OPENAI · SERVERLESS AND DEDICATED · LIVE

gpt-oss-120b

OpenAI's open-weight 117B mixture of experts, the catalog's default for production chat, streamed byte for byte.

131K

TOKEN CONTEXT

$0.0225

INPUT, PER MILLION

$0.1275

OUTPUT, PER MILLION

Streamed

BYTE FOR BYTE, NO BUFFER

Overview

gpt-oss-120b is OpenAI's larger open-weight model, a mixture of experts with 117B total parameters and 5.1B active per token, released under Apache 2.0. The sparse activation is what makes the economics work: flagship-adjacent quality at a per-token cost closer to a small model, and output priced well under the median listing for its class.

It is the model most teams standardize on for production chat, and the same properties carry to synthetic data generation and agent loops that burn tokens all day. The 131,072-token window covers long conversations and tool transcripts without pruning, and the weights make a clean fine-tune base for dedicated deployments.

Serving on Nyx

Every response streams byte for byte from the first token the engine produces, with nothing buffering chunks between the engine and your socket. When demand exceeds declared capacity the API answers 429 immediately with a Retry-After header rather than parking your request in a queue.

The prefix cache persists across turns, cutting 31 percent of prefill work on agent traces, which matters at this model's request volumes. Dedicated pods pin capacity with guaranteed throughput at a flat hourly price.

Provider A303
Provider B221

OUTPUT PRICE · $/M · LOWER IS BETTER

Nyx$0.1275
Provider A$0.17
Provider B$0.204

Independent harness · run weekly · streamed

Nyx$0.0225$0.1275388
Provider A$0.03$0.17303
Provider B$0.036$0.204221
# OpenAI-compatible: swap the base URL
curl https://api.nyxprovider.com/v1/chat/completions \
  -H "Authorization: Bearer $NYX_API_KEY" \
  -d '{
    "model": "gpt-oss-120b",
    "stream": true,
    "messages": [{"role": "user",
      "content": "Draft a support reply for this delayed order."}]
  }'
CONTEXT131,072 tokens
INPUT$0.0225 / M tokens
OUTPUT$0.1275 / M tokens
STREAMINGByte for byte, no buffer
PARAMETERS117B total · 5.1B active
MODALITYText in · text out
LICENSEApache 2.0
DEPLOYMENTServerless · Dedicated
APIOpenAI-compatible
CATALOG

All models in the library