OpenAI GPT-OSS 20B

Open weights

OpenAI GPT-OSS 20B is a language model from OpenAI with a 128K-token context window. Provider list price is $0.05 per million input tokens and $0.20 per million output; on Allocate you pay $0.053 and $0.21 with the 7% transaction fee. The weights are open under Apache 2.0, so you can fine-tune it and own the result.

Route OpenAI GPT-OSS 20B Talk to sales

Pricing

Provider listOn Allocate

Input, per M tokens$0.05$0.053

Output, per M tokens$0.20$0.21

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

Price against its peers

LFM2.5-8B-A1B$0.03$0.12

Trinity Mini$0.045$0.15

OpenAI GPT-OSS 20B$0.05$0.20

Nvidia Nemotron Nano 9B V2$0.06$0.25

Gemma 3N E4B Instruct$0.06$0.12

Arize AI Qwen 2 1.5B Instruct$0.10$0.10

Meta Llama 3 8B Instruct Lite$0.14$0.14

DeepSeek R1 Distill Qwen 1.5B$0.18$0.18

InputOutput

Provider list prices per M tokens, OpenAI GPT-OSS 20B 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 × $0.05 + 350 × $0.20 = $130 a month. Billed on Allocate it is $139.10 with the 7% transaction fee.

OpenAI GPT-OSS 20B is an open-weights model under the Apache 2.0 license. Fine-tune it on your own data and the weights stay inside your boundary; they belong to you.

Example usage

Point a route at openai/gpt-oss-20b 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-20b",
    "messages": [{"role": "user",
      "content": "Summarise the attached contract."}]
  }'

200 · openai/gpt-oss-20b · inside your boundary

Common questions

How much does OpenAI GPT-OSS 20B cost per million tokens?

Provider list price is $0.05 per million input tokens and $0.20 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.053 in and $0.21 out.

What context window does OpenAI GPT-OSS 20B 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 20B?

Yes. OpenAI GPT-OSS 20B is an open-weights model under the Apache 2.0 license. The license is permissive, so the fine-tuned weights are yours to use commercially. On Allocate the trained weights stay inside your boundary and belong to you.

How do I call OpenAI GPT-OSS 20B on Allocate?

Send openai/gpt-oss-20b 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.