GPT OSS 120B pricing & specs
OpenAI · released 2025-08-05 · ● verified 2026-10-11
input / 1M$0.05via Novita AI
output / 1M$0.25via Novita AI
context131.1K
max output32.8K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs GPT OSS 120B |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −50% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −45% |
| Qwen Turbo | $0.05 | $0.20 | 1M | −12.5% |
| DeepSeek V4 Flash 0731 | $0.06 | $0.18 | 1.05M | −10% |
| GPT OSS Safeguard 20B | $0.07 | $0.20 | 128K | +2.5% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Novita AI | $0.05 | $0.25 |
| Google Vertex AI | $0.09 | $0.36 |
| Amazon Bedrock | $0.15 | $0.60 |
| Groq | $0.15 | $0.60 |
| Cerebras | $0.35 | $0.75 |
| Cloudflare Workers AI | $0.35 | $0.75 |
// faq
How much does GPT OSS 120B cost?
GPT OSS 120B costs $0.05 per million input tokens and $0.25 per million output tokens (cheapest tracked host: Novita AI). At 50M input and 10M output tokens per month that is about $5.00.
What is the context window of GPT OSS 120B?
131.1K tokens, with up to 32.8K output tokens per request.
What are cheaper alternatives to GPT OSS 120B?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out) offer the same input types and capabilities for less.
Is GPT OSS 120B open weights?
Yes. It is available from 6 tracked hosts; the cheapest is Novita AI at $0.05 input and $0.25 output per million tokens.
// spec sheet
- input / 1M
- $0.05
- output / 1M
- $0.25
- blended (3:1)
- $0.10
- context
- 131.1K
- max output
- 32.8K
- input types
- text
- reasoning
- yes
- tool calling
- yes
- structured output
- yes
- open weights
- yes
- knowledge cutoff
- n/a
- price source
- Novita AI
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Qwen Turbo | $0.05 | $0.20 | $4.50 |
| GPT OSS 120B | $0.05 | $0.25 | $5.00 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.