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.
| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| GPT-OSS 120Bopenrelay/gpt-oss-120b | 128K | $0.15 | $0.015 | $0.60 |
| GPT-OSS 20Bopenrelay/gpt-oss-20b | 128K | $0.05 | $0.005 | $0.20 |
| Gemma 4 31Bopenrelay/gemma-4-31b | 32K | $0.99 | n/a | $1.49 |
| Gemma 4 31B NVFP4 32Kopenrelay/gemma-4-31b-nvfp4-32k | 32K | $0.12 | n/a | $0.35 |
| GLM 5.2openrelay/glm-5.2 | 1M | $1.82 | $0.338 | $5.72 |
| DeepSeek-OCR 2openrelay/deepseek-ocr-2 | 8K | $0.039 | n/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
- 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.
GPT-OSS 20B
OpenAI
- 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.
Gemma 4 31B
- 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.
Gemma 4 31B NVFP4 32K
- 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.
GLM 5.2
Zhipu
- 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.
DeepSeek-OCR 2
DeepSeek
- 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.
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.