GPT OSS 20B

Low-latency reasoning on a tiny budget

Chat
Thinking
JSON Mode
Tool Calling

Pricing

Run instantly. Pay only for what you use.

Input
$0.02/ M
Output
$0.10/ M
Cache read
$0.005/ M

About GPT OSS 20B

GPT OSS 20B is OpenAI's compact open-weight reasoning model, released under Apache 2.0: a 21B-parameter MoE with 3.6B active per token and a 131K-token context window, trained on the Harmony response format with configurable reasoning effort — low, medium, or high.

It is the price-performance floor for real reasoning: at high effort it reaches 98.7% on AIME 2025 (with tools) and 71.5% on GPQA — OpenAI's published evals put it near o3-mini — from a model small enough to run on 16GB devices.

That makes structured work cheap: Harmony-trained function calling and strict JSON output with top-15 output speed among the open models measured by Artificial Analysis.

3.6Bactive of 21B total

MoE routing delivers real reasoning at the smallest serving footprint.

3reasoning effort levels

Low, medium, and high — accuracy scales smoothly as effort rises.

131Ktoken context window

Long documents and full tool-call transcripts fit in a single request.

Key capabilities

GPT OSS 20B is strongest where volume and latency dominate — classification, routing, extraction, and assistant backends that need reasoning quality without reasoning prices.

Configurable reasoning effort

A one-line system-message setting trades latency for depth — smooth accuracy scaling across low, medium, and high.

Competition-grade math

98.7% on AIME 2025 with tools at high effort — from a model that fits on 16GB devices.

Fast structured output

Harmony-trained function calling and strict JSON — tool arguments that parse the first time, at top-15 open-model speed.

Escalation-ready

Shares the Harmony format with GPT OSS 120B — route hard requests up without changing your integration.

Where this model fits

Best for
  • High-volume classification and routing

    Reasoning quality where rule-based systems fail, at a price point that survives millions of calls.

  • Structured extraction with strict schemas

    Harmony-trained function calling and JSON output that parse the first time.

  • Latency-sensitive assistants

    Top-15 output speed on Artificial Analysis with sub-second first tokens.

  • Escalation-tier architectures

    Serve the routine calls here and escalate hard ones to GPT OSS 120B — same Harmony format, drop-in swap.

Avoid for
  • Repo-scale coding agents

    Multi-file engineering is beyond a 3.6B-active model — use DeepSeek V4 Flash or Qwen 3.6 27B for issue-to-patch work.

  • Knowledge-heavy answers without retrieval

    Compact models trail on knowledge-intensive tasks — pair it with RAG for factual workloads.

  • Image, audio, or video inputs

    GPT OSS 20B is text-only. Route visual inputs to a multimodal model such as Gemma 4 26B A4B.

Performance and
benchmarks

Entrim performance for GPT OSS 20B under production load in the past few days.

Throughput (tokens / sec)

avg. 314tokens/s

Time to first token (TTFT)

avg. 350ms

Public model benchmarks

98.7%AIME 2025 (with tools)

Competition mathematics measuring multi-step reasoning.

71.5%GPQA

Graduate-level scientific reasoning and analysis.

165tokens/s (Artificial Analysis)

Top-15 fastest of the 130 open models measured.

Run GPT OSS 20B in minutes

Test this model with $25 free credit. Use Entrim's OpenAI-compatible API to call GPT OSS 20B, compare output quality, latency, and request cost, then decide if it fits your workload.

Code examples

curl -X POST "https://api.entrim.ai/v1/chat/completions" \  -H "Content-Type: application/json" \  -H "Authorization: Bearer $ENTRIM_API_KEY" \  -d '{    "model": "openai/gpt-oss-20b",    "messages": [      {        "role": "user",        "content": "Why do they call it a building if it is already built?"      }    ]  }'

SDKs & docs

Use familiar SDK patterns with quickstart examples for common production setups.

OpenAI-compatible

Keep the request format your team already knows.

No cold starts

Production requests are served without model spin-up delays.

Not sure this is the right model?

Explore related models that may be a better fit for your workload.

o4-mini-class reasoning for tool-driven coding

131.1K
FP4
Thinking
Input / M
$0.029
Output / M
$0.13
Cached / M
$0.01

Tool-heavy coding at 3B-active cost

262K
FP8
Vision
Multimodal
Video
Input / M
$0.05
Output / M
$0.25
Cached / M
$0.025

Gemma 4 quality at 4B-active speed

256K
FP8
Vision
Multilingual
Input / M
$0.05
Output / M
$0.25
Cached / M
$0.025

Run GPT OSS 20B with the Most Cost-Effective LLM Inference

Use $25 free credits to test prompts, token sizes, latency, throughput, output quality, and request cost before moving traffic.
All services are online

© 2026. Entrim. All Rights Reserved.

Privacy policyTerms of service