OpenAI GPT-OSS 120B

Open weights

OpenAI GPT-OSS 120B is a language model from OpenAI with a 128K-token context window. Provider list price is $0.15 per million input tokens and $0.60 per million output; on Allocate you pay $0.16 and $0.64 with the 7% transaction fee. The weights are open under Custom license, so you can fine-tune it and own the result.

Route OpenAI GPT-OSS 120B Talk to sales

Pricing

Provider listOn Allocate

Input, per M tokens$0.15$0.16

Output, per M tokens$0.60$0.64

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

Price against its peers

OpenAI GPT-OSS 120B$0.15$0.60

Qwen3.5 9B FP8$0.17$0.25

Llama 4 Scout Instruct (17Bx16E)$0.18$0.59

Qwen3-VL-8B-Instruct$0.18$0.68

Qwen3 235B A22B Instruct 2507 FP8 Throughput$0.20$0.60

Meta Llama 3 8B Instruct Reference$0.20$0.20

Llama Guard 4 12B$0.20$0.20

Qwen2.5 7B Instruct Turbo$0.30$0.30

InputOutput

Provider list prices per M tokens, OpenAI GPT-OSS 120B against its nearest language peers by price.

What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.15 + 350 × $0.60 = $390 a month. Billed on Allocate it is $417.30 with the 7% transaction fee.

OpenAI GPT-OSS 120B is an open-weights model under the Custom license license. Read the license terms once before you build on it; fine-tuned weights on Allocate stay inside your boundary.

Example usage

Point a route at openai/gpt-oss-120b and the endpoint never changes; swap the model behind it whenever you want.

api.allocate.network

curl https://api.allocate.network/v1/chat/completions \
  -H "Authorization: Bearer $ALLOCATE_KEY" \
  -d '{
    "model": "openai/gpt-oss-120b",
    "messages": [{"role": "user",
      "content": "Summarise the attached contract."}]
  }'

200 · openai/gpt-oss-120b · inside your boundary

Common questions

How much does OpenAI GPT-OSS 120B cost per million tokens?

Provider list price is $0.15 per million input tokens and $0.60 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.16 in and $0.64 out.

What context window does OpenAI GPT-OSS 120B have?

131,072 tokens (128K). At roughly 0.75 words per token, that is about 98k words of English text per request.

Can I fine-tune OpenAI GPT-OSS 120B?

Yes. OpenAI GPT-OSS 120B is an open-weights model under the Custom license license. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.

How do I call OpenAI GPT-OSS 120B on Allocate?

Send openai/gpt-oss-120b in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.