OpenAI language model

GPT-OSS 120B

GPT-OSS 120B is the larger of OpenAI's two Apache 2.0 open-weight models, with 117B total and 5.1B active parameters. it takes text only and sits above the cheaper GPT-OSS 20B.

01

price

$0.35/M

input tokens

$0.75/M

output tokens

per 1M tokens. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).

02

what real work costs

workloadcost
one chat reply 3,000 tokens in, 500 out $0.0014
summarise a 100-page report 50,000 tokens in, 1,500 out, one request $0.02
1,000 classification calls 500 tokens in, 20 out, per call $0.19
coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache $0.75

at the listed rate. token counts are typical sizes, not measurements.

03

specs

provider
OpenAI
context window
128k tokens — ≈ 190 pages of prose or 13,000 lines of code
input
text
output
text
structured output
yes — JSON schema
reasoning mode
yes
weights
open — Apache 2.0
released
August 5, 2025
knowledge cutoff
June 2024
status
live
model id
gpt-oss-120b

integration notes

  • reasoning effort is low, medium or high, set in the system prompt, for example "Reasoning: high".
  • self-hosted weights only work correctly with OpenAI's harmony response format; calling generate directly means applying harmony yourself.
  • the full chain-of-thought is returned, but OpenAI says it is not intended to be shown to end users.

04

benchmarks

as published by the maker; not measured by octomind.

benchmarkscore
SWE-Bench Verified (high reasoning)source62.4%
GPQA Diamond (no tools, high reasoning)source80.1%
HLE (no tools, high reasoning)source14.9%
AIME 2025 (no tools, high reasoning)source92.5%
Tau-Bench Retail (high reasoning)source67.8%

05

when to pick it

pick it if

  • you want Apache 2.0 open weights you could also self-host
  • you need adjustable reasoning effort: low, medium or high
  • you need function calling and structured outputs from an open model

06

where it sits on price

blended price $0.45/M at 3 input tokens per output token: 11 live language models cost less, 32 cost more.

  1. GLM-5.3 Flash $0.237/M
  2. MiniMax M3.1 Flash $0.262/M
  3. GPT-OSS 120B $0.45/M
  4. Inkling 2 Small $0.475/M
  5. DeepSeek V4.1 Flash $0.525/M

07

use GPT-OSS 120B in octomind

one octohub login reaches every model in the catalog. pick this one per run, per session, or as your default.

run it
octomind login
octomind run -m octohub:gpt-oss-120b
switch mid-session
/model octohub:gpt-oss-120b
make it the default — config.toml
[model]
name = "octohub:gpt-oss-120b"

08

compare GPT-OSS 120B

all model comparisons →

09

similar models

nearest live models by listed input price.

view all models →

10

GPT-OSS 120B faq

how much does GPT-OSS 120B cost?

GPT-OSS 120B lists at $0.35/M input, $0.75/M output per 1M tokens. a typical coding-agent session (2M tokens in, 60,000 out) comes to $0.75. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).

what is the context window of GPT-OSS 120B?

128k tokens, ≈ 190 pages of prose or 13,000 lines of code.

does GPT-OSS 120B accept images?

no. GPT-OSS 120B is text-only; pick a vision model from the OpenAI lineup or the catalog for screenshots and diagrams.

is GPT-OSS 120B open source?

its weights are open under Apache 2.0, so it can also be self-hosted.

when was GPT-OSS 120B released?

August 5, 2025, by OpenAI.

is GPT-OSS 120B free?

no. GPT-OSS 120B bills per token at $0.35/M input, $0.75/M output per 1M. octomind's free plan reaches it pay as you go from credits, so you pay only for the tokens you use, at the provider price. credits carry a 3% top-up fee.

how do i use GPT-OSS 120B in octomind?

run octomind login once, then octomind run -m octohub:gpt-oss-120b. inside a running session, /model octohub:gpt-oss-120b switches to it without losing context.

use GPT-OSS 120B in octomind

choose a model when you start, then switch mid-session when the work changes.