AI API Router Directory
$ 6 entries match — showing 1–6 · sort: Free credits ↓
388 routers & providers · 813 models tracked · $3.8k free credits
- Official free tierAPI keydown4950msupdated 16h agoconsole.mistral.aisource · mistral.ai/pricingoverview
Mistral's La Plateforme is a first-party EU-based API with per-1M-token pricing, a 50% batch discount and up to 90% cached-input savings. The free plan includes $10/month of API credits plus Vibe and Studio access; Pro ($14.99/mo) raises that to $30/month. Open-weight models are available for self-hosting (Apache 2.0 for research/individual; commercial use requires a Mistral license).
free quotaCommunity reported approximate monthly value of the Experiment free tier for developers.
free modelsMistral Small 4Mistral Medium 3.5Mixtral 8x22B InstructMistral Large 2407Ministral 3B/8BPixtral+5see console.mistral.ai’s free quota / risk review → - Paid APIAPI keyunknownupdated Sep 6, 2026api.oriper.comsource · api.oriper.comoverview
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.
free quotaNo public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.
free modelsLlama-3.1-8B-InstructMistral NemoDeepSeek Chatsee api.oriper.com’s free quota / risk review → - Commercial aggregatorAPI keyunknownupdated Sep 6, 2026crof.aisource · crof.aioverview
CrofAI is a commercial AI API provider offering unified access to popular open models like Llama 3.1 and Qwen 2.5. It focuses on simplicity and ease of integration for developers requiring reliable per-token billing.
free quotaNo public free-tier information found (researched 2026-08-29).
free modelsLlama-3.1-8B-InstructMistral NemoQwen2.5 72B Instructsee crof.ai’s free quota / risk review → - Official free tierAPI keyunknownupdated Sep 6, 2026friendli.aisource · friendli.ai/pricingoverview
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 quotaFree tier for serverless inference — no credit card required
free modelsMeta-Llama-3.1-70B-InstructLlama-3.1-8B-InstructMistral NemoGemma 4 31Bsee friendli.ai’s free quota / risk review → - Paid APIAPI keyunknownupdated Sep 6, 2026speka.mesource · speka.me/pricingoverview
Speka is a unified AI API gateway providing access to frontier models (DeepSeek, Nemotron, Llama) via a single API key. It uses a subscription model with monthly usage allowances and standard per-token overage rates.
free quotaNo public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.
free modelsDeepSeek V4 FlashLlama 3.3 70B Instructgpt-oss-120bMistral NemoNemotron 3 Ultrasee speka.me’s free quota / risk review → - Paid APIAPI keyunknownupdated Sep 16, 2026www.together.aisource · together.ai/pricingoverview
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.
free quotaNo 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.
free modelsMeta-Llama-3.1-70B-InstructDeepSeek ChatQwen2.5 72B InstructMistral NemoGemma 2 27Bsee www.together.ai’s free quota / risk review →