Flash — fastest and cheapest, lighter reasoningCommercial API

gpt-oss-120b (batch) Pricing

OpenAI · openai-gpt-oss-120b-batch

ShareX Facebook LinkedIn

Input / 1M tokens

$0.150

Output / 1M tokens

$0.600

Context window

131,072 tokens

≈ 175 pages of text

Max output

117,964 tokens

What it costs in practice

Typical request (1,200 in + 400 out tokens)$0.0004

1,000 requests / month$0.42/mo 10,000 requests / month$4.20/mo 100,000 requests / month$42.00/mo

Estimate your own workloadOpens the calculator with gpt-oss-120b (batch) preloaded — adjust volume and token counts there.

Price history

Only one price point recorded so far.

The staircase chart appears once a price change is detected.

What it excels at

Handles very large output sequences up to 117k tokens at low per-token cost, suitable for bulk text generation workloads.

The business tradeoff

Batch-only access increases latency and precludes real-time use; open weights origin may show greater variance in complex reasoning than proprietary flagships.

Cheaper from OpenAI

GPT-5.6 Luna (batch)OpenAI$0.0004/ typical request GPT-5.6 Luna Pro (batch)OpenAI$0.0004/ typical request gpt-oss-120bOpenAI$0.0001/ typical request

Same tier from other providers

Claude Haiku 4.5Anthropic$0.0032/ typical request Gemini 3.5 FlashGoogle$0.0054/ typical request Llama 3.3 70BMeta$0.0002/ typical request

Head-to-head

gpt-oss-120b (batch) vs Claude Haiku 4.5 →gpt-oss-120b (batch) vs Gemini 3.5 Flash →gpt-oss-120b (batch) vs Llama 3.3 70B →

Vendor list rates, as of Aug 28, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.