OpenAI compatible API · Attested · Public status
Meta: Llama 4 Maverick
All providers serving Meta: Llama 4 Maverick via TrustedRouter.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
meta-llama/llama-4-maverick
open weights
US providers
Cerebras
| Publisher | Cerebras (cerebras) |
|---|---|
| AI IQ | IQ 90 #90 on AI IQ |
| Context | 1,048,576 tokens |
| Providers | |
| Endpoints | 4 endpoints |
| Modes | chat open weights US providers |
| Routes | prepaid BYOK |
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 | Usage | Prompt | Completion | TR router attested | Provider policy |
|---|---|---|---|---|---|
DigitalOcean Gradient AI (digitalocean) |
Credits | $0.2625/1M | $0.9135/1M | yes | upstream varies |
DigitalOcean Gradient AI (digitalocean) |
BYOK | $0.2625/1M | $0.9135/1M | yes | upstream varies |
Parasail (parasail) |
Credits | $0.3675/1M | $1.05/1M | yes | ZDR |
Parasail (parasail) |
BYOK | $0.3675/1M | $1.05/1M | yes | ZDR |
Endpoint JSON: https://api.trustedrouter.com/v1/models/meta-llama/llama-4-maverick/endpoints