gpt-oss-120b (high) API Pricing

OpenAI · released 2025-08-05 · merges 2 reasoning-effort tiers

Benchmarks shown for the highest-scoring reasoning tier. Merged tiers: gpt-oss-120b (high), gpt-oss-120b (low).

Pricing

$0.15
input / 1M tokens
0.015¢ / 1K
$0.595
output / 1M tokens
0.059¢ / 1K
$0.261
blended / 1M tokens
0.026¢ / 1K

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.0253¢
RAG query4,000 in / 500 out0.0897¢
Long document summary50,000 in / 1,000 out0.809¢
Code review of a 2k-line file30,000 in / 2,000 out0.569¢
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$7.60

Cost = (input tokens ÷ 1,000,000 × $0.15) + (output tokens ÷ 1,000,000 × $0.595).

Benchmarks

11.6
Intelligence
#228 of 533
30.4
Coding
#112 of 197
93.4
Math
#14 of 249
214
Tokens/sec
0.52s
Time to first token

Similar intelligence, lower price

ModelIntelligenceBlended $/1M
Gemma 4 E4B (Reasoning)8.9$0.04
Granite 4.2 3B9.1$0.052
Qwen3.5 4B (Reasoning)13.1$0.06
Sarvam 105B (high)8.8$0.074
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)8.9$0.088

Leaderboard neighbours

ModelIntelligenceBlended $/1M
HyperNova 60B 2605 (high, based on gpt-oss-120b)11.7
MiniMax M1 80k11.7$0.963
Nemotron Cascade 2 30B A3B11.7
gpt-oss-120b (high)11.6$0.261
K2 Think V211.5
LongCat Flash Lite11.5
DeepSeek R1 (Jan '25)11.4$2.50

More from OpenAI

ModelIntelligenceBlended $/1M
GPT-6 Astra (max)52.7$20.00
GPT-5.6 Sol (max)47.0$8.00
GPT-5.6 Terra (max)42.1$4.50
GPT-5.4 (xhigh)39.0$5.625
GPT-5.5 (xhigh)38.4$11.25
GPT-5.6 Luna (max)37.3$0.45
GPT-5.3 Codex (xhigh)32.5$4.813
GPT-5.2 (xhigh)30.4$4.813

Count tokens & estimate cost for gpt-oss-120b (high) See gpt-oss-120b (high) on the leaderboard

Source: Artificial Analysis · last synced 2026-09-22

FAQ

Who develops gpt-oss-120b (high)?

gpt-oss-120b (high) is developed by OpenAI, released 2025-08-05.

How much does gpt-oss-120b (high) cost per million tokens?

gpt-oss-120b (high) costs $0.15 per 1M input tokens and $0.595 per 1M output tokens ($0.261 blended), per Artificial Analysis's official pricing data.

How does gpt-oss-120b (high) rank on benchmarks?

gpt-oss-120b (high) scores 11.6 on the Artificial Analysis Intelligence Index, ranking #228 of 533 models we track.

Is there a cheaper model with similar intelligence to gpt-oss-120b (high)?

Yes — Gemma 4 E4B (Reasoning) scores similar intelligence (8.9) at $0.04/1M blended, versus $0.261/1M for gpt-oss-120b (high).

Where does this data come from?

Pricing and benchmark data for gpt-oss-120b (high) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.