RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

OpenAI: gpt-oss-20b API pricing

$0.018 per 1M input tokens and $0.09 per 1M output tokens on OpenRouter. Context window: 131,072 tokens.

$0.018input / 1M tokens
$0.09output / 1M tokens
$0.009cached input / 1M
128Kcontext
text->textmodality

What it costs in practice

WorkloadCost
Chatbot: 10,000 messages (1,500 in / 400 out tokens each)$0.630
RAG: 1,000 queries (8,000 in / 600 out each)$0.198
Summarize 100 long documents (50,000 in / 1,000 out each)$0.099

Cross-check against the provider's list price

No first-party entry for this model in LiteLLM's price map, so this price comes from OpenRouter only.

Price history

When (UTC)FieldOldNew
2026-11-17 11:24input$0.03$0.018
2026-11-17 11:24output$0.13$0.09
2026-11-17 11:24cacheRead$0.03$0.009
2026-11-17 12:43input$0.018$0.03
2026-11-17 12:43output$0.09$0.13
2026-11-17 12:43cacheRead$0.009$0.03
2026-11-17 13:28input$0.03$0.018
2026-11-17 13:28output$0.13$0.09
2026-11-17 13:28cacheRead$0.03$0.009

Run it yourself instead

The open weights are on Hugging Face. See the VRAM gpt oss 20b needs and which GPUs fit it →

Cheaper alternatives with similar context

Text models with at least 125K context and a lower blended price (75% input, 25% output). Price only, not a quality ranking.

ModelInput / 1MOutput / 1MContext
Z.ai: GLM 5.3 Flash (batch)$0.024$0.0691M
inclusionAI: Ling 3.0 Flash$0.021$0.063256K
ScaleDown: Summarize$0.04free977K
ScaleDown: Extract$0.04free977K
Mistral: Mistral Nemo$0.029$0.03128K
Meta: Llama 3.1 8B Instruct$0.02$0.04128K
inclusionAI: Ling 3.0 Tiny$0.015$0.045256K

Source: OpenRouter listing via the public models API. Prices checked Nov 17, 2026. Model ID openai/gpt-oss-20b, listed Aug 5, 2025. Report an error.