OpenAI compatible API · Attested · Public status

OpenAI: gpt-oss-120b

Compare every TrustedRouter route for gpt-oss-120b, including token pricing, context limits, privacy policy, regional availability, measured uptime, and API support.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.

openai/gpt-oss-120b

open weights US providers EU-focused OpenAI

Current route evidence

Live leaderboard
$0.03165/1MLowest Credits input price
$0.17935/1MLowest Credits output price
1019 msFastest measured p50 TTFT via sail-research
97 tok/sHighest measured throughput via nscale

Recent provider-route uptime spans 100.00% across 23 routes and 23 providers. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.

Providers serving this model

Sorted by lowest combined prompt and completion price. Use "provider": {"sort": "throughput"} in the request body (or append :nitro to the model id) to route to the fastest provider instead.

Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture.

Provider Input Cached input Output Weight format TR router attested Provider policy
AkashMLakashml $0.03165/1M $0.03165/1M $0.17935/1M Unknown yes privacy unknown
Weights & Biaseswandb $0.03165/1M Not published $0.17935/1M Unknown yes no verified privacy claim
DeepInfradeepinfra $0.039035/1M Not published $0.17935/1M Unknown yes no verified privacy claim
Crusoecrusoe $0.05275/1M $0.05275/1M $0.26375/1M Unknown yes privacy unknown
Novita AInovita $0.05275/1M Not published $0.26375/1M Unknown yes privacy unknown
Sail Researchsail-research $0.0633/1M $0.03165/1M $0.422/1M Unknown yes privacy unknown
Nscalenscale $0.1055/1M Not published $0.422/1M Unknown yes no verified privacy claim
SiliconFlowsiliconflow $0.05275/1M $0.079125/1M $0.47475/1M Unknown yes privacy unknown
Mancermancer $0.084232/1M Not published $0.505388/1M Unknown yes privacy unknown
Basetenbaseten $0.1055/1M $0.1055/1M $0.5275/1M Unknown yes ZDR
Databricksdatabricks $0.15825/1M Not published $0.633/1M Unknown yes no verified privacy claim
Fireworks AIfireworks $0.15825/1M $0.015825/1M $0.633/1M Unknown yes privacy unknown
Nebius Token Factorynebius $0.15825/1M Not published $0.633/1M Unknown yes ZDR
Tinfoiltinfoil $0.15825/1M Not published $0.633/1M
MXFP4 (mixed)

Published serving configuration, reviewed 2026-09-27. Per-request precision is not verified.

MXFP4 weight quantization; attention, routers, embeddings and output head are excluded.

KV cache: unspecified.

Published serving configuration

Published model router

Pinned weight configuration

yes Confidential ZDR
Togethertogether $0.15825/1M Not published $0.633/1M Unknown yes ZDR
SambaNovasambanova $0.2321/1M Not published $0.62245/1M Unknown yes privacy unknown
Parasailparasail $0.1055/1M $0.058025/1M $0.79125/1M Unknown yes ZDR
IO Intelligenceio-net $0.18779/1M $0.093895/1M $0.7174/1M Unknown yes privacy unknown
Scalewayscaleway $0.189061/1M Not published $0.756239/1M Unknown yes privacy unknown
Cerebrascerebras $0.36925/1M Not published $0.79125/1M Unknown yes ZDR
Cloudflare Workers AIcloudflare-workers-ai $0.36925/1M Not published $0.79125/1M Unknown yes privacy unknown
Privatemodeprivatemode $0.541972/1M $0.050417/1M $2.142677/1M
MXFP4 (mixed)

Published serving configuration, reviewed 2026-09-27. Per-request precision is not verified.

MXFP4 weight quantization; attention, routers, embeddings and output head are excluded.

KV cache: fp8.

Published model revisions and root hashes

Published serving configuration

Pinned weight configuration

yes Confidential
Regoloregolo $1.200379/1M Not published $5.041592/1M Unknown yes ZDR

Compare OpenAI: gpt-oss-120b

All comparisons

Questions

What model ID should I use for OpenAI: gpt-oss-120b?

Use openai/gpt-oss-120b as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve OpenAI: gpt-oss-120b?

TrustedRouter currently lists Tinfoil, Privatemode, Cerebras, Nebius Token Factory, Parasail, Together, Baseten, Regolo, DeepInfra, Novita AI, SiliconFlow, Fireworks AI, Cloudflare Workers AI, Sail Research, AkashML, SambaNova, Mancer, IO Intelligence, Scaleway, Nscale, Weights & Biases, Crusoe, and Databricks for OpenAI: gpt-oss-120b. Provider availability and routing eligibility can change as catalog and health data update.

How much does OpenAI: gpt-oss-120b cost through TrustedRouter?

The current lowest Credits input price is $0.03165/1M and the lowest Credits output price is $0.17935/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for OpenAI: gpt-oss-120b?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.

Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.