free tier | Unconfirmed: current pricing page shows only 10 free document-agent runs (no card); no Solar LLM API trial credit is listed | $10 in free credit on signup (no card) — Solar LLM (chat + embeddings) plus Document Parse / OCR / information extraction |
| 2026-07-31 | Upstage | rate limits | Solar Pro / Solar Mini | Document Parse billed $0.01/page (+$0.03 for extract), drawn from the $10 credit |
| 2026-07-31 | Upstage | the catch | A previously-listed "$10 / 3 months" Solar API trial credit could not be found on the current official pricing page (re-checked 2026-07-30), which advertises only "10 free runs" for document agents. Flagged for correction or removal. | No credit card required to receive the $10 credit; Studio agents also include 10 free runs. A separate institutional grant (up to 1 year of free Solar + Document Parse) exists for eligible organizations only. Credit validity period not stated. |
| 2026-07-31 | Upstage | commercial-use terms | unknown | yes |
| 2026-07-31 | Upstage | card requirement | unknown | no |
| 2026-07-31 | Upstage | OpenAI compatibility | unknown | yes |
| 2026-07-30 | Alibaba Cloud (Model Studio) | card requirement | unknown | no |
| 2026-07-30 | Cohere | OpenAI compatibility | unknown | yes |
| 2026-07-30 | HuggingFace | card requirement | unknown | no |
| 2026-07-30 | IBM watsonx.ai (Lite plan) | OpenAI compatibility | unknown | yes |
| 2026-07-30 | Modal | OpenAI compatibility | unknown | no |
| 2026-07-30 | NLP Cloud | commercial-use terms | unknown | yes |
| 2026-07-30 | NLP Cloud | card requirement | unknown | yes |
| 2026-07-30 | NLP Cloud | OpenAI compatibility | unknown | no |
| 2026-07-30 | Nebius AI Studio | commercial-use terms | unknown | yes |
| 2026-07-30 | Nebius AI Studio | phone requirement | unknown | no |
| 2026-07-30 | SambaNova Cloud | free tier | $5 trial credit, 3 months, plus a rate-limited free tier | Rate-limited free tier (applies when no payment method is linked) across all models |
| 2026-07-30 | SambaNova Cloud | the catch | Confirmed models: DeepSeek, Llama-3.3-70B, Gemma-3-31B, gpt-oss-120b | 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). |
| 2026-07-30 | SambaNova Cloud | free type | trial-credit | renewing-quota |
| 2026-07-30 | SambaNova Cloud | commercial-use terms | unknown | yes |
| 2026-07-30 | Upstage | free tier | $10 trial credit, ~3 months | Unconfirmed: current pricing page shows only 10 free document-agent runs (no card); no Solar LLM API trial credit is listed |
| 2026-07-30 | Upstage | the catch | $10 credit confirmed via the official pricing page; the "3 months" validity window could not be confirmed in accessible official sources (console is robots.txt-blocked) — flagged for re-verification | A previously-listed "$10 / 3 months" Solar API trial credit could not be found on the current official pricing page (re-checked 2026-07-30), which advertises only "10 free runs" for document agents. Flagged for correction or removal. |
| 2026-07-30 | Vercel AI Gateway | free tier | $5/month allocation (unconfirmed) | Free tier with a monthly free credit covering a subset of models at lower rate limits |
| 2026-07-30 | Vercel AI Gateway | rate limits | Routes to multiple supported providers rather than being a model host itself | Free tier is rate-limited per model (HTTP 429 on exceed), lower than paid; routes to many providers rather than hosting models itself |
| 2026-07-30 | Vercel AI Gateway | the catch | The "$5/month" figure doesn't appear in official reference docs, only in the community forum. Free tier confirmed but covers "a subset of models" with reduced limits; moving to a paid tier means "the monthly free credit no longer applies" — suggests a one-time benefit, not a recurring monthly one. Flagged for re-verification | 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. |
| 2026-07-30 | inference-net | free tier | $1 (up to $25 after completing a survey) | Free pay-as-you-go tier listed (1M gateway requests, 30 req/min); a model-inference credit is unconfirmed |
| 2026-07-30 | inference-net | rate limits | 30 req/min mentioned in the pricing table | 30 req/min on the free tier (per the current pricing page) |
| 2026-07-30 | inference-net | the catch | Could not verify the "$1, up to $25 after a survey" credit mechanism against docs.inference.net, pricing, or registration pages. A separate "Grants Program" exists (up to $10,000 in compute for open-source projects) but is a different offer — flagged for re-verification | The current pricing page (re-checked 2026-07-30) shows a free tier with 1M gateway requests and 30 req/min, but no confirmable "$1, up to $25 after a survey" inference credit. A separate open-source Grants Program (up to $10,000 in compute) exists but is a different offer — flagged for re-verification. |