NewHow we catch a seller listing the wrong model, and refund you if one does.

What is an LLM gateway?

An LLM gateway is a single API in front of many model providers: applications use one key and base URL, and the gateway picks the provider, retries failures and handles billing. MartLLM is an OpenAI- and Anthropic-compatible LLM gateway. On November 20, 2026, one MartLLM API key reaches 223 chat, 89 image and 152 video models a request can use now. MartLLM handled 4,101,798 billed requests in the 30 days before. Requests that fail are not billed, and MartLLM adds no fee to provider prices.

Prices as of November 20, 2026, 11:00 UTC. This page is rebuilt every hour.

Against other providers: Best OpenRouter alternatives (November 2026)

ModelInput / 1M tokensOutput / 1M tokensBelow list price
GPT-OSS 20B$0.000018$0.00008999.9%
GPT-OSS 120B$0.000069$0.00029799.9%
GPT OSS Safeguard 20B$0.000075$0.000399.9%
Qwen: Qwen3.8 Omni Flash$0.000146$0.00045699.9%
GLM 4.5 Air$0.000129$0.00084299.9%
Voxtral Mini 3B 2507$0.0004$0.000499%
Gemma 3 4B IT$0.000463$0.00057999%
Gemma 4 E2B$0.0004$0.000899%
MiniMax M2.1$0.000356$0.00143
Gemma 3 12B IT$0.000495$0.0014999.2%
GLM 4.7 Flash$0.000326$0.00299.5%
Gemma 4 26B A4B IT$0.0008$0.00199.2%

MartLLM adds no fee to these prices · every model and price →

More questions

Why use an LLM gateway?

A gateway replaces separate provider accounts and keys with one, retries a call that fails before the provider starts answering, and lets you change models by changing the model id.

How are requests priced?

A request costs what its provider charged for it, and every request is listed with its cost in Activity. MartLLM adds no fee to provider prices; a card fee of 5.5% + $0.50 is added when you add credit.