OpenAICertifiedReleased 08/05/2025

GPT OSS 120B

Extremely capable general-purpose LLM with strong, controllable reasoning capabilities

View API reference ↓
Input / output priceFrom$0.100 / $0.50per 1M
24h uptime99.89%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "openai/gpt-oss-120b",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

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

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
Amazon Bedrock128K8K0.3 s359 tps$0.15$0.60Read —Write —4 featuresYesYesGlobalCertified
Baseten131K131K0.2 s176 tps$0.100$0.50Read $0.100Write —4 featuresYesYesUSCertified
Cerebras131K131K——$0.35$0.75Read $0.35Write —5 featuresNoYesGlobalCertified
Groq131K33K0.3 s487 tps$0.15$0.60Read $0.075Write —5 featuresYesYesGlobalListed
nebius131K131K0.3 s392 tps$0.15$0.60Read $0.100Write —4 featuresYesYesGlobalCertified
parasail131K131K0.3 s274 tps$0.100$0.75Read $0.055Write —4 featuresYesYesGlobalCertified
Together AI128K128K0.2 s129 tps$0.15$0.60Read —Write —4 featuresYesYesGlobalCertified

Uptime

24 hours

Request success rate per provider.

Amazon Bedrock100.00%
Baseten99.85%
Cerebras100.00%
Groq99.45%
nebius99.99%
parasail100.00%
Together AI99.94%

Throughput

last hour

P50 output tokens per second.

Groq487 tps
nebius392 tps
Amazon Bedrock359 tps
parasail274 tps
Baseten176 tps
Together AI129 tps
Cerebras—

Latency

last hour

P50 time to first token.

Together AI0.2 s
Baseten0.2 s
Groq0.3 s
Amazon Bedrock0.3 s
parasail0.3 s
nebius0.3 s
Cerebras—

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "openai/gpt-oss-120b",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

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

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. openai/gpt-oss-120b. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. GPT OSS 120B supports up to 131,072 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 131K-token context window

More models by OpenAI

ModelContextInputOutputCacheRelease
openai/gpt-6.1-terra1.05M$1.00$5.00Read $0.050Write $1.2510/26/2026
openai/gpt-6.1-terra-fast1.05M$2.00$10.00Read $0.100Write $2.5010/26/2026
openai/gpt-6.1-sol1.05M$2.00$10.00Read $0.100Write $2.5009/29/2026
openai/gpt-6.1-sol-batch1.05M$1.00$5.00Read $0.050Write $1.2509/29/2026
openai/gpt-6.1-sol-fast1.05M$4.00$20.00Read $0.20Write $5.0009/29/2026
openai/gpt-6-luna1.05M$0.100$0.50Read $0.010Write $0.1309/22/2026
openai/gpt-6-luna-batch1.05M$0.050$0.25Read $0.0050Write $0.06309/22/2026
openai/gpt-6-luna-fast1.05M$0.20$1.00Read $0.020Write $0.2509/22/2026
openai/gpt-6-sol1.05M$2.00$10.00Read $0.20Write $2.5009/22/2026
openai/gpt-6-sol-batch1.05M$1.00$5.00Read $0.100Write $1.2509/22/2026