OpenAI compatible API · Attested · Public status

Meta: Llama 3.3 70B Instruct

Compare every TrustedRouter route for Meta: Llama 3.3 70B Instruct, 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.

meta-llama/llama-3.3-70b-instruct

open weights US providers EU-focused Cerebras

All models

Publisher Cerebrascerebras
AI IQ No AI IQ profile matched yet.
Context131,072 tokens
Providers
Credits routes11 provider routes
Modes chat decide open weights US providers EU-focused
BillingCredits

Current route evidence

Live leaderboard
$0.142425/1MLowest Credits input price
$0.422/1MLowest Credits output price
723 msFastest measured p50 TTFT via wandb
not enough dataHighest measured throughput

Recent provider-route uptime spans 100.00% across 11 routes and 11 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
Novita AInovita $0.142425/1M Not published $0.422/1M Unknown yes privacy unknown
AkashMLakashml $0.211/1M $0.1055/1M $0.5486/1M Unknown yes privacy unknown
Parasailparasail $0.2321/1M $0.11605/1M $0.5275/1M Unknown yes ZDR
Telnyxtelnyx $0.633/1M $0.633/1M $0.633/1M Unknown yes ZDR
Weights & Biaseswandb $0.74905/1M Not published $0.74905/1M Unknown yes no verified privacy claim
IO Intelligenceio-net $0.576663/1M $0.288332/1M $1.078843/1M Unknown yes privacy unknown
SambaNovasambanova $0.633/1M Not published $1.266/1M Unknown yes privacy unknown
Databricksdatabricks $0.5275/1M Not published $1.5825/1M Unknown yes no verified privacy claim
Togethertogether $1.0972/1M Not published $1.0972/1M Unknown yes ZDR
Scalewayscaleway $1.134359/1M Not published $1.134359/1M Unknown yes privacy unknown
Tinfoiltinfoil $1.84625/1M Not published $2.90125/1M
FP8

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

FP8 weight groups with dynamic FP8 activations; excluded layers retain higher precision.

KV cache: unspecified.

Published serving configuration

Published model router

Pinned weight configuration

yes Confidential ZDR

Compare Meta: Llama 3.3 70B Instruct

All comparisons

Questions

What model ID should I use for Meta: Llama 3.3 70B Instruct?

Use meta-llama/llama-3.3-70b-instruct as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve Meta: Llama 3.3 70B Instruct?

TrustedRouter currently lists Tinfoil, Parasail, Together, Telnyx, Novita AI, AkashML, SambaNova, IO Intelligence, Scaleway, Weights & Biases, and Databricks for Meta: Llama 3.3 70B Instruct. Provider availability and routing eligibility can change as catalog and health data update.

How much does Meta: Llama 3.3 70B Instruct cost through TrustedRouter?

The current lowest Credits input price is $0.142425/1M and the lowest Credits output price is $0.422/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for Meta: Llama 3.3 70B Instruct?

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.