Gemma 4 26B A4B
Open-weights chat model from Google AI Studio. One API key reaches all 11 providers, with automatic failover.
No card required. Start with 1 million free tokens.
About Gemma 4 26B A4B
Gemma 4 26B A4B is an open-weights chat model published by Google AI Studio, with a 256,000-token context window. It scores 99 on AI IQ, ranked #131. Through TrustedRouter it runs on 11 providers, with options in the US and EU, from $0.069 per million input tokens. Two providers offer zero data retention.
- Model ID
google/gemma-4-26b-a4b-it- Publisher
- Google AI Studio
- Modes
- chat, decide
- 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 4 26B A4B 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-4-26b-a4b-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-4-26b-a4b-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-4-26b-a4b-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 |
|---|---|---|---|---|---|
Muna
Cheapest
|
$0.0686 | $0.0211 | $0.316 | $0.39 | |
|
Retention Verification: no verified privacy claim. Muna (NatML Inc.) operates its own serving stack on rented US GPUs, without reselling downstream model APIs. No training on customer content. Its published zero-retention policy permits incidental content fragments in diagnostic logs for up to 30 days, so these routes remain Standard, not strict ZDR or confidential/E2EE. Shared prefix and decoded-image caches are memory-only; prefix caching is not account-isolated. Request and edge metadata remain for 30 days, billing records for seven years. Renewable electricity coverage is unknown. Tools support auto/none selection; required tool selection is not currently supported. Location Operator country: US Headquarters / registered office: Not verified. Inference: United States (provider-declared), dynamically placed; specific datacenter region is not exposed. Provider-declared US inference on rented dedicated GPUs operated by Muna; no downstream model APIs. Region pinning through TR: Select provider.only=[muna] with allow_fallbacks=false; no finer regional pin is available. Reviewed 2026-10-22. Weight format Unknown Price and speed Input $0.068575/1M · Cached input $0.0211/1M · Output $0.3165/1M TTFT: 1.00 s Speed: insufficient data Last sample: |
|||||
NextBit
|
$0.0950 | $0.0528 | $0.316 | $0.41 | |
|
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 $0.09495/1M · Cached input $0.05275/1M · Output $0.3165/1M TTFT: 1.27 s Speed: insufficient data Last sample: |
|||||
NextBit (EU)
Zero retention
|
$0.0950 | $0.0528 | $0.316 | $0.41 | |
|
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 $0.09495/1M · Cached input $0.05275/1M · Output $0.3165/1M TTFT: 1.06 s Speed: insufficient data Last sample: |
|||||
Cloudflare Workers AI
|
$0.106 | $0.0528 | $0.316 | $0.42 | |
|
Retention Verification: privacy unknown. Workers AI documents no input/output retention after ordinary stateless inference and no model training. Stateful features, customer-enabled logging/caching, and safety, security or legal exceptions may retain content. No exception-free commitment is verified for this account; these routes remain outside strict ZDR. 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 $0.1055/1M · Cached input $0.05275/1M · Output $0.3165/1M TTFT: insufficient data Speed: insufficient data |
|||||
Weights & Biases
|
$0.106 | $0.0528 | $0.316 | $0.42 | |
|
Retention Verification: no verified privacy claim. W&B Serverless Inference runs on CoreWeave infrastructure. W&B does not publish a zero-retention, confidential-compute, or end-to-end-encryption commitment for this service, so these routes use the Standard privacy tier. TrustedRouter does not enable W&B Weave tracing for provider calls. 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 $0.1055/1M · Cached input $0.05275/1M · Output $0.3165/1M TTFT: insufficient data Speed: insufficient data |
|||||
DeepInfra
|
$0.0738 | — | $0.359 | $0.43 | |
|
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 $0.07385/1M · Cached input Not published · Output $0.3587/1M TTFT: insufficient data Speed: insufficient data |
|||||
IO Intelligence
|
$0.115 | $0.0577 | $0.328 | $0.44 | |
|
Retention Verification: privacy unknown. In its September 28, 2026 marketplace submission, io.net states that inference prompts and completions are processed only in memory, are not stored or logged, and are not used for training. Content-free operational metadata is retained for billing, capacity planning and abuse prevention. This is a provider declaration: the reviewed public privacy policy does not establish inference-specific zero-retention terms, and the applicable DPA has not been reviewed. Routes remain Standard pending that evidence. Confidential compute is offered on request, but this integration has no verified confidential-compute or provider-side E2EE guarantee. Location Operator country: US Headquarters / registered office: West Hollywood, California, United States (operating address). Company location source (reviewed 2026-09-28). Inference: United States and Canada, provider-declared; no US-only or fixed-country guarantee on this route. io.net declares US and Canadian serving locations and data residency in its September 28, 2026 marketplace submission. This is provider-wide information, not an independently verified per-model or per-request location. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-28. API documentation (not a location guarantee) Weight format Unknown Price and speed Input $0.115312/1M · Cached input $0.057656/1M · Output $0.328105/1M TTFT: insufficient data Speed: insufficient data Last sample: |
|||||
Novita AI
|
$0.137 | — | $0.422 | $0.56 | |
|
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 $0.13715/1M · Cached input Not published · Output $0.422/1M TTFT: 0.68 s Speed: insufficient data Last sample: |
|||||
Parasail
Zero retention
|
$0.137 | $0.0528 | $0.422 | $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 $0.13715/1M · Cached input $0.05275/1M · Output $0.422/1M TTFT: insufficient data Speed: insufficient data Last sample: |
|||||
SiliconFlow
|
$0.148 | $0.0528 | $0.422 | $0.57 | |
|
Retention Verification: privacy unknown. No provider-ZDR claim is tracked here. SiliconFlow's privacy policy source is linked for retention and interaction-data terms. Location Operator country: SG Headquarters / registered office: Singapore (international API operator). Company location source (reviewed 2026-09-27). Inference: Inference countries unconfirmed; no verified country-specific residency commitment. TrustedRouter uses api.siliconflow.com. Neither its hostname nor the provider's Singapore legal jurisdiction establishes the DeepSeek V4.1 Flash GPU location. No exhaustive route-specific country list verified. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-26. Weight format Unknown Price and speed Input $0.1477/1M · Cached input $0.05275/1M · Output $0.422/1M TTFT: insufficient data Speed: insufficient data |
|||||
Scaleway
|
$0.308 | — | $0.616 | $0.92 | |
|
Retention Verification: privacy unknown. Scaleway routes are discovered from its authenticated Model as a Service catalog and priced from Scaleway's first-party EUR price feed with a bounded FX reserve. No contractual ZDR, confidential-compute, or E2EE claim is tracked for this account, so these routes are Standard. Location Operator country: FR Headquarters / registered office: Not verified. Inference: Serverless: currently Paris, France, provider-declared; future expansion within Europe possible. Scaleway's FAQ places its current Serverless inference fleet in Paris. Dedicated deployments are a separate product. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-27. Weight format Unknown Price and speed Input $0.308149/1M · Cached input Not published · Output $0.616298/1M TTFT: 0.85 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 Gemma 4 26B A4B ?
Use google/gemma-4-26b-a4b-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 4 26B A4B ?
TrustedRouter currently lists Parasail, NextBit (EU), DeepInfra, Novita AI, SiliconFlow, Cloudflare Workers AI, NextBit, IO Intelligence, Scaleway, Muna, and Weights & Biases for Gemma 4 26B A4B . Provider availability and routing eligibility can change as catalog and health data update.
How much does Gemma 4 26B A4B cost through TrustedRouter?
The current lowest Credits input price is $0.068575/1M and the lowest Credits output price is $0.3165/1M. Prices are per one million tokens and come from the current route catalog.
How do I require zero data retention for Gemma 4 26B A4B ?
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 4 26B A4B vs other models
Start building with Gemma 4 26B A4B .
No card required. Start with 1 million free tokens.