Groq
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 ↗Adjust the token mix for GPT-OSS-120B. These are listed token charges, before the rest of your application bill.
Fixed default illustration: 1,000 input and 500 output tokens per request.
Enter whole token counts from 1 to 65,536 in both fields.
1,000 input + 500 output tokens per request; 1,000 requests.
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.
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.
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 ↗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 ↗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 ↗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 ↗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 ↗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 ↗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 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 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 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 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 ↗