grok-4.20-0309-reasoning
Chat model from xAI Grok. One API key reaches all 2 providers, with automatic failover.
No card required. Start with 1 million free tokens.
About grok-4.20-0309-reasoning
grok-4.20-0309-reasoning is a chat model published by xAI Grok. Through TrustedRouter it runs on 2 providers, with options in the US, from $1.32 per million input tokens. Two providers offer zero data retention.
- Model ID
x-ai/grok-4.20-reasoning- Publisher
- xAI Grok
- Modes
- chat
- Billing
- Credits
Set it up with your agent
Paste this into Claude Code, Cursor or any coding agent.
Use grok-4.20-0309-reasoning through TrustedRouter in this project.
1. Read https://trustedrouter.com/llms.txt
2. Point the OpenAI-compatible client at
https://api.trustedrouter.com/v1 and read the key from
TRUSTEDROUTER_API_KEY.
3. Set the model to x-ai/grok-4.20-reasoning.
4. Run the tests, then show me the diff before committing.import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.trustedrouter.com/v1",
api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
response = client.chat.completions.create(
model="x-ai/grok-4.20-reasoning",
messages=[{"role": "user", "content": "What is the capital of France?"}],
)
print(response.choices[0].message.content)curl https://api.trustedrouter.com/v1/chat/completions \
-H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "x-ai/grok-4.20-reasoning",
"messages": [{"role": "user", "content": "What is the capital of France?"}]
}'Providers
Your key goes to the cheapest healthy provider and fails over on its own. Open a row for retention, location and weight format, or see how we check privacy claims and the live speed leaderboard.
| Provider | Input | Cached | Output | Cost per 1M in + out | Details |
|---|---|---|---|---|---|
Microsoft Azure AI Foundry
Zero retention
|
$1.32 | — | $2.64 | $3.96 | |
|
Retention Zero data retention. Verification: provider E2EE not verified. ZDR is approved for reviewed TR-funded Azure-hosted Foundry routes. Microsoft approved modified abuse monitoring on November 12, 2026, and ContentLogging=false was verified on TrustedRouter's serving resource. Partner-hosted services, Azure Speech previews, unreviewed models and customer BYOK credentials are not covered. This is policy-backed ZDR, not upstream confidential compute or E2EE. Location Operator country: US Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Weight format Unknown Price and speed Input $1.31875/1M · Cached input Not published · Output $2.6375/1M TTFT: 3.55 s Speed: insufficient data Last sample: |
|||||
|
xAI Grok
Zero retention
|
$1.32 | $0.211 | $2.64 | $3.96 | |
|
Retention Zero data retention. TR-funded routes use TrustedRouter's xAI team with zero data retention enabled, confirmed by x-zero-data-retention: true on the authenticated key endpoint. xAI documents no persistence of prompts or outputs under ZDR; operational metadata may be retained. BYOK is not covered by this account setting. This is provider ZDR, not confidential compute. Location Operator country: US Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Weight format Unknown Price and speed Input $1.31875/1M · Cached input $0.211/1M to $0.422/1M · Output $2.6375/1M TTFT: 1.36 s Speed: insufficient data Last sample: |
|||||
Append :nitro to the model ID, or send "provider": {"sort": "throughput"}, to route to the fastest provider instead.
Questions
What model ID should I use for grok-4.20-0309-reasoning?
Use x-ai/grok-4.20-reasoning as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Do you log my prompts or outputs?
No. Prompt and output content are intentionally excluded from the control plane and metadata systems. Optional content export requires explicit destination-level configuration.
Which providers serve grok-4.20-0309-reasoning?
TrustedRouter currently lists xAI Grok, and Microsoft Azure AI Foundry for grok-4.20-0309-reasoning. Provider availability and routing eligibility can change as catalog and health data update.
How much does grok-4.20-0309-reasoning cost through TrustedRouter?
The current lowest Credits input price is $1.31875/1M and the lowest Credits output price is $2.6375/1M. Prices are per one million tokens and come from the current route catalog.
How do I require zero data retention for grok-4.20-0309-reasoning?
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.
grok-4.20-0309-reasoning vs other models
Start building with grok-4.20-0309-reasoning.
No card required. Start with 1 million free tokens.