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

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

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

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

OnAllways (llm.onallways.top) is a 'subscription-to-API' relay that pools various AI subscription accounts (Claude, GPT) and redistributes them as API keys. It is anonymously run and targets users looking for low-cost access to restricted models.

Unknown: the site's subtitle is 'Subscription to API Conversion Platform', with payment/affiliate/risk-control enabled and traffic funneled to third-party card shop catfk.com; no clear public persistent free quota is visible.

OAuth access — sign-in with your existing account. OpenAI Codex (CLI) 93 models tracked (via OpenRouter catalog).

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

OpenAI Codex CLI — OpenAI's terminal coding agent (also web/IDE). Authenticates via ChatGPT OAuth or an API key. Model lineup (as of mid-2026): GPT-6 Astra, GPT-5.6 (Sol/Terra/Luna), GPT-5.5, GPT-5.4 / 5.4 mini, plus gpt-oss-120b; GPT-5.3-Codex-Spark is a Pro-only research preview. Plans: Free, Go ($8), Plus ($20), Pro 5x ($100) / 20x ($200); API-key mode is pay-as-you-go at API rates.

ChatGPT plans use credit-based usage allowances (credits per 1M tokens, e.g. GPT-5.6 Sol 100/10/500); not a fixed $ credit value. API-key mode billed at standard OpenAI API token rates.

no-auth access — no key or sign-in required. No API key required — uses OpenCode's public free endpoint. This entry is an access surface/agent — it routes to third-party models rather than hosting its own.

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

OpenCode Zen is the model gateway from the OpenCode team that serves a curated, tested set of coding models. It includes a set of free models (Big Pickle, MiMo-V2.5 Free, Ling 3.0 Flash Fin Free, Nemotron 3 Ultra Free, Nemotron 3.5 Lightning Free, Muse Spark 1.3 Contributor Free) plus pay-as-you-go paid models, reachable at https://opencode.ai/zen/v1.

Free models are genuinely $0 per token (documented); no separate monthly USD credit.

OpenVecta provides an AI model API with an OpenAI-compatible endpoint. It focuses on simplicity and ease of use, with reports of a free tier or trial credits available for new users. Details were checked against the provider's own page at openvecta.com.

Free credits on signup for OpenAI-compatible inference across LLMs, embeddings, and reasoning models

OAuth access — sign-in with your existing account. Sign in with your Openference account to route requests through api.openference.com. An active plan is required for inference — OAuth may authenticate but return 402 without one. This entry is an access surface/agent — it routes to third-party models rather than hosting its own.

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

OrcaRouter is an LLM gateway offering zero token markup and adaptive routing across 200+ models. It is OpenAI-compatible and supports both pay-as-you-go and subscription plans with a handful of free-tier models.

Free-forever 'Hacker' plan: only $0-priced -free models and orcarouter/free endpoint are genuinely free, limited by request rate; probe showed $0 auto-grant. '1B free tokens'/voucher promos lack verifiable terms.

Perplexity's API blends request and token pricing: Search API at $5 per 1,000 requests; Sonar at $1/$1 tokens plus a $5–$12 per-1K request fee that scales with search depth; and the new Agent API serving OpenAI, Anthropic, Google and xAI models at direct provider rates with no markup, plus per-invocation tool pricing (web_search $0.0025). Sonar is sunset after September 27, 2026 — the Agent API is the successor.

No free tier on the API (checked 2026-09-16). Consumer Pro/Max plan credits (35K bonus + 10K monthly) apply to the app, not the API.

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

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

web-cookie access — wraps the provider web app (unofficial). Paste your __Secure-next-auth.session-token cookie value from perplexity.ai 5 models tracked (via OpenRouter catalog).

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

Play.ht is an AI text-to-speech platform with 900+ ultra-realistic voices, 32+ languages, voice cloning, and a real-time voice generation API. Plans: Free (1,000 chars/mo, no API), Creator ($31.20/mo billed annually, ~3M chars/yr), Unlimited ($99/mo regular; API add-on billed separately), Enterprise custom. Note: the official pricing page is JS-rendered and could not be fully captured; details sourced from third-party pricing guides.

Free tier = 1,000 chars/month (third-party guide; official page not captured); too small to value reliably against current API rates, and sources conflict on exact current pricing — set to null rather than guess.

Poe is Quora's multi-model chat product that aggregates GPT, Claude, Gemini, Grok, Kimi and image/video/audio bots behind one subscription and one points balance rather than separate provider plans. Official subscription plans are annual: $49.99/year ($4.17/month) for 10 thousand points per day, $199.99/year for 660 thousand points per month, $499.99/year for 1.65 million, $999.99/year for 3.3 million and $2,499.99/year for 8.25 million points per month, with an add-on rate of $30 per 1M points that subscribers can buy for API or one-off use. Non-paying users receive points daily that reset every 24 hours and never roll over; Poe's help centre states subscriptions start at $4.99/month.

Poe gives non-paying users daily compute points that reset every 24 hours, but no official page fetched states the daily quantity, and poe.com/pricing returns 404, so no dollar value is claimed (checked 2026-09-16).

web-cookie access — wraps the provider web app (unofficial). Paste your p-b cookie value from poe.com (DevTools → Application → Cookies → p-b) This entry is an access surface/agent — it routes to third-party models rather than hosting its own.

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

Poixe AI is a commercial AI API router and aggregator that provides a unified interface for multiple LLM upstreams. It features model-group specific rate limits and a dashboard for API key management, targeting developers seeking simplified access to global and Chinese models.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.

Poolside develops foundation models optimized for software engineering. Their API provides access to the Laguna series models (Laguna S, Laguna XS) with an emphasis on code generation and technical reasoning.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.

PromptQL (prompt.ql.app, by Hasura) is an agentic data-access platform: the app lets users 'just ask' questions answered by querying connected data sources (databases, SaaS integrations, GraphQL via Hasura DDN), with a shared-thread 'AI Slack' style product. Free sign-up is documented; public pricing/model lineup is not published (company raised $136M, enterprise-oriented). Underlying LLMs are not disclosed, so no catalog models are linked. This route is an unofficial web integration using the Bearer JWT from the prompt.ql.app graphql endpoint (marked Unofficial/Experimental in the OmniRoute provider reference).

No public pricing documented.

Qwen Cloud / Alibaba Cloud Model Studio is the API and model-marketplace side of Qwen, reachable internationally at qwencloud.com and in mainland China through Bailian at bailian.console.aliyun.com. The international marketplace page states that new users get 70M+ free tokens and advertises full-modality access from $6/month. Chinese-language Model Studio documentation states that activating Bailian for the first time automatically issues a newcomer free quota per model, usually 1,000,000 tokens, valid for 90 days and available only in the Beijing (cn-beijing) region.

Free grants are token allowances, not currency: 70M+ tokens for new users on the international Qwen Cloud marketplace, and typically 1,000,000 tokens per model (90 days, cn-beijing only) on Chinese Model Studio.

Qwen Studio is the consumer web app and desktop/mobile client for the Qwen model family, served at qwen.ai and app.chat.qwen.ai. The official product page states that Qwen Studio is free to use and open to all, and the same page lists Thinking, Search, Deep Research, Web Dev, Artifacts, Image Generation, Image Edit and Video Generation as product features. No paid consumer subscription and no numeric usage caps are published on the official pages fetched.

No numeric free allowance is published on official pages (checked 2026-09-16); qwen.ai states only that Qwen Studio is free to use and open to all.

Recraft bills its image and vector API in prepaid API Units sold at USD $1.00 per 1,000 units, making one unit equal $0.001. Recraft V4.1 raster generation costs $0.035 per image, V3 $0.04, V4 $0.04, V4 Pro $0.25 and V2 $0.022, while vector output costs more (V4.1 Vector $0.08, V3 Vector $0.08, V4.1 Pro Vector $0.30). Utility calls are metered per request - background removal and vectorization $0.01, erase region $0.002, crisp upscale $0.004, creative upscale $0.25. API Units are prepaid, non-cancellable, non-refundable and never expire.

A Free plan is documented on recraft.ai/pricing (images owned by Recraft, publicly visible, non-commercial) but no credit quantity or USD value is published, so none is set (checked 2026-09-16).

Regolo AI provides scalable serverless AI infrastructure with a focus on privacy and zero data retention. It serves popular open-source models (Llama, Mistral, Qwen) via an OpenAI-compatible API, offering monthly token capacity plans and a flexible free trial.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.

Routeway is an AI model router and gateway that provides a unified Bearer-auth interface for multiple global and domestic models. It simplifies integration for developers by handling model-specific protocols and providing a consistent management dashboard for keys and usage.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.