AI API Router Directory

OCI Generative AI (now positioned as OCI Enterprise AI) is Oracle's managed service for pretrained and custom models, agents and governance on Oracle Cloud Infrastructure, with chat, embeddings, rerank, OpenAI-compatible APIs and an OCI Responses API. Oracle bills it through the public OCI price list, where rates are itemised per model: xAI Grok and Google Gemini entries are priced per 1,000,000 tokens (with cached-input and >200K-context variants), Cohere and Meta Llama endpoints per 10,000 transactions, and private replicas or fine-tuned models on Dedicated AI units per hour. New accounts get a US$300 cloud credit valid for 30 days plus ongoing Always Free services, but Generative AI is not among the AI services Oracle lists as having a free pricing tier.

Oracle Cloud Free Tier gives a US$300 cloud credit to spend within 30 days on all OCI services in addition to Always Free services, switching to pay-as-you-go or Always Free only afterwards (oracle.com/cloud/free/); OCI Generative AI itself is not listed among Oracle AI services with a free pricing tier.

DigitalOcean's AI stack is GPU Droplets plus a managed Inference product (model catalog, serverless and dedicated inference, agents and knowledge bases) rather than one hosted LLM endpoint. GPU Droplets bill per second from $0.76/GPU/hour (RTX 4000 Ada) up to $11.19/GPU/hour spot or $7.94 reserved for HGX B300, and serverless inference is prepaid only, charging published per-token rates such as Llama 4 Maverick at $0.20 input / $0.696 output per 1M tokens and gpt-oss-120b at $0.055 / $0.385. New accounts can receive a $5 credit valid for 90 days.

A $5 new-account credit applied to usage and expiring after 90 days is described in the 'How does the $5 free credit work?' FAQ on the GPU Droplets pricing page; no larger AI-specific credit is stated on the official pages fetched.

Venice (venice.ai) — privacy-focused web app (anonymous or zero-retention) for chat, image, video and audio, known for self-hosted open-weight models plus TEE-hosted closed models. Unofficial browser/cookie integration (merged into existing 'venice' row).

Credits are USD-denominated; Pro $18/mo → $1 credit, Pro+ $68/mo → $75 credit (10% bonus), Max $200/mo → $225 credit (12.5% bonus).

AI/ML API is a major AI model aggregator providing unified access to 1000+ models from OpenAI, Anthropic, Google, DeepSeek, and more. It offers a single API key for LLM, image, voice, and video models with a focus on production-ready pay-as-you-go access.

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

Hyper (by Charm) is an AI inference solution purpose-built for coding. It manages its own infrastructure to optimize open-source coding models. It provides 100 free Hypercredits monthly on signup. Details were checked against the provider's own page at hyper.charm.land.

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

DataRobot is an enterprise AI platform that provides centralized access to a wide range of LLMs through its AI Gateway. It emphasizes model governance, security, and unified billing for large-scale enterprise AI deployments.

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).

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.

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.

FriendliAI is a high-performance AI inference platform specializing in serving frontier open-weight models like GLM, DeepSeek, and Llama with industry-leading speed. It offers serverless Model APIs, dedicated GPU endpoints, and on-premise containers.

Free tier for serverless inference — no credit card required

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.

Inference.net is a unified LLM gateway, observability and fine-tuning platform rather than an image or video vendor. Its pay-as-you-go tier is $0 + usage and includes 1M gateway requests and 1M tracing spans per month, 14-day data retention, one seat and a 30 req/min rate limit. Growth is $250/month with a $50 one-time opening credit, 50M gateway requests and tracing spans per month, unlimited seats and a 250 req/min limit. The catalog lists 60 models from OpenAI, Anthropic, Google and open-source labs billed per token, from Schematron V2 Turbo at $0.03/$0.15 to Claude Opus 5 and GPT-6 Astra at $5.00-$10.00 input and $25.00-$50.00 output per 1M tokens.

No free dollar credit: the $0 pay-as-you-go tier includes 1M gateway requests and 1M tracing spans per month, while the $50 one-time opening credit is listed only on the $250/month Growth plan (checked 2026-09-16).

Muse Code is Meta's specialized AI coding environment and agent service, built on the Meta Model API. It provides a terminal-based interface for code generation and transformation, featuring both a monthly subscription plan for high usage and credit-based PAYG options via Muse Spark.

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

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.

Snowflake Cortex AI runs LLMs, agents and search inside the Snowflake governance perimeter, exposed through SQL AI functions, Cortex Agents, Cortex Analyst and Cortex Search. It bills on a second credit type: AI Credits, priced at $2.00 per credit on demand globally and $2.20 regionally (Snowflake Service Consumption Table, effective 2026-09-09), on top of Platform Credits for warehouses. Published AI Credit rates per 1M tokens include llama3.1-8b at 0.11 in / 0.11 out, llama3.3-70b at 0.36 / 0.36, mistral-large2 at 1.00 / 3.00, and claude-sonnet-5 at 1.30 / 6.50 when invoked via Snowflake CoWork or Cortex Agents; Cortex Search is 6.3 AI Credits per GB per month of indexed data and Cortex Analyst is 67 Platform Credits per 1,000 messages.

Snowflake markets a free 'start for free' signup but no dollar credit amount or free Cortex allowance is stated on the official pricing page or consumption table (checked 2026-09-16).

Together AI is a first-party inference platform spanning serverless models (published per-1M pricing from $0.14 on Llama 3 8B Lite, with batch discounts), fine-tuning, provisioned throughput, and dedicated H100/H200/B200 instances from $3.99/hr. One account covers the full ladder from serverless to reserved capacity.

No free credit listed on the official pricing page as of 2026-09-16. Sign-up grants vary by campaign — confirm in the console before relying on one.