GPT OSS 120B
OpenAI • API Price Comparison
GPT OSS 120B is a large language model by OpenAI with a 131K-token context window. Across the 4 API channels tracked here, input pricing ranges from $0.15–$0.15 per 1M input tokens (USD-normalized); the cheapest is XycAi at ¥1.01 per 1M input tokens. Channels reachable from mainland China without a VPN include XycAi. Prices are collected daily from official provider pages and every tracked channel, then cross-checked by a data-accuracy audit.
Model performance benchmarks
Scores retain their original benchmark, version and metric. We do not combine them into a site-wide score; results from different versions are not directly comparable.
| Channel | Type | Input / 1M | Output / 1M | Rate Limit | China | vs Official | |
|---|---|---|---|---|---|---|---|
XycAi💰 Best Price | 转售商 | ¥1.01 | ¥4.06 | - | - | ||
Together AI | 聚合平台 | $0.15 | $0.60 | - | - | - | |
Fireworks AI | 聚合平台 | $0.15 | $0.60 | - | - | - | |
OpenRouter20 variants | 聚合平台 | $0.15 | $0.60 | - | - | - | |
Show all price variants for this channelOpenRouter Auto / default routeDefault $0.15 / $0.60 per 1M default_route AkashML | openai/gpt-oss-120b $0.03 / $0.17 per 1M upstream_provider CoreWeave | openai/gpt-oss-120b $0.03 / $0.17 per 1M upstream_provider DekaLLM | openai/gpt-oss-120b $0.03 / $0.18 per 1M upstream_provider DeepInfra | openai/gpt-oss-120b $0.04 / $0.17 per 1M upstream_provider Crusoe | openai/gpt-oss-120b $0.05 / $0.25 per 1M upstream_provider Mancer 2 | openai/gpt-oss-120b $0.05 / $0.30 per 1M upstream_provider DigitalOcean | openai/gpt-oss-120b $0.06 / $0.42 per 1M upstream_provider Parasail | openai/gpt-oss-120b $0.10 / $0.75 per 1M upstream_provider BaseTen | openai/gpt-oss-120b $0.10 / $0.50 per 1M upstream_provider SambaNova | openai/gpt-oss-120b $0.14 / $0.95 per 1M upstream_provider Amazon Bedrock | openai/gpt-oss-120b $0.15 / $0.60 per 1M upstream_provider DeepInfra | openai/gpt-oss-120b $0.15 / $0.60 per 1M upstream_provider Together | openai/gpt-oss-120b $0.15 / $0.60 per 1M upstream_provider Nebius | openai/gpt-oss-120b $0.15 / $0.60 per 1M upstream_provider Groq | openai/gpt-oss-120b $0.15 / $0.60 per 1M upstream_provider Amazon Bedrock | openai/gpt-oss-120b $0.15 / $0.60 per 1M upstream_provider SiliconFlow | openai/gpt-oss-120b $0.15 / $0.60 per 1M upstream_provider DeepInfra | openai/gpt-oss-120b $0.20 / $0.95 per 1M upstream_provider Cerebras | openai/gpt-oss-120b $0.35 / $0.75 per 1M upstream_provider | |||||||
| Usage Level | Tokens/Month | XycAi | Together AI | Fireworks AI | OpenRouter |
|---|---|---|---|---|---|
| 🐣 Light | 0.1M in + 0.1M out | $0.04 | $0.05 | $0.05 | $0.05 |
| 📊 Medium | 1.0M in + 0.5M out | $0.44 | $0.45 | $0.45 | $0.45 |
| 🚀 Heavy | 10.0M in + 5.0M out | $4.41 | $4.50 | $4.50 | $4.50 |
| 🏢 Enterprise | 100.0M in + 50.0M out | $44.10 | $45.00 | $45.00 | $45.00 |
Frequently asked questions about gpt-oss-120b
What is the cheapest API provider for GPT OSS 120B?
Of the channels tracked here, XycAi is the cheapest at ¥1.01 per 1M input tokens and ¥4.06 per 1M output tokens (about $0.15 per 1M input). Confirm on the provider's page; figures are updated daily.
Can I use GPT OSS 120B from mainland China?
Yes — these channels are directly reachable from mainland China without a VPN: XycAi. Domestic channels generally support Alipay/WeChat Pay.
What is the context window of GPT OSS 120B?
GPT OSS 120B offers a 131,072-token context window.
How often are GPT OSS 120B prices updated, and how reliable is the data?
Prices are scraped daily from official pricing pages and every tracked channel, with every significant change recorded in a price-history log. A daily read-only data audit cross-checks each channel against the model producer's published price and flags stale or inconsistent rows for correction.