OpenAI language model

GPT-OSS 20B

GPT-OSS 20B is the smaller of OpenAI's two open-weight reasoning models: 21B parameters with 3.6B active, text input only. it is the low-cost sibling of GPT-OSS 120B and is the GPT-OSS model on the free plan.

01

price

$0.03/M

input tokens

$0.1/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 $0.00014
summarise a 100-page report 50,000 tokens in, 1,500 out, one request $0.0017
1,000 classification calls 500 tokens in, 20 out, per call $0.02
coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache $0.07

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
knowledge cutoff
June 2024
status
live
model id
gpt-oss-20b

integration notes

  • self-hosted weights work correctly only with the harmony response format; raw prompts without it break output.
  • reasoning effort is set in the system prompt (e.g. "Reasoning: high"): low, medium or high.

04

benchmarks

as published by the maker; not measured by octomind.

benchmarkscore
SWE-Bench Verified (high reasoning)source60.7%
GPQA Diamond (no tools, high reasoning)source71.5%
HLE (no tools, high reasoning)source10.9%
AIME 2025 (no tools, high reasoning)source91.7%
Tau-Bench Retail (high reasoning)source54.8%

05

when to pick it

pick it if

  • you want low-cost text work at under a tenth of GPT-OSS 120B input
  • you want Apache 2.0 weights that run within 16GB of memory
  • you want adjustable reasoning effort: low, medium or high

06

where it sits on price

blended price $0.048/M at 3 input tokens per output token: 0 live language models cost less, 43 cost more.

  1. GPT-OSS 20B $0.048/M
  2. Muse Spark 1.3 Contributor $0.125/M
  3. Mercury 3 $0.163/M
  4. MiMo V2.6 Flash $0.175/M
  5. Beam $0.194/M

07

use GPT-OSS 20B 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-20b
switch mid-session
/model octohub:gpt-oss-20b
make it the default — config.toml
[model]
name = "octohub:gpt-oss-20b"

08

compare GPT-OSS 20B

all model comparisons →

09

similar models

nearest live models by listed input price.

view all models →

10

GPT-OSS 20B faq

how much does GPT-OSS 20B cost?

GPT-OSS 20B lists at $0.03/M input, $0.1/M output per 1M tokens. a typical coding-agent session (2M tokens in, 60,000 out) comes to $0.07. 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 20B?

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

does GPT-OSS 20B accept images?

no. GPT-OSS 20B is text-only; pick a vision model from the OpenAI lineup or the catalog for screenshots and diagrams.

is GPT-OSS 20B open source?

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

is GPT-OSS 20B free?

no. GPT-OSS 20B bills per token at $0.03/M input, $0.1/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 20B in octomind?

run octomind login once, then octomind run -m octohub:gpt-oss-20b. inside a running session, /model octohub:gpt-oss-20b switches to it without losing context.

use GPT-OSS 20B in octomind

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