Free to start

Google: Gemma 4 31B

Try Gemma 4 31B on us. Starter credit covers your first requests, then one key reaches all 13 provider routes with automatic failover.

`google/gemma-4-31b-it`

open weights US providers EU-focused Google AI Studio

All models

Publisher	Google AI Studiogoogle-ai-studio
AI IQ	IQ 101 #120 on AI IQ
Context	262,144 tokens
Providers	TinfoilTrusted Confidential ZDR Parasail ZDR Sail Research ZDR Regolo ZDR Greenference ZDR Crusoe FriendliAI Novita AI SiliconFlow DigitalOcean Gradient AI Weights & Biases IO Intelligence DeepInfra
Credits routes	13 provider routes
Modes	chat open weights US providers EU-focused
Billing	Credits

Current route evidence

Live leaderboard

$0.1055/1MLowest Credits input price

$0.3587/1MLowest Credits output price

1333 msFastest measured p50 TTFT via tinfoil

79 tok/sHighest measured throughput via tinfoil

Recent provider-route uptime spans 75.00% to 100.00% across 13 routes and 13 providers. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.

All route prices All providers Performance details

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. Company country is separate from inference location. Weight formats are source-backed declarations, not per-request proofs.

Provider	Input	Cached input	Output	Weight format	Provider policy	Company / inference location	Measured speed
Weights & Biaseswandb	$0.1055/1M	Not published	$0.3587/1M	Unknown	no verified privacy claim Retention details 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. Provider policy source	Operator country: US Location details 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. Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-31T07:48:42.000Z
Crusoecrusoe	$0.1477/1M	$0.1477/1M	$0.422/1M	Unknown	privacy unknown Retention details No provider-ZDR claim is tracked here. Crusoe's Managed Inference docs and pricing/catalog pages are linked for model and API data-handling review. Provider policy source	Operator country: US Location details 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. Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-31T00:10:58.000Z
FriendliAIfriendli	$0.1477/1M	Not published	$0.422/1M	Unknown	privacy unknown Retention details No provider-ZDR claim is tracked here. Friendli's legal/privacy terms are linked for users who need to review API data handling. Provider policy source	Operator country: US Location details 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. Full location evidence	TTFT: 2.54 s Speed: insufficient data Last sample: 2026-10-31T04:52:24.000Z
Novita AInovita	$0.1477/1M	Not published	$0.422/1M	Unknown	privacy unknown Retention details 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. Provider policy source	Operator country: US Location details 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. GPU rental regions (different product) Native model catalog Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-30T17:56:13.000Z
Parasailparasail	$0.15825/1M	$0.0633/1M	$0.422/1M	Unknown	ZDR Retention details 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. Provider policy source	Operator country: US Location details 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. Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-30T20:11:02.000Z
Greenferencegreenference	$0.156668/1M	$0.060927/1M	$0.4431/1M	Unknown	ZDR provider E2EE not verified Retention details Greenference SAS's DPA commits to EU-only inference, no persistent prompt/output storage and no training or secondary use. Shared prefix caches remain in volatile GPU memory until eviction or instance restart; they are not account-isolated and have no fixed maximum lifetime. Content-free operational metadata is retained. Greenference runs its own serving software on rented EU compute; this is contractual ZDR, not verified confidential compute or E2EE. Its current electricity mix is unverified, not a 100% renewable-energy commitment. Provider policy source	Operator country: FR Location details Headquarters / registered office: Not verified. Inference: EU-only inference, dynamically placed; no individual-country commitment. All inference is on Greenference-operated serving software on rented EU GPU capacity. Region pinning through TR: Select provider.only=[greenference] with allow_fallbacks=false to restrict this route. Reviewed 2026-10-09. EU processing and retention commitments Compute subprocessors Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-31T01:10:50.000Z
DeepInfradeepinfra	$0.211/1M	Not published	$0.422/1M	Unknown	no verified privacy claim Retention details 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. Provider policy source	Operator country: US Location details 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 DeepInfra Toronto announcement Full location evidence	TTFT: insufficient data Speed: insufficient data
DigitalOcean Gradient AIdigitalocean	$0.1899/1M	$0.03798/1M	$0.5275/1M	Unknown	privacy unknown Retention details No provider-ZDR claim is tracked here. DigitalOcean's Gradient AI model and pricing documentation is linked for data-handling review. Provider policy source	Operator country: US Location details 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. Full location evidence	TTFT: insufficient data Speed: insufficient data
Sail Researchsail-research	$0.422/1M	$0.211/1M	$0.633/1M	Unknown	ZDR Retention details Sail's public DPA and security documentation provide default ZDR for inference: Sail and its subprocessors process prompts and outputs ephemerally in memory, without persistent storage or training absent written consent. Files API uploads and stateful Sailboxes are excluded. This is policy-backed ZDR, not verified confidential compute or E2EE. Provider policy source	Operator country: Not verified Location details Headquarters / registered office: Not verified. Inference: Global, dynamically placed; TrustedRouter does not enforce Sail's US-only option. Sail documents multi-region processing by default, including outside the United States. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-10-28. Data processing and residency Provider US-only option Full location evidence	TTFT: 2.42 s Speed: insufficient data Last sample: 2026-10-31T08:24:31.000Z
Tinfoiltinfoil	$0.422/1M	Not published	$1.055/1M	BF16 Published serving configuration, reviewed 2026-09-27. Per-request precision is not verified. Pinned model configuration declares BF16, with no weight quantization override in the reviewed serving command. Draft model precision is separate. KV cache: unspecified. Published serving configuration Published model router Pinned weight configuration	Confidential ZDR Retention details Tracked as a confidential inference provider with attested provider compute and no prompt/output logging claims. Provider policy source	Operator country: US Location details 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. Full location evidence	TTFT: 1.33 s 78.6 tokens/s Last sample: 2026-10-31T09:51:16.000Z
IO Intelligenceio-net	$0.4009/1M	$0.20045/1M	$1.21325/1M	Unknown	privacy unknown Retention details 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. Provider policy source	Operator country: US Location details 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) Privacy policy (operator identity, not GPU residency) Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-30T17:30:55.000Z
SiliconFlowsiliconflow	$0.79125/1M	$0.26375/1M	$1.055/1M	Unknown	privacy unknown Retention details No provider-ZDR claim is tracked here. SiliconFlow's privacy policy source is linked for retention and interaction-data terms. Provider policy source	Operator country: SG Location details 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. API documentation Privacy policy (not a GPU-location declaration) Full location evidence	TTFT: 1.67 s Speed: insufficient data Last sample: 2026-10-30T20:55:49.000Z
Regoloregolo	$0.472345/1M	Not published	$2.47981/1M	Unknown	ZDR Retention details Regolo states that inference prompts and outputs are processed in memory and discarded, with no reuse for training. This is a provider policy, not verified confidential compute or provider-side E2EE. Provider policy source	Operator country: IT Location details 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. Full location evidence	TTFT: 1.43 s Speed: insufficient data Last sample: 2026-10-30T23:57:35.000Z

Speed is the median (p50) from TR's recent measured requests for this exact model and provider, refreshed from the cached leaderboard. At least two timing samples are required; workload and network conditions affect results. Performance details

Compare Google: Gemma 4 31B

All comparisons

Google: Gemma 4 31B vs Z.ai: GLM 5.346 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.245 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.3 Flash45 combined provider routes
Google: Gemma 4 31B vs MoonshotAI: Kimi K341 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs Google: Gemma 4 31B39 combined provider routes
DeepSeek: DeepSeek V4.1 Flash vs Google: Gemma 4 31B37 combined provider routes

Questions

What model ID should I use for Google: Gemma 4 31B?

Use google/gemma-4-31b-it as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve Google: Gemma 4 31B?

TrustedRouter currently lists Tinfoil, Parasail, Sail Research, Regolo, Greenference, Crusoe, FriendliAI, Novita AI, SiliconFlow, DigitalOcean Gradient AI, Weights & Biases, IO Intelligence, and DeepInfra for Google: Gemma 4 31B. Provider availability and routing eligibility can change as catalog and health data update.

How much does Google: Gemma 4 31B cost through TrustedRouter?

The current lowest Credits input price is $0.1055/1M and the lowest Credits output price is $0.3587/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for Google: Gemma 4 31B?

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.