AI API Router Directory

Chat Oripe is an AI API aggregator offering access to multiple LLM families via a unified interface. It targets low-cost inference with standardized pricing across different upstream models. Details were checked against the provider's own page at api.oriper.com.

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

Clarifai provides a production-ready AI API for developers, offering an OpenAI-compatible endpoint to run inferences on Clarifai-hosted models from labs like Meta, Google, and Mistral, alongside their own specialized vision and NLP models.

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

Coze is an all-in-one AI bot building platform that allows users to create and deploy agents with multiple models. It provides a production API for developers to integrate these bots into external applications with usage-based billing.

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

DGrid AI is a decentralized AI network that routes requests across a distributed mesh of nodes. It features an OpenAI-compatible gateway and is integrated into tools like Chatbox and Claude Code. Operates with on-chain transparency.

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

Databricks Foundation Model Serving prices inference in Databricks Units (DBUs) on a pay-as-you-go basis with per-second granularity, no up-front cost and no published monthly platform floor. Per-model DBU rates per 1M tokens are public: Llama 3.3 70B at 7.143 input / 21.429 output, GPT-OSS-20B at 1.000 / 4.286, Llama 3.1 8B at 2.143 / 6.429, and Kimi K3 at 42.857 / 214.286 with a 4.286 cache-read rate. Databricks states the DBU price on the Serverless Real-time Inference SKU is $0.07 per DBU in the base region (us-east-1 for AWS, us-central1 for GCP, eastus for Azure), and the page offers a 14-day free trial without disclosing a fixed credit amount.

No dollar-denominated free credit is published: the pricing page offers a 14-day free trial and states that trial credit eligibility, amount and expiry are determined solely by Databricks after account creation (checked 2026-09-16).

DeepAI bundles its image APIs into the DeepAI Pro subscription instead of publishing per-call API pricing. Free access is $0 with no account balance needed and only 'Limited' allowances across HD images, chat, music and video. Pro costs $7.49/month billed annually at $89.99 (or $9.99 monthly with the renewal rate fixed) and includes 500 HD images, 60 Genius images, 10 Super Genius 2K images, 1,750 chat messages, 25 seconds of HD video, 8 seconds of 2K Hollywood Mode, 100 songs and 12 Concierge tasks per month. Overages draw on a prepaid wallet at 1 cent per HD image, 8 cents per Genius image, 25 cents per Super Genius 2K image, 20 cents per second of HD video and 10 cents per song.

The Free plan is $0 with no account balance needed and only 'Limited' allowances (HD images, chat, music, video); no credit quantity or USD value is stated, and API access is bundled with DeepAI Pro (checked 2026-09-16).

DeepInfra is an OpenAI-compatible inference cloud for open-weight models, with per-token rates published on a single pricing page. Examples from that page: DeepSeek-V4-Flash-0731 at $0.06 per 1M input tokens ($0.015 cached) and $0.18 per 1M output; Qwen3.5-9B at $0.10/$0.15; DeepSeek-V3.2 at $0.26/$0.38; Kimi-K3 at $2.85 per 1M input and $14.25 per 1M output; embeddings from $0.005 per 1M input tokens. Models without fixed token rates are billed on execution time, and custom LLM deployments are billed per minute of GPU uptime across A100 ($0.89/GPU-hour) through B300 ($4.89/GPU-hour). There is no free credit: the pricing page states you must add a card or pre-pay before you can use the service.

No free tier stated on official pages (checked 2026-09-16): deepinfra.com/pricing states that you must add a card or pre-pay before using the service, with no starter credit offered.

Doubao (by Bytedance/Volcengine) provides a suite of models including the high-performance Doubao-Pro and Lite series. It is a major Chinese cloud provider with native API endpoints. Details were checked against the provider's own page at www.volcengine.com.

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

Empower provides an AI API router with an OpenAI-compatible endpoint. It focuses on bridging multiple model providers (Llama, etc.) through a single gateway for standard clients and SDKs. Details were checked against the provider's own page at docs.empower.dev.

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

fal.ai runs a generative-media model API: 1,000+ endpoints across image, video, audio and 3D behind one queue-based HTTP interface, called with the same request/response shape from Python, JavaScript or raw HTTP. Pricing is per output rather than per token, as published on its pricing page: $0.03 per Seedream V4 image, $0.04 per Flux Kontext Pro image, $0.02 per megapixel for Qwen image, $0.05 per second of Wan 2.5 video, $0.07 per second of Kling 2.5 Turbo Pro and $0.40 per second of Veo 3 video. Dedicated GPU capacity is listed at $4.50/hr for H100 (as low as $1.89/hr), $4.50/hr for H200, $6.25/hr for B200 and $8.50/hr for B300. There is no free token allowance: fal runs on a prepaid credit balance that funds both model usage and the account's concurrency limit.

No free tier stated on official pages (checked 2026-09-16): fal.ai/pricing and the Model APIs pricing docs describe only prepaid credits, with no starter credit or free allowance.

Featherless AI provides serverless access to LLMs and agent runtimes. It offers subscription-based 'Chat' plans with unlimited tokens and credit-based 'Developer' plans for API usage. Details were checked against the provider's own page at featherless.ai.

Free tier available — no credit card required

FenayAI is an AI API router and aggregator providing unified access to major models like GPT-6 Astra and Claude Fable. It features an OpenAI-compatible gateway with BYOK support. Details were checked against the provider's own page at fenayai.com.

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

GigaChat is an AI model series developed by Sberbank, optimized for the Russian language and multimodal tasks. It provides a robust API for developers featuring both chat and reasoning capabilities, primarily targeting the Russian AI ecosystem.

No public free-tier information found (researched 2026-08-29).

Google Jules is an asynchronous coding agent that clones a connected GitHub repository into a Google Cloud VM, presents a plan for approval, then returns a diff and pull request. The no-cost tier is stated as 15 tasks per day and 3 concurrent tasks, while Jules in Google AI Pro provides 100 tasks per day and 15 concurrent tasks and Jules in Google AI Ultra provides 300 tasks per day and 60 concurrent tasks. Jules is described as language agnostic but works best with JavaScript/TypeScript, Python, Go, Java and Rust projects.

The no-cost tier is stated on jules.google as 15 tasks per day and 3 concurrent tasks, described in Google's blog as 'Introductory access to Jules'; no USD credit is published and daily task caps do not convert to a dollar amount.

Haiper AI is an advanced generative video platform offering text-to-video, image-to-video, and video-to-video capabilities. Its API provides programmatic access to Haiper Video 2.x and 1.5 models with support for multiple resolutions, billed per second of generated video.

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

Heroku AI is a managed inference and agents layer on top of the Heroku platform, billed per 1M tokens with the model, input and output rates published directly on the Heroku pricing page. Examples include claude-opus-4-8 at $5.50 input / $27.50 output, claude-4-5-sonnet at $3.30 / $16.50, gpt-oss-120b at $0.15 / $0.60, qwen3-235b at $0.22 / $0.88, glm-4-7-flash at $0.07 / $0.40 and nova-lite at $0.06 / $0.24, with each model tagged by which region it is provisioned in (US, EU, or both). MCP servers run as one-off dynos on a pay-as-you-go basis, and the platform retains its dyno grid from Eco at $5/month up to Shield-2XL at $1,800/month.

No free inference credits or AI allowance are stated on the Heroku pricing page; the only credit mechanism described is Enterprise add-on credits where one credit equals $1 of marketplace services (checked 2026-09-16).

IBM watsonx.ai is an enterprise AI studio combining machine learning, decision optimization and generative AI, with an Essentials pay-as-you-go plan starting at USD 0/month and a Standard plan starting at USD 1110/month. The free Toolbox playground includes up to 300,000 foundation-model tokens per month, up to 20 compute usage hours (CUH) per month and up to 100 text-extraction documents per month. Model usage is metered per million tokens, for example granite-4h-small at USD 0.0636 input and USD 0.265 output, with all IBM and third-party embedding models at USD 0.10 per million tokens.

The free Toolbox playground grants up to 300,000 foundation-model tokens, 20 compute usage hours and 100 text-extraction documents per month; IBM publishes no USD-denominated credit on the official pages fetched, so no dollar value is asserted.

Ideogram sells text-to-image generation twice over: a consumer credit subscription for the web app and a separate pay-per-image API. Published API rates are $0.03 for 4.0 Turbo, $0.06 for 4.0 Default and $0.10 for 4.0 Quality per image, with character-reference variants at $0.10-$0.20 and the cheaper P-Image line starting at $0.003. Web plans are Free ($0, weekly slow credits for eligible accounts), Plus at $15/month billed annually for 1,000 priority credits/month and Pro at $42/month for 3,500. The API defaults to a 10 in-flight request limit.

The Free plan is listed at $0 with slow credits granted 'Weekly for eligible accounts' for eligible accounts signing in with Google/Apple/Microsoft and the amount may vary; no numeric credit or USD value is published, so none is set (checked 2026-09-16).

Jina AI (Foundation API) provides specialized AI models for search and RAG, including high-quality embeddings, reranking, and a Reader API that converts web content to LLM-friendly markdown. The Reader API is currently free for developers, while other APIs follow token-based usage billing.

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

KIE.AI is an AI model API relay providing access to frontier models like Claude 3.5 Sonnet and GPT-4o. It operates on a pay-as-you-go basis and provides an integrated dashboard for API key management and usage tracking.

No public free-tier information found (researched 2026-08-29).

Kenari is an Indonesian AI gateway providing a unified OpenAI-compatible API to 38+ models from Claude, GPT, and Gemini. It is uniquely tailored for the Indonesian market, accepting local payment methods like QRIS and billing in Rupiah (IDR).

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

Kilo Gateway is Kilo's OpenAI-compatible inference gateway at base URL https://api.kilo.ai/api/gateway, branded as "The Universal Gateway for AI Inference" and positioned as the routing layer that powers Kilo's own coding tools. It provides one key across 500+ models from 60+ providers, with pay-as-you-go billing at "exact provider rates" and no inference markup, plus BYOK where you "pay only for the routing, not the tokens". Its pricing page lists a Free access tier at $0/forever with access to default free models, basic analytics and BYOK support, and credit purchases carry a 5% processing fee with no subscription required.

No free tier stated on official pages (checked 2026-09-16): Kilo Gateway publishes a Free tier at "$0/forever" giving access to default free models, but no dollar or token credit allowance.

LLM Gateway is a unified AI API router that allows access to over 200 models from multiple providers. It features a 'Hosted Free' plan where free models are accessible with a 5 requests per 10 minutes limit when no credits are available in the account.

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

LLM.Kiwi is an AI model router offering access to various LLMs via an OpenAI-compatible endpoint. It provides a free tier with a rate limit of 40 requests per hour for specific high-resource models and higher limits for pro subscribers.

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