Best Free AI & ML Tools for Developers

Fast LLM inference on Groq's LPU hardware. Free plan: gpt-oss-120b, gpt-oss-20b and Qwen3.8 27B, each at 30 requests a minute, 1,000 requests and 200,000 tokens a day, plus Whisper speech-to-text at 2,000 requests a day. Llama 3.3 70B and Llama 3.1 8B left the free and developer plans on 2026-08-16 and are Enterprise-only. Developer plan prices per 1M tokens: gpt-oss-120b $0.15/$0.60; gpt-oss-20b $0.075/$0.30.

Free tier: Gemini 3.8 Flash, 3.7 Flash, 3.6 Flash, 3.5 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite, Gemini 3 Flash Preview, Gemini Embedding 2 and Gemma 4 are free of charge. Gemini 3.1 Pro Preview is paid only. Google publishes no free-tier rate limits; each project's limits are shown in Google AI Studio. Google's pricing table marks free-tier use as "Used to improve our products". Since 2026-09-18 Google serves the Gemini 2.5 models only to users who have used them before, and points new projects to 3.5 Flash-Lite or 3.8 Flash. Paid, per million tokens (input/output): Gemini 3.8 Flash $0.75/$3.75 until 2026-12-31, then double; Gemini 3.5 Flash $1.50/$9; Gemini 3.5 Flash-Lite $0.30/$2.50; Gemini 3.1 Flash-Lite $0.25/$1.50; Gemini 3.1 Pro Preview $2/$12 (prompts up to 200K tokens). Accounts opened after 2026-03-02 cannot spend the $300 Google Cloud welcome credit on the Gemini API.

Mistral's Free plan includes $10 per month in API credits and lets you test Mistral models in Studio, alongside limited messages, web searches and coding sessions in Vibe. API keys work in Free mode with no credit card, within usage and rate limits. In Free mode, Mistral may use your inputs and outputs to train its models unless you opt out. API prices: Ministral 3 (3B) $0.1/$0.1 (per 1M tokens); Mistral Small 4 $0.15/$0.6 (per 1M tokens); Mistral Large 3 $0.5/$1.5 (per 1M tokens); Mistral Medium 3.5 $1.5/$7.5 (per 1M tokens). Batch processing is half price, and cached input tokens cost up to 90% less.

AI model router. Free plan: 25+ free models, 4 free providers, 50 requests a day, no BYOK. Free models are capped at 20 requests a minute; accounts that have bought at least $10 of credits get 1,000 free-model requests a day. The Standard plan (pay-as-you-go) charges a 5.5% fee on credit purchases and includes BYOK up to $25,000 of list-price inference a month with no fees, 5% after.

Workers AI runs AI models on Cloudflare's global network. Every account gets 10,000 Neurons per day at no charge, reset daily at 00:00 UTC; on the Workers Free plan, requests beyond that fail until the reset. On the Workers Paid plan (from $5 per month), usage above 10,000 Neurons per day costs $0.011 per 1,000 Neurons. Seven models, including @cf/moonshotai/kimi-k2.6, @cf/zai-org/glm-5.3 and @cf/deepseek-ai/deepseek-v4-pro-0813, require the Workers Paid plan or prepaid AI Gateway credits.

Ultra-fast LLM inference API — no permanent free tier. New accounts get $5 in free credits after adding a verified payment method, expiring 30 days after they are granted. Free Trial limits on gpt-oss-120b and qwen-3.8-27b: 5 requests/min and 1M tokens/day. Pay as you go after: GPT OSS 120B $0.35/$0.75 per M tokens, Qwen 3.8 27B $0.99/$1.49 per M tokens. Multi-thousand tokens/sec inference speedWhen we last read the page we cite for this offer, on 2026-09-17, we could read no amount, tier or rate on the page, so we cannot confirm these terms today.

AI model API for Command chat models, Embed, Rerank, Transcribe and Parse. Every account starts with a Trial API key: calls made with it are free, limited to 1,000 API calls a month, and may not be used for production or commercial purposes. Trial rate limits: 20 requests a minute per Chat model, 2,000 Embed inputs a minute and 10 Rerank requests a minute. Trial keys can use all of Cohere's models and APIs. Production keys are pay-as-you-go. Prices per 1M tokens: Command R7B $0.0375/$0.15; Command R $0.15/$0.60. The pricing page lists Command A+ (Apache 2.0) at $0 through an API key and as a model download.

AI API platform. One model is priced Free in OpenAI's own table: the moderation model omni-moderation-latest. No GPT model is priced free. GPT prices per 1M tokens (Standard, short context): gpt-6-astra $10.00/$50.00; gpt-6-sol $2.00/$10.00; gpt-6-luna $0.10/$0.50; gpt-5.6-sol $4.00/$20.00 (a promotional price, available at least through November 21, 2026); gpt-5.6-terra $2.00/$12.00; gpt-5.6-luna $0.20/$1.20. Batch and Flex processing halve these prices. Embeddings from $0.02 per 1M tokens. Three further free amounts are sub-quotas inside paid tools: 1 GB of File search storage (then $0.10/GB per day), 1 GB per account per month of ChatKit upload storage, and search content tokens from the web search preview tool on non-reasoning models.

AI media gateway: one OpenAI-compatible API to image and video generation models from several providers, billed at each provider's price with no markup, platform fee or subscription. One model, FLUX.1 [schnell] FP8, is listed free per image ("Free to try", served through Fireworks AI). New accounts also get a $1 credit with no card required; Lumenfall's terms say promotional credits typically expire after 90 days. After that you top up prepaid credits. Under Lumenfall's terms (2026-03-05), content sent through free features, including free API usage, may be used to train AI models.

Social media scheduling, publishing and analytics. Free plan at $0/month. The pricing page states no per-plan entitlements: the feature list shown is identical for all four plans.

easy-to-use, free image generation AI with free API available. No signups or API keys required, and several option for integrating into a website or workflow. [#opensource](https://github.com/pollinations/pollinations)The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-14, so we cannot confirm these terms today.

Grok API, pay as you go: sign up at console.x.ai, then load it with credits. grok-4.7 $2.00/$6.00 (per 1M tokens, under 200k prompt tokens). grok-4.3 $1.25/$2.50 (under 200k prompt tokens). grok-build-0.1 $1.00/$2.00 (under 200k prompt tokens). Grok 4.1 Fast was retired on 2026-05-15; its model names now route to grok-4.3 at grok-4.3 rates.The page we cite for this offer does not name it when we last looked, on 2026-09-05, so we cannot confirm these terms today.

Claude API with usage-based pricing per million tokens (input/output). Claude Fable 5.1 $10/$50. Claude Opus 5.5 $4/$20. Claude Sonnet 5 $2/$10. Claude Haiku 4.5 $1/$5. The Batch API gives a 50% discount on input and output tokens. New users receive a small amount of free credits to test the API.

AI-powered code editor built on VS Code. Hobby is the free plan: no credit card required, limited Agent requests, access to Composer — cursor.com/pricing states no completion or request figure for it. Individual paid plans: Pro $20/month, Pro+ $60/month (3x Pro's Agent limits), Ultra $200/month (20x). Teams is $40/user/month for a Standard seat or $120/user/month for a Premium seat (5x Standard's Agent limits). Enterprise is custom-priced with pooled usage, invoice/PO billing and SCIM. Cursor renders only the selected tier's price in the page body.

Autonomous AI software engineer by Cognition. Cognition replaced its Core and Team plans on 2026-04-14 with Free, Pro, Max, Teams and Enterprise. Free ($0) includes a "Light quota to code with agents", "Limited model availability", "Unlimited inline edits" and "Unlimited Tab completions". Pro ($20/month) adds cloud agents, Max ($200/month) has "Significantly higher quotas", and Teams is "$80/month for team plan + $40/mo per full dev seat". Paid plans include a usage allowance, and extra usage is billed in dollars at API pricing. Enterprise is custom-priced, with VPC deployment and SAML/OIDC SSO, and is billed in Agent Compute Units (ACUs).

AI builder for websites, web apps and mobile apps by StackBlitz; it builds full-stack apps in the browser on WebContainers. Free plan ($0): 1M tokens per month with a 300K daily limit, public and private projects, unlimited databases, a 10MB file upload limit, and hosting on a bolt.host URL with up to 10 GB of bandwidth and 333,333 web requests a month, with Bolt branding. Pro is $25/month billed monthly ($18/month billed yearly), with no daily token limit and from 10M tokens a month. Teams is $30 per member a month ($27 billed yearly), and Enterprise is custom-priced.

AI app builder (formerly GPT Engineer) — The free plan includes a daily grant of 5 build credits (up to 30 a month), plus monthly grants of 20 Cloud credits. The free plan also grants 4 credits usable by AI features built into user apps, to try the feature before subscribing.The page we cite for Lovable states in words that it is free, which confirms the price — the limits stated here come from our read of the vendor's page on 2026-09-03.

Agentic coding tool by Anthropic: it reads a codebase, edits files, runs commands and works with development tools, in the terminal, IDEs, a desktop app and the browser. No free plan: "Claude Code is included in all paid plans", and Claude's Free plan does not include it. Pro is $20/month billed monthly ($17/month billed annually), Max is $100/month (5x) or $200/month (20x), Team Standard seats are $25/seat billed monthly ($20 billed annually), and Enterprise is "$20 per seat per month plus usage billed at API rates". Plan usage is shared with Claude chat. At the limit, paid plans can turn on usage credits billed at standard API rates, or use an Anthropic API key billed pay-as-you-go.The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-02, so we cannot confirm these terms today.

AI coding assistant by GitHub. Copilot Free is $0 with no credit card: 2,000 code completions a month, a limited monthly allowance of GitHub AI Credits for chat and agent features, and models through auto model selection only. Copilot Student is free for verified students. Paid plans include a monthly allowance of AI credits: Pro $10 (1,500 credits), Pro+ $39 (7,000) and Max $100 (20,000); Business $19 (1,900) and Enterprise $39 (3,900) per seat. Code completions are unlimited on paid plans, and usage beyond an allowance costs $0.01 per AI credit.

AI coding assistant by AWS. Free tier: inline code suggestions, chat, 1,000 lines code transformation/month, 50 agentic requests/month, access to latest Claude models. Supports VS Code, JetBrains, CLI, and AWS Console. Pro plan $19/user/month (higher limits, admin controls, IP indemnity). AWS will end support for the Amazon Q Developer IDE plugins on April 30, 2027, and points IDE users to Kiro.

Open-source autonomous AI coding agent for VS Code. Fully free — users provide their own API keys (OpenRouter, Anthropic, OpenAI, etc.). Supports file editing, terminal commands, browser interaction. No usage limits beyond API provider costs. MIT licensed.The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-02, so we cannot confirm these terms today.

Open-source AI pair programming CLI tool. Fully free — users provide their own LLM API keys (supports GPT-4o, Claude, Gemini, DeepSeek, Ollama local models). Git-aware editing, multi-file changes, voice coding, in-chat image support. Apache 2.0 licensed.The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-02, so we cannot confirm these terms today.

Windsurf is now Devin Desktop ("Devin Desktop is the new name for Windsurf."), Cognition's AI IDE. windsurf.com/pricing redirects to devin.ai/pricing, which prices it together with Devin. The Free plan ($0) includes a "Light quota to code with agents", "Limited model availability", "Unlimited inline edits" and "Unlimited Tab completions", with quotas that reset daily and weekly. Pro is $20/month, Max $200/month, and Teams "$80/month for team plan + $40/mo per full dev seat"; paid plans can buy extra usage at API list prices. Pro subscribers on the old $15/month price keep it indefinitely.The page we cite for this offer does not name it when we last looked, on 2026-09-24, so we cannot confirm these terms today.

Agentic development platform by Google, generally available: a desktop app to manage multiple local agents in parallel, an agentic IDE, a CLI and an SDK, for macOS, Windows and Linux. Its agents can open and drive a local Chrome browser. The individual plan is $0/month, with Gemini, Claude and gpt-oss agent models, "Unlimited Tab completions", "Unlimited Command requests" and "Basic weekly rate limits". Google AI Pro ($19.99/month) and Google AI Ultra (from $99.99/month) add "More generous rate limits" and a "Flexible AI credit pool", and organizations can use it through Google Cloud. Announced November 2025.The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-02, so we cannot confirm these terms today.

Open-source terminal AI coding agent by Google, Apache 2.0 licensed. Since 2026-06-18, Login with Google no longer works for personal accounts, according to Google's Gemini Code Assist deprecation notice; the README still advertises 60 requests a minute and 1,000 a day with a personal Google account. With a Gemini API key, use counts against the Gemini API's own free tier and pricing. A Gemini Code Assist Standard or Enterprise licence is unaffected. Supports MCP tools, shell commands and file editing.

Coding agent by OpenAI. Available with a ChatGPT subscription, including the $0 Free plan, and separately with an API key billed on token use; both routes are current. OpenAI's Codex pricing page lists Free ($0/month, "Explore Codex capabilities on quick coding tasks") and Go ($8/month, "Use Codex for lightweight coding tasks"), both with GPT-6 Luna at Standard speed in the desktop app, subject to rollout. Plus ($20/month) adds Codex on the web, in the CLI, in the IDE extension and on iOS, cloud code review and Slack integrations, and GPT-6 Sol. Pro (from $100/month) gives 5x or 20x more Codex usage than Plus. ChatGPT Business has two seat types, both carrying Codex: Standard at $20/user/mo billed annually ($25 monthly) and Premium at $100/user/mo billed annually ($125 monthly), where Premium buys 5x more usage than Standard and removes the five-hour usage limit. The Codex pricing page we cite lists only the Standard seat — the Premium seat is published on OpenAI's business pricing page. Codex-only pay-as-you-go seats closed to new Business workspaces on 2026-06-24; existing seats continue. With an API key, Codex runs in the CLI, SDK or IDE extension at API prices, without the cloud features.

ML model hub. Free users get $0.10 a month of Inference Providers credits (subject to change); Inference Providers serves 200+ models, and extra usage requires a credits purchase. PRO ($9/month) gets $2.00 a month. Free accounts get 100GB of private storage and best-effort public storage; substantial storage needs PRO, Team or Enterprise.When we last read the page we cite for this offer, on 2026-09-13, we refused the change we considered recording because it named no figure that had moved, and refusing a change is not a confirmation of the terms above, so we cannot confirm these terms today.

Google's data science platform with free notebooks, datasets and competitions. Notebooks get a weekly GPU quota of 30 hours, sometimes more depending on demand (one NVIDIA Tesla P100 or two Tesla T4s), and a TPU v3-8 for up to 20 hours per week. Sessions run up to 12 hours on CPU or GPU and 9 hours on TPU, with 20 GB of auto-saved disk in /kaggle/working. Free GPUs and TPUs may queue at busy times. Datasets are capped at 200 GB each and 200 GB of private datasets in total. Kaggle's one paid service is hosting a competition.

ML model hosting and inference. A new account can run the models in Replicate's Try for Free collection without buying credit, for a limited number of runs that Replicate does not state; after that you add billing and buy credit. Replicate says these models are not free forever. Most models bill by the second for the hardware they run on, such as $0.000025/sec on CPU Small and $0.001525/sec on one H100. Official models bill per output instead, such as FLUX 1.1 Pro at $0.04 per image; per million input/output tokens: DeepSeek-R1 $3.75/$10.When we last read the page we cite for this offer, on 2026-09-17, we found the page did not mention this offer, which is not evidence it ended, so we cannot confirm these terms today.

ML model deployment platform. New workspaces receive credits for testing and deployment; Baseten does not state the amount. Basic plan: $0 per month, pay as you go. Dedicated deployments bill per minute. Model APIs bill per 1M tokens: GLM-5.3 $1.40/$4.40. GLM-5.3-Flash $0.15/$0.50.When we last read the page we cite for this offer, on 2026-09-10, we found a change we could not reconcile with the terms we publish, so we cannot confirm these terms today.

ML experiment tracking, model registry, and LLM app tracing and evaluation (Weave). The cloud Free plan is $0/mo and designed for personal development, with up to 5 model seats, 5 GB/mo of storage and 1 GB/mo of Weave data ingestion. Pro starts at $60/month with a 30-day free trial and is for teams with fewer than 50 employees. A separate self-hosted Personal plan (W&B server on your own machine) is $0/mo with 1 user seat, for personal projects only; corporate use is not allowed.

Comet makes Opik, for LLM and agent observability and evaluation, and an MLOps platform for ML experiment tracking. Opik is open source and free to self-host. Opik Free Cloud allows up to 10 team members, 25k spans per month and 60-day data retention, with agent tracing and analysis, test suites and assertions, and Agent Playground. MLOps Free covers 1 platform user, with experiment tracking, dataset management and versioning, Model Registry and 100GB of data storage. Academics can apply for a free Pro plan.

ML platform (Gradient Notebooks, Workflows and Deployments) from Paperspace, now part of DigitalOcean. The Free plan is $0 with public projects, 5 GB of storage and free machines for Notebooks in your private workspace (Free CPU C4 and Free GPU M4000; free machines shut down after at most 6 hours). Other machines are billed per hour. Pro is $8/month for individuals and $12/month for teams; Growth is $39/month. DigitalOcean says new customers can still sign up but recommends its own GPU products instead.

Integration platform for AI Agents and LLMs — Free $0 No credit card required 100,000 tool calls / mo 50,000 triggers / mo 3 team members

Simulate, evaluate, and observe your AI agents. Maxim is an end-to-end evaluation and observability platform, helping teams ship their AI agents reliably and >5x faster. Free forever for indie developers and small teams (3 seats).

Platform for agent observability, evaluation and improvement. AX Free costs $0 with no credit card required: 25k trace spans per month, 1 GB ingestion per month, 15 days of retention, unlimited users and evals, 10 Signal issues per month, the Alyx agent and community support. AX Pro is $50 per month with 50k spans and 10 GB of ingestion per month and 30 days of retention. Arize also offers Phoenix, which is ELv2 licensed and can be self-hosted, and 2 Phoenix Cloud instances for free.

Evals, prompt playground, and data management for Gen AI. Starter plan (free): 1 GB processed data/month, 10k scores/month, 14 days data retention. Unlimited users, projects, datasets, playgrounds, and experiments. Overage: $4/GB data, $2.50 per 1k scores.

Rebranded to Respan; keywordsai.co redirects to respan.ai. Free plan: full platform, 100k logs, 1k scores, 5 datasets, 2 evaluators, 5 prompts. No credit card required.

Open-source LLM engineering platform for tracing, evaluating and debugging AI applications. The Langfuse Cloud Hobby plan is free with no credit card: 50k units a month (each trace, observation and score counts as one unit), 30 days of data access, 2 users, community support via GitHub, and all platform features with limits. Core is $29/month with 100k units, then $8 per 100k units up to 1M units and less above that. The open-source self-hosted edition is free under the MIT license.When we last read the page we cite for this offer, on 2026-09-13, we found a change we could not reconcile with the terms we publish, so we cannot confirm these terms today.

enables developers to trace, evaluate, manage prompts and datasets, and debug issues related to an LLM application’s performance. It creates open telemetry standard traces for any LLM which helps with observability and works with any observability client. Free plan offers 50K traces/month.Its pricing page has not resolved for us since 2026-05-07, so we cannot confirm these terms today.

A LLMOps platform helping AI teams measure, monitor, and optimize LLM applications for reliability, cost-efficiency, and performance. With a powerful DSPy component, we enable seamless collaboration between engineers and non-technical teams to fine-tune and productionize GenAI products. Free plan includes all platform features, 1k traces/month and 1 workflow DSPy optimizers. [#opensource](https://github.com/langwatch/langwatch)When we last read the page we cite for this offer, on 2026-09-14, we found a change we could not reconcile with the terms we publish, so we cannot confirm these terms today.

Control panel for Gen AI apps featuring an observability suite & an AI gateway. Send & log up to 10,000 requests for free every month.When we last read the page we cite for this offer, on 2026-09-18, we could read no amount, tier or rate on the page, so we cannot confirm these terms today.

Free accounts get 15 PR reviews/week and 100 agentic reviews/day.

Vector database. The Starter plan is free: up to 2 GB storage, 2M write units and 1M read units a month, 1 GB of egress a month (reads that return data stop at the cap until the next billing period), 5 indexes, 1 project and 2 users, on AWS us-east-1 only. Assistant includes 1 GB storage and 500k input, 300k output and 500k context tokens a month. Three embedding models include 5M tokens a month each; bge-reranker-v2-m3 includes 500 requests a month. Builder is $20/month flat.

Vector database. The Qdrant Cloud Free Tier is a single-node cluster with 0.5 vCPU, 1 GB RAM and 4 GB disk, for testing and prototypes, with no credit card required; Qdrant says it serves about 1M vectors of 768 dimensions. It includes free Cloud Inference with selected models. An unused free cluster is suspended after 1 week and deleted after 4 weeks of inactivity if not reactivated. Paid clusters are billed on CPU, memory and disk usage.

Superseded: As of 2026-08-28, deepgram.com/pricing reads: Free $200 Credit then pay-as-you-go. Flux TTS is free until 9/12/2026. Voice Agent API's Flux TTS is free through September 12, 2026. We are not publishing our stored Deepgram terms beside it — our own pricing change record, discovered 2026-08-28, names them as the previous ones. Read what we recorded ↓

Computer vision platform for labeling, training and deploying models. On September 18, 2026 Roboflow announced a free tier for its Core plan: 10 credits that refresh every month, private projects and models, and model weight download. More credits can be bought. Credits pay for storage, labeling, training and cloud deployment; running models on your own hardware with Roboflow Inference uses none. Core's data licensing and model training setting is on by default, including for private projects; a workspace can turn it off. Public plan workspaces are moving to the Core free tier.

Data labeling and AI data platform. scale.com/pricing now redirects to a form for booking an intro call and states no prices. Self-serve sign-up for labeling and Nucleus dataset management is open at dashboard.scale.com, and Scale's docs describe a billing tab for on-demand customers. Until at least August 25, 2026, the pricing page offered a Self-Serve Data Engine, paid as you go by credit card, with the first 1,000 labeling units free when you label with your own workforce and the first 10,000 images free in data management. Scale's Nucleus docs still show a 2022 pricing table with a free Nucleus tier that includes 10,000 items of data.The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-02, so we cannot confirm these terms today.

Speech-to-text and Speech Understanding API. New accounts get $50 in free credits with no credit card required; the credits do not expire and cover pre-recorded and streaming speech-to-text, the Voice Agent API, Speech Understanding and Guardrails, but not LLM Gateway. Free accounts can run 5 pre-recorded transcriptions in parallel and open 5 new streaming sessions per minute. Pay-as-you-go rates: Universal-3.5 Pro $0.21/hr; Universal-2 $0.15/hr; Universal-Streaming $0.15/hr; Universal-3.5 Pro Realtime $0.45/hr.

Data labeling platform (Catalog, Annotate and Model). The Free plan includes 500 Labelbox Units (LBUs) each month, up to 30 users, 50 projects and 25 ontologies. When the LBUs run out you can still access and export data, but cannot add data rows, labels or predictions until the next billing period. It handles image, video, text, audio, document, chat and geospatial data. The Starter plan costs $0.10 per LBU. Students and faculty at qualifying institutions can apply for a free Education License for non-commercial use.We could not read the page we cite for this offer when we last looked, on 2026-09-26, so we cannot confirm these terms today.

Augmented reality face filters for any platform with one SDK. The free plan provides up to 10 monthly active users (MAU) and tracks up to 4 facesThe page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-14, so we cannot confirm these terms today.

Free OCR API that parses image and PDF files and returns the text as JSON: 25,000 requests/month, 1 MB file size limit, 3-page PDF limit, 500 requests/day per IP address, plus 2,500 Engine 3 conversions/month. Free-tier searchable PDFs carry a watermark. The online OCR web form needs no registration and accepts files up to 5MB.The page we cite for OCR.Space states in words that it is free, which confirms the price — the limits stated here come from our own record rather than from that page.

20 free pages/month: Extract data from PDFs, emails. AI powered. Full API access.

Turn any unstructured documents (PDF, XLSX, JPG, PPTX, etc.) into structured JSON data. Parse, extract data, and edit PDF forms. Free tier with 15k free credits and pay-as-you-go.When we last read the page we cite for this offer, on 2026-09-19, we reached a domain root that states nothing about the terms we hold, so we cannot confirm these terms today.

Real-time web search API for AI agents, with search, extract, crawl and research endpoints. The free Researcher plan gives 1,000 API credits per month with no credit card required, resetting on the first of each month. A basic search costs 1 credit and an advanced search 2; extract costs 1 credit per 5 successful URLs (2 at advanced depth); research costs 4 to 250 credits per request. Search and Extract can also be called without an API key, free and rate-limited. Pay-as-you-go costs $0.008 per credit; the Project plan is $30 per month for 4,000 credits.

AI-powered audio enhancer SaaS that removes noise and echo while preserving natural vocal clarity. totally Free: unlimited one-click enhancements, no login required, supports MP3/WAV/FLACWe could not read the page we cite for this offer when we last looked, on 2026-09-28, so we cannot confirm these terms today.

Clinical AI Reference. Students have free access to the professional tool suite, which includes Open Search, Clinical Summary, Med Review, Drug Interactions, ICD-10 Codes, and Stewardship. Additionally, a free trial for the professional suite is available.The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-02, so we cannot confirm these terms today.

Free $0 Forever. Including 2 Analytical Agents, 2 Data Sources, Up to 2 Team Members, 2 Dashboards. Usage Limits 20 requests / day · 50,000 tokens / month

AI Powered Writing Assistant. The entire platform is free as long as you bring your own API key.When we last read the page we cite for this offer, on 2026-09-13, we reached a domain root that states nothing about the terms we hold, so we cannot confirm these terms today.

Clarifai's platform is no longer available, so there is no free tier. On May 12, 2026 Nebius announced it was licensing Clarifai's inference technology and that Clarifai's core engineering and research team was joining Nebius. Clarifai's site said platform credit purchases would be disabled after June 18, 2026. Its pricing page returned 404 from June 2026, and on 2026-09-27 Clarifai's API and documentation hosts did not resolve.

ML experiment tracker, now shut down. After agreeing to be acquired by OpenAI, Neptune closed new sign-ups and trials on December 3, 2025, and set March 5, 2026 as the day its hosted app and API would be turned off and remaining hosted data deleted; on 2026-09-27 neptune.ai returned errors. Its free plan for individuals and researchers ended with the service. Neptune's migration guides cover Weights & Biases, Comet, MLflow and ZenML, among others.We could not read the page we cite for this offer when we last looked, on 2026-09-26, so we cannot confirm these terms today.

LLM observability and evaluation platform by LangChain — Developer plan is $0/seat/month with up to 5k base traces/month, then pay-as-you-go. LCU is $1.50/unit and LSU is $1.00/unit. Plus plan is $39/seat/month with up to 10k base traces/month, then pay-as-you-go.

AI coding assistant with deep codebase understanding. No free tier. Standard $20/month flat and Business $100/month flat, each covering up to 50 seats with $20 and $100 of included monthly usage respectively across LLM, Context Engine and compute; top-ups are pay-as-you-go. Enterprise is custom-priced. Flat team pricing with no per-seat charge. Supports VS Code, JetBrains and CLI. SOC 2 Type II certified

GitHub retired GitHub Models on 2026-07-30, so there is no free tier. GitHub's own documentation states "GitHub Models has been retired." The former offer was free access to 100+ models via GitHub Marketplace at 10-15 RPM and 50-150 requests/day.

Free inference endpoints on build.nvidia.com: models marked Free Endpoint, including Kimi K3, DeepSeek V4.1 Flash and NVIDIA Nemotron, can be called at no cost. Up to 40 requests per minute; limits may vary by model, and traffic from other users may cause throttling. NVIDIA's API Trial Terms allow free use for testing and evaluation only, not production.The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-02, so we cannot confirm these terms today.

Cloud-hosted Ollama for running open-source LLMs — The Free plan costs $0 and includes starter usage credits. Buying usage credits unlocks all models. It includes 1 concurrent request.

LLM inference gateway. Without a key: 10 requests a minute, 60 an hour, 500,000 tokens per 24 hours. With a free token from dash.llm7.io: 40 a minute, 100 an hour, 1,000,000 tokens per 24 hours. Free access covers turbo-tier models not marked usage-only, such as GLM-5.3-Flash and codestral-latest. Other models, including all image and speech-to-text models, need Pro ($12/mo) or a paid balance.We could not read the page we cite for this offer when we last looked, on 2026-09-16, so we cannot confirm these terms today.

Pay-as-you-go model inference. siliconflow.cn, run by a Beijing company, lists these models at no charge: the chat models Qwen3-8B, Qwen2.5-7B-Instruct (Free), Qwen3.5-4B, GLM-4-9B-0414, GLM-Z1-9B-0414, DeepSeek-R1-0528-Qwen3-8B (Free) and Xing4.0-29B; the translation model Hunyuan-MT-7B; the OCR models PaddleOCR-VL-1.5 and DeepSeek-OCR; the embedding models bge-m3, bge-large-zh-v1.5 and bge-large-en-v1.5; the reranker bge-reranker-v2-m3; Kolors image generation; and six speech recognition models. The Pro versions are paid: Qwen2.5-7B-Instruct (Pro), bge-m3 (Pro) and bge-reranker-v2-m3 (Pro). All other models are paid too, including DeepSeek-V4-Flash, DeepSeek-V4-Pro and GLM-5.3. Using all the free models requires real-name verification, and online personal verification accepts only Chinese-issued documents, such as a resident ID card or a Foreign Permanent Resident ID Card. The international site, siliconflow.com, is run by SiliconFlow Labs Pte. Ltd. under Singapore law, is not offered in mainland China, and gives $1 in free credits to start. Its paid rates per million input/output tokens: gpt-oss-120b $0.05/$0.45; DeepSeek-V4.1-Flash $0.15/$0.60.When we last read the page we cite for this offer, on 2026-09-16, we found the page did not mention this offer, which is not evidence it ended, so we cannot confirm these terms today.

China-based GLM model API. The price list marks these models free: GLM-4.7-Flash, GLM-4-Flash-250414 and GLM-Z1-Flash (text); GLM-4.6V-Flash, GLM-4V-Flash and GLM-4.1V-Thinking-Flash (vision); CogView-3-Flash (image); CogVideoX-Flash (video). API calls are rate limited, with a separate concurrency limit per model.The page we cite for this offer does not name it when we last looked, on 2026-09-16, so we cannot confirm these terms today.

Pay-as-you-go LLM API with no free tier, billed from a prepaid balance. DeepSeek-V4.1-Flash (deepseek-flash): $0.30/M input, $1.20/M output at peak. DeepSeek-V4-Pro (deepseek-v4-pro): $1.32/M input, $3.96/M output at peak. Cache-hit input is $0.006/M on Flash and $0.044/M on Pro. Off-peak rates are half; peak hours are 01:00-04:00 and 06:00-10:00 UTC on weekdays. 1M context, up to 384K output. China-based.

MiniMax sells API access pay-as-you-go on platform.minimax.io. Its pricing pages list no free API allowance; one docs page mentions a free quota for new pay-as-you-go users but gives no amount. Text: MiniMax-M3 $0.30/$1.20 (per 1M tokens, inputs up to 512k, after a permanent 50% discount); MiniMax-M2.7 $0.30/$1.20 (per 1M tokens); MiniMax-M2.7-highspeed $0.60/$2.40 (per 1M tokens). Speech: speech-2.8-turbo $60 and speech-2.8-hd $100 per 1M characters. Video: MiniMax-H3 $0.08 per second at 768P. Image: image-01 $0.0035 per image. Music and lyrics APIs closed to new users on 2026-08-20. Token Plan subscriptions: Plus $22, Max $55 and Ultra $132 per month.

AI coding tool by AWS, with an IDE, a CLI and a web interface. Prompts run by default on Auto, "an agent that uses a mix of different frontier models", and users can pick Claude, GPT or open-weight models. KIRO FREE $0 per month 50 credits. KIRO PRO $20 per user / month 1,000 credits. KIRO PRO+ $40 per user / month 2,000 credits. KIRO PRO MAX $100 per user / month 5,000 credits. KIRO POWER $200 per user / month 10,000 credits. Add-on credits are $0.04/credit. $20 credit towards first paid plan upgrade.

Web search API for AI agents with Search, Contents, Answer, Monitors and Agent endpoints. The free tier gives $10 in credits each month, about 1,400 searches, resetting on the first of the month without rollover, plus a one-time $10 onboarding bonus; no payment method required. Free teams get 10 QPS on search. Search costs $7 per 1,000 requests; Contents $1 per 1,000 pages per content type; Deep Search $12 to $15 per 1,000 requests. Search and Contents can also be paid per request over x402 in USDC on Base or Solana, with no API key.

Multi-provider GPU inference API — 30+ AI services (LLM, image generation, embeddings, speech) accessible via x402 micropayments. Unified API across providers, no accounts needed. Pay per inference call.Its pricing page has not resolved for us since 2026-04-14, so we cannot confirm these terms today.

Vertex AI Agent Builder with sessions and memory now GA. Build, deploy, and manage AI agents with persistent memory, multi-turn sessions, and tool governance. Part of the Vertex AI platform.Its pricing page has not resolved for us since 2026-04-15, so we cannot confirm these terms today.

Vector Search 2.0 now GA on Vertex AI. High-performance approximate nearest neighbor (ANN) vector similarity search for AI/RAG applications. Supports billion-scale indexes.The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-05, so we cannot confirm these terms today.

First natively multimodal embedding model — text, images, video, audio, and documents in a single embedding space. Enables cross-modal similarity search and retrieval. Available via Vertex AI and Gemini API.

Open-source AI coding agent for the terminal, editors, desktop, browser and chat, formerly with a free Qwen OAuth tier. No free tier: Qwen Code's documentation says "The Qwen OAuth free tier was discontinued on 2026-04-15" and points users to Alibaba Cloud Coding Plan, OpenRouter, Fireworks AI or another provider. Coding Plan Pro is $50 a month; a Model Studio API key is billed pay-as-you-go.The page we cite for this offer states no amount, tier or rate we can read when we last looked, on 2026-09-10, so we cannot confirm these terms today.

Cloud sandboxes for AI agents: isolated Linux machines that run generated code and shell commands, work with files and reach the internet. The Hobby plan has no monthly fee and a one-time $100 usage credit, with no credit card needed to start. When the credit runs out, the account is blocked until a payment method is added. Hobby allows 20 concurrent sandboxes and up to 1 hour of continuous runtime per sandbox. Running sandboxes are billed per second for CPU and RAM. Pro is $150/month plus usage.

Inference API for open-source models, billed per token. Together AI does not currently offer free trials; access requires a minimum $5 credit purchase, and the platform is fully prepaid. Llama 3.3 70B $1.04/$1.04 (per 1M tokens). gpt-oss-120B $0.15/$0.60.

Inference platform for open models, with serverless per-token pricing and on-demand GPU deployments billed per GPU second. Fireworks offers $1 in free credits to get started. Accounts with no payment method, or with no credits, are limited to 10 requests per minute, and an account without a payment method is suspended when the $1 credit runs out until one is added. Serverless prices: OpenAI GPT OSS 120B $0.15/$0.60 (per 1M tokens); MiniMax M3 $0.30/$1.20 (per 1M tokens); GLM 5.3 $1.40/$4.40 (per 1M tokens); Kimi K3 $3.00/$15.00 (per 1M tokens). Batch inference costs 50% of serverless prices. Image generation and audio inference were deprecated on June 10, 2026.

Serverless platform for running CPU and GPU workloads. The Starter plan has no monthly fee and includes $30 of compute per month (GPU, CPU and memory), 3 workspace seats, 100 containers and 10 GPU concurrency. Usage beyond the $30 is billed per second: T4 $0.000164 per second; H100 $0.001097 per second. Since 2026-09-01, Shared Endpoints are billed per token from the first request and are not covered by the $30. Team is $250 per month with $100 of compute included.

Free plan at $0 per month: 10,000 credits per month and 3 Projects in Studio, with Text to Speech, Speech to Text, Sound Effects, Voice Design, Music, Productions and Image. No commercial licence on the free plan — that starts at Starter, $6 per month for 30,000 credits. Unused credits do not roll over on the free plan, and cancelling a paid plan drops the account back to it. elevenlabs.io/pricing, read 2026-09-19.

Developer Platform API is credit-priced at 1 credit = $0.01, with 25 free credits to start — a one-time $0.25 grant, not a monthly allowance. Per-image costs: SDXL 1.0 from 0.9 credits, Stable Diffusion 3.5 Flash 2.5, Stable Image Core 3, Stable Diffusion 3.5 Medium 3.5, Large 6.5, Stable Image Ultra 8. Stable Audio 2.5 is 20 credits and 3.0 is 26. platform.stability.ai/pricing, read 2026-09-19.

Sandboxes for running AI-generated code, priced pay as you go. New accounts get $200 in free compute on a free trial that needs no credit card; Daytona does not say whether the credit expires or renews, and it does not cover GPU sandboxes. A sandbox can use up to 4 vCPUs, 8 GB of RAM and 10 GB of disk, and on the first two usage tiers its network access is restricted. After the credit: $0.0504 an hour per vCPU and $0.0162 an hour per GiB of memory; the first 5 GiB of storage is free.

Sandboxes and runtime for AI agents, priced on usage with no plan fee. New accounts get up to $200 in free credits; Blaxel does not say whether they renew, and its terms say unused service credits expire one year after they are issued unless otherwise specified. The free quota tier allows 10 sandboxes, which it deletes after at most 7 days, and free accounts cannot request higher quotas. A running sandbox costs $0.0000115 per GB of RAM per second; idle time is not billed as active CPU.

Sandboxes for AI agents from Novita AI, billed per second for CPU and RAM while a sandbox runs. New users who complete an account setup survey get $100 in promotional credits for Novita Sandbox usage, with no credit card; the credits expire, and Novita does not state after how long. The free tier allows 5 concurrent sandboxes of up to 2 vCPUs and 4 GB of RAM, each running for at most 1 hour. Paid usage costs $0.0000098 per vCPU-second and $0.0000032 per GiB-second.

Devboxes: secure micro-VM environments for building and running AI agents. New accounts get $50 in usage credits with Pro features and no credit card; usage draws the credit down until it is gone, and nothing is charged automatically when it ends. On the trial: 3 running devboxes, sizes up to Medium (2 CPUs, 4 GB), and at most 1 hour of keep-alive. After the credit, the Basic plan is a free subscription with usage billed at $0.108 per CPU-hour and $0.0252 per GB-hour of memory. Pro is $250 a month plus usage.

Memory layer for AI agents and apps. The Hobby plan is free with no credit card: 10,000 memory add requests and 1,000 retrieval requests a month, 1 project, unlimited end users and community support. Mem0 calls it permanently free. Graph memory is not on Hobby. Starter is $19/month for 50,000 add and 5,000 retrieval requests a month. Under Mem0's terms (2026-08-03), Free Plan users grant Mem0 a perpetual licence to their content, including to train AI models; paid plans exclude that, apart from aggregated, de-identified data. Mem0 Open-Source (Apache 2.0) can be self-hosted.

Context and memory layer for AI agents: Zep gives an agent context from past conversations, user activity and changing preferences. The Free plan includes 10,000 credits a month, with no rollover or auto top-up. An Episode (a chat message, JSON payload or block of text) up to 350 bytes costs 1 credit; retrieval, storage and users cost none. Free allows 2 projects, 1 Memory MCP Server seat and 5 custom entity and edge types, with variable rate limits and lower-priority processing. When the credits run out, Episodes stop processing until the next billing cycle and the account's rate limit drops to 5 requests a minute. Flex, the first paid plan, is $125/month for 50,000 credits. The self-hosted Community Edition is deprecated; Graphiti, the framework under Zep, is open source (Apache 2.0).

Stateful AI agents that keep their memory across sessions. The Free plan is $0/month for the Letta app, CLI and web app: up to 3 stateful agents, limited use of Letta Auto, a limited number of LLM requests on rotating free models, and your own model API keys or coding plans. Free is a Personal Plan; API-key access to the Letta API is sold as a Developer Plan, the API Plan at $20/month plus $0.10 per active agent a month and pay-as-you-go model usage. Pro is $20/month for up to 20 stateful agents. The Letta agent harness is open source (Apache 2.0) and runs on your own infrastructure with no Letta account.

Memory and search API for AI agents, with user profiles and plugins for coding agents. The Free plan is $0/month with $5 of credits included, renewed every month; plan credits do not roll over. Credits pay the same rates on every plan, such as $5 per 1M SM tokens of plain-text memory and $5 per 1M search queries, and usage needs an available credit balance. Free includes the memory and search API and the coding-agent plugins for 1 team seat and unlimited end users; connectors such as Google Drive and Notion need a paid plan. Pro is $19/month with $20 of credits included.

Open-source memory engine that turns documents and data into a knowledge graph agents can query. Cognee Cloud's Free plan is $0/month, labelled "Free forever", with no card required: 1 workspace, unlimited users and API calls, and 1M tokens included (Cognee's billing docs say 10M). Cognee does not say the tokens renew; when the balance runs out, uploads, graph processing and search are refused. Tokens beyond it cost $1.00 per 1M on every plan, and Standard adds workspaces at $5 a month each. The open-source engine (Apache 2.0) is free to self-host.

Google Search API returning real-time results. 2,500 free queries when you sign up, no credit card required; a plain search uses one credit, and Maps and Lens searches use 3. No Serper page says the free queries renew or expire, and the terms bar registering more than one account. Serper stops accepting queries when the balance reaches zero. Paid credits are prepaid packs with no subscription: Starter is $50 for 50,000 queries ($1.00 per 1,000) at 50 queries per second, valid for 6 months; the largest pack falls to $0.30 per 1,000.

Web search API for AI agents. Accounts created with a professional email address get $20 of credit, topped back up to $20 each month (Linkup's docs); the pricing page calls this 4,000 free queries and states no period. Linkup's app asks other sign-ups to add a card, with no charge, to unlock the credit. Rate limit: 10 queries a second per organization. Then pay as you go from a prepaid balance: search $0.005 a call ($0.006 with a sourced answer or structured output), deep search $0.05 to $0.055, fetch from $0.001. Top-ups of $1,000 or more earn 10-20% bonus credit.

Web search and research APIs for AI agents. Organizations with a credit card on file get $5 of free credit each month, and unused credit expires at month end. $5 covers up to 5,000 Search requests in Turbo or Fast mode, or 1,000 in Basic or Advanced (Advanced is the API default); usage beyond $5 is billed to the card at standard rates. One monthly credit per organization and per card; marketplace and postpaid organizations are not eligible. The pricing page also offers "up to $80 at signup" without stating its terms. A hosted Search MCP is free without an account or API key, at lower rate limits, for personal and hobby use. Then pay as you go: Search $1 per 1,000 requests (Turbo, Fast) or $5 (Basic, Advanced) with 10 results, at 600 requests a minute.

Search, Reader, embeddings and reranker APIs. Each new API key comes with 10M free tokens, shared across these APIs and for non-commercial use only (CC-BY-NC); no page says they renew. Search (s.jina.ai) needs a key and costs at least 10,000 tokens a request, so the free tokens cover at most 1,000 searches, at 100 requests a minute. Reader (r.jina.ai), which converts a URL to LLM-friendly text, also works without a key at 20 requests a minute. Paid tokens are prepaid: 1 billion for $50 ($0.05 per million), or 11 billion for $500 with a premium key. Jina AI has been part of Elastic since October 2025.

Web Search API for AI agents. 100 free queries a day with no API key or account through the keyless MCP profile (api.you.com/mcp?profile=free), limited to the you-search and you-discover tools. New API accounts also get a $100 sign-up credit with no credit card required; no page says it renews or expires. Then pay as you go with no minimums: Web Search API $5.00 per 1,000 calls with up to 100 results per call, live page extraction $1.00 per 1,000 pages, at 10 requests a second on self-serve accounts.