Inference pricing

Pay per token, nothing else

Five production models on one OpenAI-compatible endpoint. Every rate below is per million tokens: no hourly GPU rental, no reserved capacity, no minimum spend.

  • Billed per 1M tokens
  • Cached input discounts
  • Streaming included
  • No minimum spend

Rates per 1M tokens

One rate card for every request: streaming or not, tools or not. Cached input is the rate for prompt prefixes served from cache.

ModelContextInputCached inputOutput
GPT-OSS 120Bopenrelay/gpt-oss-120b128K$0.15$0.015$0.60
GPT-OSS 20Bopenrelay/gpt-oss-20b128K$0.05$0.005$0.20
Gemma 4 31Bopenrelay/gemma-4-31b32K$0.99n/a$1.49
Gemma 4 31B NVFP4 32Kopenrelay/gemma-4-31b-nvfp4-32k32K$0.12n/a$0.35
GLM 5.2openrelay/glm-5.21M$1.82$0.338$5.72
DeepSeek-OCR 2openrelay/deepseek-ocr-28K$0.039n/a$0.039

All prices in USD per 1M tokens. You pay only for the tokens you use, metered per request. More models are on the way; browse the inference catalog or request a model.

The models behind the rates

GPT-OSS 120B

OpenAI

Most popular
Context
128K
Parameters
120B
Input / 1M
$0.15
Output / 1M
$0.60

OpenAI's largest open-weight model. Strong general reasoning with native tool calling and structured output. The default choice when you want frontier-class quality on an open model.

TextReasoningCode

GPT-OSS 20B

OpenAI

Best value
Context
128K
Parameters
20B
Input / 1M
$0.05
Output / 1M
$0.20

The lightweight GPT-OSS variant. Fast responses at a fraction of the cost, with the same tool calling and JSON mode. Built for high-volume, latency-sensitive traffic.

TextCode

Gemma 4 31B

Google

Vision
Context
32K
Parameters
31B
Input / 1M
$0.99
Output / 1M
$1.49

Google's dense 31B model. Reads text and images, runs built-in reasoning, and calls tools natively, with a 32K-token context window.

TextVisionReasoning

Gemma 4 31B NVFP4 32K

Google

Best value
Context
32K
Parameters
31B
Input / 1M
$0.12
Output / 1M
$0.35

NVFP4-quantized Gemma 4 31B for low-latency serving at 32K context. Vision, reasoning, and native tool calling at a fraction of the full-precision rate.

TextVisionReasoning

GLM 5.2

Zhipu

Reasoning
Context
1M
Parameters
744B MoE
Input / 1M
$1.82
Output / 1M
$5.72

Zhipu's frontier GLM model. Long-form reasoning, coding, and agentic tool use across English and Chinese, with a 1M-token context window for whole-codebase and document workloads.

TextReasoningCode

DeepSeek-OCR 2

DeepSeek

OCR
Context
8K
Parameters
-
Input / 1M
$0.039
Output / 1M
$0.039

DeepSeek's second-generation OCR model. Reads document images (scans, receipts, screenshots, tables) and returns structured markdown that preserves headings, tables, and layout.

Vision

How billing works

Metered per request, itemized per token

Cached input

Prompt prefixes served from cache bill at the cached input rate: 10x cheaper than fresh input on GPT-OSS models. It applies automatically, with no configuration.

Everything included

Streaming, tool calls, vision input, and JSON mode cost nothing extra. Every request is metered on tokens in and tokens out, at the rates above.

Batch at 50% off

Large offline jobs can run on the Batch Inference API at half the per-token rate, with results delivered within 24 hours.

Send your first request today

Grab an API key, point your OpenAI SDK at OpenRelay, and pay only for what you run.