Request Budget

What does your request cost?

Adjust the token mix for GPT-OSS-120B. These are listed token charges, before the rest of your application bill.

One thousand requests

Fixed default illustration: 1,000 input and 500 output tokens per request.

1,000 input + 500 output tokens per request; 1,000 requests.

Groq$0.450
Fireworks AI$0.450
DeepInfra$0.122
Together AI$0.450
Input chargeOutput charge

USD. Token charges = (input tokens × input rate + output tokens × output rate) × 1,000 requests ÷ 1,000,000. No cache, batch, tools, retries or taxes in this illustration.

The model name is one check.

DeepInfra lists bfloat16. Serving precision, model revisions and output fidelity across these hosts were not tested. A lower listed token charge is not a quality result.

Groq

GPT-OSS-120B
$0.15 input / $0.60 output per 1M tokens

openai/gpt-oss-120b, Developer plan

Listed token rates; no cache, batch, tools, taxes or retry cost included. Serving configuration and output fidelity untested.

Source ↗

Fireworks AI

GPT-OSS-120B Standard
$0.15 input / $0.60 output per 1M tokens

GPT-OSS-120B, Standard Serverless

Cached input $0.015 / 1M separately. Priority rates differ; US-only option on select models has a 50% premium, waived on Muse Spark Open.

Source ↗

DeepInfra

GPT-OSS-120B
$0.037 input / $0.17 output per 1M tokens

openai/gpt-oss-120b, public model listing, bfloat16

131,072 context listed. Zero retention badge alone is not a reviewed endpoint policy. No independent serving-fidelity or latency test.

Source ↗

Together AI

GPT-OSS-120B
$0.15 input / $0.60 output per 1M tokens

openai/gpt-oss-120b model listing; Serverless and Dedicated links

128K context listed. Listed rates, not a live account quote; page also contains a generic launching-soon component. Model availability not independently exercised.

Source ↗

Other ways the bill changes

OpenAI

GPT-6.1 Sol Standard
$2 input / $10 output per 1M tokens

gpt-6.1-sol API text tokens, Standard

Cached input $0.10; cache write $2.50. Over 272K input tokens: full request input/cache rates 2×, output 1.5×. Regional processing adds 10% where offered.

Source ↗

Anthropic

Sonnet 5.5 base tokens
$2 input / $10 output per MTok

Claude Sonnet 5.5 first-party standard API rates

5-minute cache write $2.50, 1-hour $4, cache hit $0.10 per MTok. Cache writes and hits have separate rates. Different model from the GPT-OSS cost illustration.

Source ↗

Google Vertex AI

Failed long completions
Gemini 4 retrievable usage can still be charged

Gemini 4 completion above 32K tokens

Effective November 13, 2026: retrievable token usage is charged even if the request ultimately fails due to client/server timeout. This is an exception to the page’s general non-200 statement.

Source ↗

OpenRouter

Platform fee
Standard 5.5% / Business 8%

OpenRouter paid plans, underlying model token rates separate

Model tokens billed at posted per-model input/output rates. BYOK has separate fee thresholds. This is not a per-token rate or application total.

Source ↗

Replicate

Public vs private serving
Private models can bill setup and idle time

Replicate private models except fast-booting fine-tunes

Public models bill processing by time/hardware or input/output. Private models bill setup+idle+active while online; fast-booting fine-tunes are an explicit active-only exception.

Source ↗

Cerebras

Prepaid credits
Purchased credits expire after one year

Cerebras PayGo purchased credits

At zero balance rate limits revert to zero until funds added. The separate promotional-credit terms are in IA-040.

Source ↗

Cerebras

Promotional credit
$5 once; expires after 30 days

Cerebras promotional trial with valid payment method

No automatic paid enrollment. API/Playground access pauses when exhausted or expired unless PayGo credits separately purchased. Numeric tier table was not exposed in this opened text; do not treat this as a current production quote.

Source ↗