GPT OSS 20B

OpenAIMCP Tool CallReasoning
openai/gpt-oss-20bOpen Weights

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

Benchmark Pricing$0.04 / 1M in$0.17 / 1M out
Context: 131,072 tokens•Max Output: 32,768 tokens•Knowledge: 2024-06•Released: 2025-08-05

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens
Max Output32,76832.8K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ GPT OSS 20B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling GPT OSS 20B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "openai/gpt-oss-20b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

15 providers
Cortecsgpt-oss-20b
$0.04 / $0.17
OCI Generative AIopenai.gpt-oss-20b
$0.07 / $0.30
Clarifaiopenai/chat-completion/models/gpt-oss-20b
$0.04 / $0.18
NanoGPTopenai/gpt-oss-20b
$0.02 / $0.10
IO.NETopenai/gpt-oss-20b
$0.06 / $0.19$0.03 cache
LLM Gatewayconsensusprotocol/gpt-oss-20b
$0.04 / $0.19$0.01 cache
QVACgpt-oss-20b
$0.00 / $0.00
CoreWeaveopenai/gpt-oss-20b
$0.03 / $0.13$0.03 cache
Tempr Gatewaygroq/openai/gpt-oss-20b
$0.07 / $0.30$0.04 cache
AI/ML APIopenai/gpt-oss-20b
$0.10 / $0.41$0.05 cache
Thinking Machinesopenai/gpt-oss-20b
$0.18 / $0.45$0.04 cache
Databricksdatabricks-gpt-oss-20b
$0.07 / $0.30
Vercel AI Gatewayopenai/gpt-oss-20b
$0.03 / $0.14
Eden AIdatabricks/databricks-gpt-oss-20b@eu
$0.07 / $0.30$0.01 cache
Merge Gatewayopenai/gpt-oss-20b
$0.04 / $0.15$0.02 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

MODEL RESOURCES

View OpenAI HubHugging Face Weights

More Models by OpenAI

Alternative and family models from the same lab

View all OpenAI models →
GPT-5.6 Sol
openai/gpt-5.6-sol•OpenAI
1.1M ctx

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

128K out maxVisionPDFSWE-Bench Pro: 64.6 resolve rate
In: $4.00 • Out: $20.00
OpenAI
GPT-5.4 Pro
openai/gpt-5.4-pro•OpenAI
1.1M ctx

More exact GPT-5.4 tier for demanding professional reasoning and agent tasks

128K out maxVisionGPQA Diamond: 94.4 accuracy
In: $30.00 • Out: $180.00
OpenAI
GPT-5.6 Terra
openai/gpt-5.6-terra•OpenAI
1.1M ctx

Balanced GPT-5.6 model for capable, cost-efficient everyday work

128K out maxVisionPDFSWE-Bench Pro: 63.4 resolve rate
In: $2.00 • Out: $12.00
OpenAI