Gemma 3 27B
Open-weights chat model from Google AI Studio. One API key reaches all 7 providers, with automatic failover.
No card required. Start with 1 million free tokens.
About Gemma 3 27B
Gemma 3 27B is an open-weights chat model published by Google AI Studio, with a 131,072-token context window. Through TrustedRouter it runs on 7 providers, with options in the US and EU, from $0.084 per million input tokens. Three providers offer zero data retention.
- Model ID
google/gemma-3-27b-it- Publisher
- Google AI Studio
- Modes
- chat
- Billing
- Credits or your own provider key
Set it up with your agent
Paste this into Claude Code, Cursor or any coding agent.
Use Gemma 3 27B 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 google/gemma-3-27b-it.
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="google/gemma-3-27b-it",
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": "google/gemma-3-27b-it",
"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 |
|---|---|---|---|---|---|
DeepInfra
Cheapest
|
$0.0844 | — | $0.169 | $0.25 | |
|
Retention Verification: no verified privacy claim. Tracked as no-store, not strict ZDR. DeepInfra documents memory-only handling and no training for ordinary inference, but reserves the right to log a small portion of requests for debugging or security. Google- and Anthropic-backed routes also inherit those vendors' terms. Location Operator country: US Headquarters / registered office: Palo Alto, California, United States. Company location source (reviewed 2026-09-27). Inference: US infrastructure plus announced Canadian capacity; model-specific residency unconfirmed. DeepInfra describes US infrastructure and announced its first international data center in Toronto on July 8, 2026. This is a provider footprint, not an exhaustive or model-specific placement list. DeepSeek V4.1 Flash placement has not been confirmed; do not declare this route US-only. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-27. DeepInfra infrastructure statement Weight format Unknown Price and speed Input $0.0844/1M · Cached input Not published · Output $0.1688/1M TTFT: insufficient data Speed: insufficient data |
|||||
Novita AI
|
$0.126 | — | $0.211 | $0.34 | |
|
Retention Verification: privacy unknown. No provider-ZDR claim is tracked here. Novita's privacy policy says personal information is not used for model training; customer-content processing is governed by customer agreements. Location Operator country: US Headquarters / registered office: San Francisco, California, United States. Company location source (reviewed 2026-09-27). Inference: Shared inference API; processing countries unconfirmed, no fixed-region commitment. No exhaustive inference-country list verified for the shared model API. Novita publishes worldwide GPU rental regions, but that separate product does not establish shared serverless model placement. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-10-28. Weight format Unknown Price and speed Input $0.125545/1M · Cached input Not published · Output $0.211/1M TTFT: insufficient data Speed: insufficient data |
|||||
Nebius Token Factory
Zero retention
|
$0.106 | — | $0.316 | $0.42 | |
|
Retention Zero data retention. Marked ZDR via TrustedRouter's arrangement — Nebius RETAINS inputs/outputs by default (for speculative decoding); zero retention is an opt-in control, which the deployed Nebius account has enabled. Nebius does not train on customer data. Location Operator country: NL Headquarters / registered office: Amsterdam, Netherlands. Company location source (reviewed 2026-10-28). Inference: Global, dynamically placed public inference; no fixed-country commitment. Token Factory public endpoints are Global; Finland storage of retained content does not identify the inference location. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-10-28. Weight format Unknown Price and speed Input $0.1055/1M · Cached input Not published · Output $0.3165/1M TTFT: 1.01 s Speed: insufficient data Last sample: |
|||||
NextBit
|
$0.0844 | $0.0422 | $0.369 | $0.45 | |
|
Retention Verification: privacy unknown. NextBit's global API can use third-party infrastructure outside the EEA. Its DPA permits exceptional legal retention for up to 30 days, so this route remains Standard. Use NextBit (EU) for Spain-only processing and zero content retention. No confidential-compute or E2EE claim is made. Location Operator country: ES Headquarters / registered office: Not verified. Inference: Global inference; countries unspecified. Not an EU-only route. NextBit's global API may run inference on third-party infrastructure outside the EEA. Region pinning through TR: Use provider.only=[nextbit-eu] for the separate EU route, not nextbit. Reviewed 2026-10-14. Weight format Unknown Price and speed Input $0.0844/1M · Cached input $0.0422/1M · Output $0.36925/1M TTFT: 1.31 s Speed: insufficient data Last sample: |
|||||
NextBit (EU)
Zero retention
|
$0.0844 | $0.0422 | $0.369 | $0.45 | |
|
Retention Zero data retention. Verification: provider E2EE not verified. NextBit's EU API processes inference exclusively in Spain. Its public DPA sections 4 and 11 prohibit retaining prompts, outputs, or content logs and using them for training; operational metadata is retained. This route uses eu.api.nextbit256.com, never the global API. Special-category personal data requires a separate agreement under section 13. No confidential-compute or E2EE claim is made. Location Operator country: ES Headquarters / registered office: Not verified. Inference: Spain-only inference; gateway in the EU. Operational metadata retained; no content retention. The EU API's DPA commits to inference exclusively on NextBit infrastructure in Spain. Region pinning through TR: Select provider.only=[nextbit-eu] with allow_fallbacks=false and min_privacy=zdr. Reviewed 2026-10-14. Weight format Unknown Price and speed Input $0.0844/1M · Cached input $0.0422/1M · Output $0.36925/1M TTFT: 1.00 s Speed: insufficient data Last sample: |
|||||
Parasail
Zero retention
|
$0.0844 | $0.0422 | $0.475 | $0.56 | |
|
Retention Zero data retention. Tracked as ZDR for serverless and dedicated inference. Parasail documents no storage or logging of submitted input on those service paths, retention only while generating and delivering output, and no training on input or output. Batch service is excluded from this claim; TrustedRouter does not route Parasail traffic through batch. 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 $0.0844/1M · Cached input $0.0422/1M · Output $0.47475/1M TTFT: insufficient data Speed: insufficient data Last sample: |
|||||
Amazon Bedrock
|
$0.243 | — | $0.401 | $0.64 | |
|
Retention Retention unverified - not strict ZDR: This exact model and upstream ID have not been approved for strict ZDR under the current account controls. Provider-wide ZDR, no-training and successful inference are insufficient. Safety retention or other content storage may apply; the route is excluded until reviewed. This exact model and upstream ID have not been approved for strict ZDR under the current account controls. Provider-wide ZDR, no-training and successful inference are insufficient. Safety retention or other content storage may apply; the route is excluded until reviewed. 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 $0.24265/1M · Cached input Not published · Output $0.4009/1M TTFT: insufficient data 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 Gemma 3 27B?
Use google/gemma-3-27b-it 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 Gemma 3 27B?
TrustedRouter currently lists Nebius Token Factory, Parasail, NextBit (EU), DeepInfra, Novita AI, NextBit, and Amazon Bedrock for Gemma 3 27B. Provider availability and routing eligibility can change as catalog and health data update.
How much does Gemma 3 27B cost through TrustedRouter?
The current lowest Credits input price is $0.0844/1M and the lowest Credits output price is $0.1688/1M. Prices are per one million tokens and come from the current route catalog.
How do I require zero data retention for Gemma 3 27B?
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.
Gemma 3 27B vs other models
Start building with Gemma 3 27B.
No card required. Start with 1 million free tokens.