gpt-oss-120b

OpenAIReleased Aug 5, 2025

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.

Try it in the estimate Compare

Input, per 1M tokens: $0.044$0.041 for holders
Output, per 1M tokens: $0.20$0.19 for holders
Context: 131K tokens
Tokens this week: None yet

Price

Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.

Charge	Agents	Holders	Per
Inputper 1M tokens	$0.044	$0.041	per 1M tokens
Outputper 1M tokens	$0.20	$0.19	per 1M tokens

Price history

What an agent paid per million tokens, by day.

Unchanged since Sep 29, 2026: $0.044 in and $0.20 out per million tokens.

Usage through bInference

Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.

Last 7 days: 0
Last 30 days: 0
All time: 0

InputOutputReasoning

Where it runs

The hosts serving this model now, and how often each answered over the last day.

Use it

Two settings: our address and your agent’s key. The model is set in each call.

import OpenAI from "openai";const client = new OpenAI({  baseURL: "https://binference.io/api/v1",Address  apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({  model: "openai/gpt-oss-120b",  messages: [{ role: "user", content: "Summarize today's trades" }],  max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address  -H "Authorization: Bearer $BINF_API_KEY" \Key  -H "Content-Type: application/json" \  -d '{    "model": "openai/gpt-oss-120b",    "messages": [{ "role": "user", "content": "Hello" }],    "max_tokens": 1024  }'

Questions

More from OpenAI

GPT-6.1 Sol ProOpenAI1M$2.40 in · $12.00 out$2.21 in · $11.04 out GPT-6.1 SolOpenAI1M$2.40 in · $12.00 out$2.21 in · $11.04 out GPT-6 Luna ProOpenAI1M$0.12 in · $0.60 out$0.11 in · $0.55 out GPT-6 LunaOpenAI1M$0.12 in · $0.60 out$0.11 in · $0.55 out

Agents

Holders

Inputper 1M tokens

$0.044

$0.041

per 1M tokens

Outputper 1M tokens

$0.20

$0.19

per 1M tokens

Host	Answered, last day	Context
CoreWeaveFp4fp4, answering	99.6%	131K
DekaLLMBf16bf16, answering	99.1%	131K
DeepInfraBf16bf16, answering	98.8%	131K
AkashMLBf16bf16, answering	100%	131K
CrusoeBf16bf16, answering	100%	131K
NovitaFp4fp4, answering	99.5%	131K
Mancer 2Fp8fp8, answering	98.8%	131K
DigitalOcean, answering	99.9%	128K
GoogleGlobal, having trouble	50.7%	131K
BaseTenFp4fp4, answering	99.5%	128K
BaseTenFp4fp4, answering	99.6%	128K
ParasailFp4fp4, answering	100%	131K
SambaNova, answering	97.5%	131K
Amazon BedrockEu west 1, answering	98.5%	131K
NebiusFp4fp4, answering	91.8%	131K
Amazon Bedrock, answering	100%	131K
DeepInfraTurbobf16, answering	100%	131K
SiliconFlowFp8fp8, answering	81.6%	131K
Phala, answering	99.5%	131K
Together, answering	97.2%	131K
Groq, answering	99.3%	131K
Mara, having trouble	65%	131K
DeepInfraFp8fp8, answering	91.9%	131K
CerebrasFp16fp16, answering	100%	131K

Host

Answered, last day

Context

CoreWeaveFp4fp4

99.6%

131K

DekaLLMBf16bf16

99.1%

131K

DeepInfraBf16bf16

98.8%

131K

AkashMLBf16bf16

100%

131K

CrusoeBf16bf16

100%

131K

NovitaFp4fp4

99.5%

131K

Mancer 2Fp8fp8

98.8%

131K

DigitalOcean

99.9%

128K

GoogleGlobal

50.7%

131K

BaseTenFp4fp4

99.5%

128K

BaseTenFp4fp4

99.6%

128K

ParasailFp4fp4

100%

131K

SambaNova

97.5%

131K

Amazon BedrockEu west 1

98.5%

131K

NebiusFp4fp4

91.8%

131K

Amazon Bedrock

100%

131K

DeepInfraTurbobf16

100%

131K

SiliconFlowFp8fp8

81.6%

131K

Phala

99.5%

131K

Together

97.2%

131K

Groq

99.3%

131K

Mara

65%

131K

DeepInfraFp8fp8

91.9%

131K

CerebrasFp16fp16

100%

131K

import OpenAI from "openai";const client = new OpenAI({ baseURL: "https://binference.io/api/v1",Address apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({ model: "openai/gpt-oss-120b", messages: [{ role: "user", content: "Summarize today's trades" }], max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address -H "Authorization: Bearer $BINF_API_KEY" \Key -H "Content-Type: application/json" \ -d '{ "model": "openai/gpt-oss-120b", "messages": [{ "role": "user", "content": "Hello" }], "max_tokens": 1024 }'

gpt-oss-120b

Price

Price history

Usage through bInference

Where it runs

Use it

Questions

More from OpenAI

Similar models

gpt-oss-120b

Price

Price history

Usage through bInference

Where it runs

Where it runs

Use it

Questions

More from OpenAI

Similar models

Where it runs

gpt-oss-120b

Price

Price history

Usage through bInference

Where it runs

Use it

Questions

How much does gpt-oss-120b cost?

How does my agent use gpt-oss-120b?

How much can gpt-oss-120b read at once?

What can gpt-oss-120b do?

Are my prompts stored?

More from OpenAI

Similar models

gpt-oss-120b

Price

Price history

Usage through bInference

Where it runs

Where it runs

Use it

Questions

How much does gpt-oss-120b cost?

How does my agent use gpt-oss-120b?

How much can gpt-oss-120b read at once?

What can gpt-oss-120b do?

Are my prompts stored?

More from OpenAI

Similar models

Where it runs