AI API Router Directory

OpenInference - open-source LLM relay with a single OpenAI-compatible endpoint (Anthropic-format root also available at https://api.openference.com/), API-key auth, automatic provider failover and a zero-data-retention option; free to start, paid plans from USD 1/mo; documented per-model on-demand USD/1M pricing on openference.com/models.

Free plan: 3-day trial with open-source models — no credit card required

VSLLM (Weiyun Model Open Platform) is a commercial AI API relay gateway that aggregates multiple large models. It is OpenAI-compatible and features a daily auto-refreshing free quota for new sign-ups. Claims to offer highly competitive, transparent pricing based on actual token usage.

Free subscription auto-refreshes daily without claiming: ~20 API calls + ~100K tokens/day (non-cumulative, reset next day) ~ $3/mo at $1/1M tokens; also GitHub-star and daily check-in reward activities.

FastRouter is a high-performance gateway for AI model routing, comparison, and operations. It supports 200+ models via an OpenAI-compatible API with intelligent cost optimization and failover. Details were checked against the provider's own page at fastrouter.ai.

Free credits included to build, test and explore.

The Cloudflare AI Playground at playground.ai.cloudflare.com is a browser environment for experimenting with, benchmarking and tuning AI models, with a Model mode for testing system prompts and run settings, a Compare mode for side-by-side evaluation of models under identical prompts, and an experimental Generative UI mode. It is the front end for models that Cloudflare hosts and serves, and the free access terms come from Workers AI: the free allocation allows anyone to use a total of 10,000 Neurons per day at no charge, with additional usage on the Workers Paid plan billed at $0.011 per 1,000 Neurons. The model catalog covers 65 models including Llama, Qwen, DeepSeek, Kimi, GLM, Gemma, Mistral, Nemotron, Whisper and FLUX families, and the playground itself states that output is unverified and does not reflect Cloudflare's views.

Free allocation is stated as 10,000 Neurons per day at no charge on the Workers AI pricing page, equivalent to about $0.11/day at the published rate of $0.011 per 1,000 Neurons (the dollar figure is a conversion, the allowance is official).

Qoder - AI coding IDE (Agent/Quest modes) with credit-based plans; Free tier (2-week Pro trial with 300 credits, limited completions/NES, BYOK); Pro/Pro+/Ultra; Credit Pack; per-model cost varies by tier multiplier (Auto approx 1.0x, Ultimate approx 1.6x, Performance approx 1.1x, Efficient approx 0.3x now free for paid, Lite free); context options 200K/400K/1M.

Plan quota approx subscription value (approx USD 0.01/credit). qoder.com/pricing headline shows Pro at 4,000 credits incl. a 2,000 first-purchase bonus; docs base is 2,000 credits/mo.

Devin, built by Cognition, is an agentic software engineering product spanning Devin Desktop, a CLI, Devin Cloud agents, DeepWiki and the Devin API, aimed at multi-repo engineering work such as migrations, PR review, incident triage and scheduled chores. Its pricing page lists Free at $0 with "a light quota to code with agents", limited model availability, unlimited inline edits and unlimited Tab completions, then Pro at $20/month, Max at $200/month for significantly higher quotas, Teams at $80/month for the team plan plus $40/month per full dev seat, and Enterprise by contact. Paid plans come with a usage allowance that refreshes daily and weekly, and usage beyond the allowance is purchased and consumed at API pricing.

Devin Free is $0 with a light agent quota, limited model availability, unlimited inline edits and unlimited Tab completions (devin.ai/pricing, checked 2026-09-16).

AINative Studio specializes in AI agent infrastructure, providing multimodal APIs, persistent agent memory, and MCP server hosting. It offers tiered subscription plans that include 'ZeroTime' credits for agentic workflows and specialized model access.

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

Blackbox AI now presents itself as enterprise inference rather than a consumer coding tool: its pricing page shows a single Enterprise plan with custom, annual, purchase-order committed spend and no free or individual tiers. Pricing is per token against published list rates across a 300+ model catalog served from one OpenAI-compatible endpoint, for example deepseek-v4.1-flash at $0.15 input / $0.60 output per 1M tokens and kimi-k3 at $3.00 / $15.00 per 1M, with commitments drawn down as usage is consumed and spend alerts at 75% and 90%. The same pages state end-to-end encryption on every connection, contractual zero data retention, PII removal before prompts reach closed models, dedicated single-tenant deployment and implementation included at $0 with a forward-deployed engineer.

No free tier stated on official pages (blackbox.ai, blackbox.ai/pricing and docs.blackbox.ai all present enterprise per-token commits only, checked 2026-09-16).

ClinePass — Cline's flat $9.99/month subscription giving 2-5x the usage (vs standard API rates) on a curated set of open-weight coding models from Z.ai, Moonshot AI, DeepSeek, MiniMax, MiMo, and Qwen. No separate provider accounts or API keys needed; usable with other agents via the ClinePass API key. Separate from Cline's pay-as-you-go provider.

Flat monthly quota (2-5x API rate); not a per-token credit system.

Tencent CodeBuddy (CN) — Tencent's AI coding tool (IDE, plugin, CLI) backed by the TokenHub LLM platform. Proxies open-weight models from Z.ai, Moonshot, MiniMax, and DeepSeek under a monthly Token Plan (credit-based). Compatible with Claude Code, Codex CLI, Cline, Cursor, OpenCode, Kilo Code, etc. Note: pricing/model data below is from the documented Tencent Cloud Token Plan pages; CN endpoint specifics (copilot.tencent.com) were not separately fetchable, so this reflects the TokenHub plan as documented.

Credits are the unified billing unit; per-model deduction coefficients apply with DeepSeek peak/off-peak pricing (off-peak = half peak). No clean 1 credit = $X mapping documented, so no creditValueUsd.

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

Zhipu AI's GLM platform (bigmodel.cn, also served at open.bigmodel.cn) sells model access per token in CNY and bundles agentic coding into a separate GLM Coding Plan. The official pricing page lists GLM-5.3 at 8 yuan per million input tokens, 2 yuan per million cached tokens and 28 yuan per million output tokens with a 1M-token context, and GLM-5.3-Flash at 0.8 / 0.23 / 2.8 yuan. New accounts receive 20 million free tokens on registration, and the text model GLM-4.7-Flash (200K context) and vision model GLM-4.6V-Flash are listed as free for input, output and cache. The GLM Coding Plan shows 118 yuan/month (Lite), 538 yuan/month (Pro) and 1078 yuan/month (Max), with discounted continuous-subscription prices of 94.4 / 430.4 / 862.4 yuan and quarterly billing at 8-fold and annual at 7-fold discounts.

Free grant is 20,000,000 GLM tokens for new registrations (tokens, not currency), stated on bigmodel.cn/pricing and bigmodel.cn/claude-code; GLM-4.7-Flash and GLM-4.6V-Flash are additionally free per token.

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.

MNN AI (mnnai.ru) is a Russian AI API aggregator offering access to models like GPT-5.6 and Claude 5. It features a free entry tier with $1 monthly credits and strict rate limits (10 RPM), designed for low-volume testing and regional access.

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

MegaNova AI is a comprehensive AI API aggregator and infrastructure provider, offering access to 200+ models including GPT-5.6, Claude 4, and proprietary Manta models. It features a tiered free quota system based on account status and spend, plus OpenAI-compatible serverless and dedicated GPU endpoints.

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

Morph (morphllm.com) is an AI provider focusing on agentic coding models. Its API offers high-speed code editing and search via proprietary models (Compact, Reflexes) and optimized frontier models (GLM, Kimi), with a limited free tier of 200 requests per month.

Free tier: 250K credits/month, $0

OfoxAI is an enterprise AI gateway aggregating 100+ models from OpenAI, Anthropic, Google, and more. It offers official provider pricing with a 0% platform fee and includes built-in budget controls and audit logs.

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

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.

TGhan (Xiao Yu Yun API) is a feature-rich AI API relay providing unified access to over 30 LLM providers including OpenAI, Claude, and Grok. It offers professional features like empty-response compensation, transparent usage logs, and multi-protocol support optimized for high stability.

Confirmed paid-only via direct /api/pricing check: 49 models, all paid (fixed-price quota_type=1 or per-token model_ratio>0); zero free-price entries. Top-up is via third-party redemption codes.

ZCode is Zhipu's official coding client for the GLM Coding Plan sold on bigmodel.cn, whose personal tiers are listed in CNY: ¥94.4/month (list ¥118) with 10,000 credits per week, ¥430.4/month (list ¥538) at six times the Lite allowance, and ¥862.4/month (list ¥1078) at fourteen times, each unlocking Claude Code, Codex, Cursor, OpenCode, Cline, Kilo Code and AutoClaw, with ZCode subscribers receiving 150% quota. The platform's API price list shows GLM-5.3 at 8 CNY per million input tokens and 28 CNY output, GLM-5.3-Flash at 0.8/2.8 CNY, GLM-TTS at 2 CNY per 10,000 characters, and Batch calls at half the standard price. New registered users receive 20 million tokens, and GLM-4.7-Flash (200K context) and GLM-4.6V-Flash are listed as free API models.

Allowance is 20,000,000 tokens for newly registered users ('新用户注册得 2000万 Tokens') plus up to 200 million tokens via referral on bigmodel.cn/pricing; no CNY or USD cash value is stated for the grant (checked 2026-09-16).