ModelBench
OpenAI logo
Models/OpenAI

GPT OSS 20B

Open GPT reasoning model for self-hosted agents and controllable deployments

Source-linked gpt-oss Open weights Released 2025-08-05
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.03/1M tokens
Output price$0.13/1M tokens
Context window131.072K
Max output32.768K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
✓ Open weights Yes
Creator
OpenAI
Model family
gpt-oss
Knowledge cutoff
Not documented
License
Not documented
Release date
2025-08-05
Model ID
openai/gpt-oss-20b
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering GPT OSS 20B
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
LMStudio openai/gpt-oss-20b 131.072K Not listed Not listed - ReasoningTools Docs
Kenari gpt-oss-20b 131.072K Not listed Not listed - ReasoningTools Docs
Nvidia openai/gpt-oss-20b 131.072K Not listed Not listed - ReasoningToolsJSON Docs
Deep Infra openai/gpt-oss-20b 131.072K $0.03 $0.14 - ReasoningToolsJSON Docs
IO.NET openai/gpt-oss-20b 64K $0.03 $0.14 $0.015 Tools Docs
Weights & Biases openai/gpt-oss-20b 131.072K $0.03 $0.13 $0.03 ReasoningToolsJSON Docs
Kilo Gateway openai/gpt-oss-20b 131.072K $0.03 $0.14 - ReasoningTools Docs
OpenRouter openai/gpt-oss-20b 131.072K $0.03 $0.13 $0.03 ReasoningToolsJSON Docs
NovitaAI openai/gpt-oss-20b 131.072K $0.04 $0.15 - ReasoningJSON Docs
LLM Gateway gpt-oss-20b 131.072K $0.04 $0.15 - ReasoningToolsJSON Docs
SiliconFlow openai/gpt-oss-20b 131K $0.04 $0.18 - ToolsJSON Docs
NanoGPT openai/gpt-oss-20b 128K $0.04 $0.15 - Reasoning Docs
Merge Gateway openai/gpt-oss-20b 131.072K $0.04 $0.2 $0.02 Reasoning Docs
Clarifai openai/chat-completion/models/gpt-oss-20b 131.072K $0.045 $0.18 - ReasoningTools Docs
Vercel AI Gateway openai/gpt-oss-20b 131.072K $0.05 $0.2 - ReasoningToolsJSON Docs
Together AI openai/gpt-oss-20b 131.072K $0.05 $0.2 - ReasoningToolsJSON Docs
Databricks databricks-gpt-oss-20b 131.072K $0.05 $0.2 - ReasoningToolsJSON Docs
FastRouter openai/gpt-oss-20b 131.072K $0.05 $0.2 - ReasoningTools Docs
Neon gpt-oss-20b 131.072K $0.05 $0.2 - ReasoningToolsJSON Docs
Fireworks AI accounts/fireworks/models/gpt-oss-20b 131.072K $0.07 $0.3 $0.035 ReasoningTools Docs
Pioneer openai/gpt-oss-20b 131.072K $0.07 $0.3 $0.035 ReasoningToolsJSON Docs
FrogBot gpt-oss-20b 131.072K $0.07 $0.2 - ReasoningToolsJSON Docs
Vertex openai/gpt-oss-20b-maas 131.072K $0.07 $0.25 - ReasoningTools Docs
Groq openai/gpt-oss-20b 131.072K $0.075 $0.3 $0.037 ReasoningToolsJSON Docs
Hugging Face openai/gpt-oss-20b 131.072K $0.1 $0.5 - ReasoningToolsJSON Docs
STACKIT openai/gpt-oss-20b 131.072K $0.18 $0.29 - ReasoningTools Docs
Cloudflare Workers AI @cf/openai/gpt-oss-20b 128K $0.2 $0.3 - ReasoningToolsJSON Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
Agentic Index - Unversioned - indexTop 8 reported models
Claude Opus 5
55.3
GPT-5.6 Sol
54.0
Anthropic: Claude Fable 5 (batch)
52.8
Claude Fable 5
52.8
Kimi K3
50.1
GPT-5.6 Terra
47.4
Anthropic: Claude Opus 4.8 (batch)
47.2
GPT OSS 20B
3.1
Coding Index - Unversioned - indexTop 8 reported models
Claude Opus 5
78.0
GPT-5.6 Sol
77.4
GPT-5.6 Terra
76.7
Anthropic: Claude Fable 5 (batch)
76.5
Claude Fable 5
76.5
Kimi K3
76.2
OpenAI: GPT-5.5 (batch)
74.9
GPT OSS 20B
20.7
Design Arena: dataviz - Unversioned - eloTop 8 reported models
Kimi K3
1382.0
Claude Opus 5
1378.0
Z.ai: GLM 5.1
1366.0
Google: Gemini 3.6 Flash (batch)
1350.0
Gemini 3.6 Flash
1350.0
Anthropic: Claude Fable 5 (batch)
1349.0
Claude Fable 5
1349.0
GPT OSS 20B
963.0
Design Arena: website - Unversioned - eloTop 8 reported models
Kimi K3
1375.0
Claude Opus 5
1343.0
Z.ai: GLM 5.2
1340.0
Anthropic: Claude Fable 5 (batch)
1323.0
Claude Fable 5
1323.0
xAI: Grok 4.5
1323.0
Google: Gemini 3.6 Flash (batch)
1322.0
GPT OSS 20B
877.0
Intelligence Index - Unversioned - indexTop 8 reported models
Claude Opus 5
60.7
Anthropic: Claude Fable 5 (batch)
59.9
Claude Fable 5
59.9
GPT-5.6 Sol
58.9
Kimi K3
57.1
Anthropic: Claude Opus 4.8 (batch)
55.7
Anthropic: Claude Opus 4.8
55.7
GPT OSS 20B
14.9
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
Max Output Tokens131072 → 32768
Max Output Tokens32768 → 131072
Max Output Tokens131072 → 32768
Max Output Tokens32768 → 131072
Max Output Tokens131072 → 32768
Price Completion0.14 → 0.13
Max Output Tokens32768 → 131072
Price Completion0.13 → 0.14
Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/openai/gpt-oss-20b
curl
curl "https://www.modelbench.lol/api/v1/models/openai/gpt-oss-20b"