|
Halva · The unified AI gateway
One clean API for 400+ models. Halva routes every request through a single endpoint at wholesale rates, with every token accounted for. No subscriptions, no...
|
85 % |
|
What’s the Token?
What’s the Token is a provenance-backed registry of AI inference prices.
|
83 % |
|
akrouter · Multi-provider LLM API platform
Connect Claude Code, Codex, and Gemini CLI to a multi-provider LLM API platform with one base_url. Suppliers compete on each model, failover is automatic, an...
|
82 % |
|
Draupnir — cut the token bill, keep the performance
Draupnir serves open-weight models through lower-cost API endpoints, tuned per accelerator without changing the weights.
|
82 % |
|
WeCoding Console
WeCoding user console
|
82 % |
|
OpenFill: the open market for LLM inference
OpenAI-compatible inference priced by a live market. You name a price limit and pay the clearing level your request executes at. No order is rejected on price.
|
82 % |
|
lowcostllm: frontier models at half price
Claude and GPT, through the official APIs, at up to 50% off list. Not a Chinese model, not a proxy to one. Change one line and keep everything else.
|
82 % |
|
TokenMercato — an order book for LLM compute
A live order book that matches idle GPUs with inference demand. Providers post asks, buyers post bids, and every filled token is metered by the venue.
|
82 % |
|
Tokenulator — compare model prices side by side
Compare AI model token prices head to head: rates, your estimated cost, and price history for up to four models at once.
|
82 % |
|
Token Broker — The cheapest inference for every frontier model
A live market for AI tokens. Every request fills at the lowest verified offer. OpenAI-compatible.
|
82 % |
|
Kyma API: AI models for your app, one account
Use chat, reasoning, image and audio models with one account and balance. Compare real prices and measured uptime. OpenAI- and Anthropic-compatible APIs.
|
81 % |
|
usepod.ai — The inference marketplace built for agents
Route OpenAI- and Anthropic-compatible requests to the best-priced available provider, with transparent centralized fallback. Pay by card, USDC balance, or p...
|
81 % |
|
Agent Terminal
자연어로 시세 조회·스왑·포트폴리오를 처리하는 AI 에이전트 터미널
|
81 % |
|
Lucenta.ai — All the best models. One API. Lower costs.
Access GPT, Claude, and Gemini through one OpenAI-compatible API. Prepaid credits and savings vs official list prices. Swap your base URL — keep your code.
|
81 % |
|
VORQ – An exchange for inference
Vetted, top-tier providers compete on price to run your workload. Up to 80% cheaper for the same open-weight models – LLMs and generative diffusion models fo...
|
81 % |
|
BlazeRail — One API for every model
One API for every model, and your OpenAI code already works with it. Change the base URL and keep everything else. Each request goes to the cheapest provider...
|
80 % |
|
Vynaris — same quality, a fraction of the cost
Cut AI costs drastically without compromising on privacy or reliability. Vynaris routes each request to the cheapest model that clears your quality bar.
|
80 % |
|
Odasher — Inference priced by the second
Inference prices that follow available GPU capacity. Odasher is building second-by-second pricing and routing to lower costs, shorten queues, and keep provid...
|
80 % |
|
Aigenway
Single API gateway over external AI providers.
|
80 % |
|
TokenAIRouter — One endpoint for every model
|
80 % |
Detected social media networks