DeepInfra vs Google Gemini API
SEPT 2026 auditA comparison of DeepInfra and Google Gemini API built from values read directly from each provider's own documentation, with the source recorded against every figure.
The short answer
Choose DeepInfra if…
Running open-weight models at the lowest published per-token rates here — DeepSeek-V4-Flash at $0.06 per million input is a fraction of what the lab itself charges — with dedicated H100s at $2.20 an hour if throughput demands it.
Editorial · Palash Bagchi · approved
Choose Google Gemini API if…
Getting to a working prototype without a card, then staying on the cheapest frontier-adjacent rates in this set — $0.75 per million input tokens is well under half what Anthropic and OpenAI charge for their top models.
Editorial · Palash Bagchi · approved
Consider something else if…
- DeepInfra: Only some models carry per-token pricing; the rest bill for inference execution time, which is a different and harder thing to forecast.
- Google Gemini API: The rates are dated: they roughly double on 1 January 2027, free-tier content is used to improve Google's products, and rate limits are not published anywhere you can read before signing up.
17 sourced criteria separate them — see where, with sources, below.
Pick the criteria you care about. The chart counts how many of them lean toward each provider — the same read as scanning the bars below, just totalled for the ones you chose.
DeepInfra 0
Google Gemini API 0
At a glance.
| Criterion | DeepInfra | Google Gemini API |
|---|---|---|
| Pricing | ||
| Free tier | No | Yes |
| Kind of free offer | No free offer | Free tier |
| Entry paid plan | No minimum spend and no seat fees - billing is pay-per-token usage only, with no charge for idle GPU time. | $5 minimum prepaid credit to move from the Free Tier to the Paid Tier; the minimum credit purchase is $5 and the maximum $5,000. No monthly plan fee — usage is billed per token. Applies to the Prepay billing plan; some accounts are offered or assigned Postpay instead. |
| Pricing model | Two products on one bill: per-token serverless inference with a separate cached-input rate for each model, and dedicated GPUs billed per minute and invoiced weekly. Models without per-token pricing are billed for inference execution time instead. | Per million tokens, with dated price changes published in advance — the current Gemini 3.x rates are explicitly promotional through 31 December 2026 and roughly double on 1 January 2027. A free tier exists, and its content is used to improve Google's products where the paid tier's is not. |
| Infrastructure | ||
| Regions | Serverless inference runs on DeepInfra's own inference-optimised infrastructure in US-based data centers. No region selector is documented for the shared inference API. | Google publishes availability as a country list rather than deployment regions: the Gemini API and Google AI Studio are listed as available in 230 countries and territories, counted from the page's own list, which publishes no total. Country and territory availability for access, not a choice of data region. |
| Inference | ||
| Input price, top model | $1.30 per million input tokens for DeepSeek-V4-Pro, the most expensive model in its catalogue. Cached input is $0.10. | $0.75 per million input tokens for Gemini 3.8 Flash through 31 December 2026, then $1.50. Gemini 3.1 Pro, still preview, is $2.00 for prompts up to 200k tokens and $4.00 above. |
| Output price, top model | $2.60 per million output tokens for DeepSeek-V4-Pro. | $3.75 per million output tokens for Gemini 3.8 Flash through 31 December 2026, then $7.50. Thinking tokens are billed as output. |
| Input price, cheapest model | $0.06 per million input tokens for DeepSeek-V4-Flash-0731, with cached input at $0.015 and output at $0.18. DeepSeek itself charges $0.44 at peak for the same checkpoint and Fireworks $0.22. | $0.30 per million input tokens for Gemini 3.5 Flash-Lite, with output at $2.50. |
| Context window | 1024k tokens on the DeepSeek V4 models it serves; 160k on the V3 generation. The window is the model's rather than a platform limit. | 1,048,576 tokens for Gemini 3.8 Flash. Read from the Vertex AI model card: the Gemini API docs build their model cards client-side and publish no figure a fetch can read. |
| Max output tokens | Hard cap of 16384 output tokens per response for most models on the chat completions API; the exact limit is model-dependent. | 65,536 tokens for Gemini 3.8 Flash, and Google counts thinking tokens as output. |
| Prompt caching | Supported | Supported |
| Batch discount | Batch API jobs are billed 20% below real-time pricing, with results returned within 24 hours. | 50% off through the Batch API, which is a paid-tier feature. |
| Rate limits | Default 200 concurrent requests per model per account (429 above it); a limit increase can be requested in the dashboard. | Tied to a usage tier — Free, then Tier 1/2/3 unlocked by cumulative spend — and enforced as requests per minute, input tokens per minute and requests per day. Google publishes no numbers in the docs: limits are viewed in AI Studio and are stated not to be guaranteed. |
| Compliance | ||
| ISO 27001 | Security measures stated to comply with ISO 27001 standards in the privacy policy; no certificate or issuing body is published. | Google commits to maintain ISO/IEC 27001:2013 certification for the Processor Services, which include Gemini API Paid Services. Contractual commitment in the DPA the Gemini API terms incorporate, not a Gemini-specific ISO certificate. |
| GDPR / data residency | Privacy Policy: data may be transferred, stored and processed outside your jurisdiction, specifically in the United States; EU residents keep GDPR rights. | Processed under Google's Data Processing Addendum on the paid tier; abuse-detection logs may be stored or cached in any country where Google has facilities. Scope: the logs Google keeps for Paid Services to detect Prohibited Use Policy violations. |
| Encryption at rest | Inference inputs and outputs are not stored to disk; bulk-inference data may be stored on disk in encrypted form, then deleted. | Google security policies mandate encryption at rest for all user data; personal data is encrypted at the storage level, generally using AES256. From the processor DPA that the Gemini API Additional Terms incorporate for Paid Services. |
| Role-based access control | Team roles are member and admin; an admin can change roles, but all team members share the same API tokens and models. | The only IAM role published for the Gemini API is a service agent role for GCS reads; the reference states there are no IAM permissions for the service. |
| Dedicated infrastructure | Private model deployments run on dedicated GPU infrastructure - your weights, your endpoint, your isolation - not shared with other users. | Provisioned throughput is offered as optional access on the Enterprise tier, which the pricing page says is powered by Gemini Enterprise Agent Platform. |
Where they differ.
Free tier
- DeepInfra
- No
- Google Gemini API
- Yes
Sources (2) →Sources ↓
- Simple Pricing | Machine Learning Infrastructure | DeepInfra ↗
“You have to add a card or pre-pay [...] Pre-paid accounts draw down their balance as they go, and invoiced accounts are billed once at the beginning of the following month.”
Read 2026-09-13 · official pricing · Report a correction
- Gemini Developer API Pricing ↗
“Free input & output tokens [...] Limited access to certain models [...] Google AI Studio access [...] Content used to improve our products [...] Get started for Free”
Read 2026-09-06 · official pricing · Report a correction
Kind of free offer
- DeepInfra
- No free offer
- Google Gemini API
- Free tier
Sources (2) →Sources ↓
- Simple Pricing | Machine Learning Infrastructure | DeepInfra ↗
“You have to add a card or pre-pay [...] Pre-paid accounts draw down their balance as they go, and invoiced accounts are billed once at the beginning of the following month.”
Read 2026-09-13 · official pricing · Report a correction
- Gemini Developer API Pricing ↗
“Free input & output tokens [...] Limited access to certain models [...] Google AI Studio access [...] Content used to improve our products [...] Get started for Free”
Read 2026-09-06 · official pricing · Report a correction
Entry paid plan
- DeepInfra
- No minimum spend and no seat fees - billing is pay-per-token usage only, with no charge for idle GPU time.
- Google Gemini API
- $5 minimum prepaid credit to move from the Free Tier to the Paid Tier; the minimum credit purchase is $5 and the maximum $5,000. No monthly plan fee — usage is billed per token. Applies to the Prepay billing plan; some accounts are offered or assigned Postpay instead.
Sources (2) →Sources ↓
- What is DeepInfra - DeepInfra ↗
“You only pay per token - no idle GPU time, no minimums, no seat fees.”
Read 2026-09-13 · official docs · Report a correction
- Billing | Gemini API | Google AI for Developers ↗
“Upgrading from the Free Tier to the Paid Tier means linking a billing account and prepaying to add a minimum of $5 (or equivalent in other currencies) of credits to your account. [...] The minimum purchase is $5. The maximum amount of credits you can prepay for is $5,000.”
Read 2026-09-13 · official docs · Report a correction
Pricing model
- DeepInfra
- Two products on one bill: per-token serverless inference with a separate cached-input rate for each model, and dedicated GPUs billed per minute and invoiced weekly. Models without per-token pricing are billed for inference execution time instead.
- Google Gemini API
- Per million tokens, with dated price changes published in advance — the current Gemini 3.x rates are explicitly promotional through 31 December 2026 and roughly double on 1 January 2027. A free tier exists, and its content is used to improve Google's products where the paid tier's is not.
Sources (2) →Sources ↓
- Pricing — DeepInfra ↗
“Some of our langauge models offer per token pricing. Most other models are billed for inference execution time. [...] Billed in minute granularity Invoiced weekly”
Read 2026-09-06 · official pricing · Report a correction
- Gemini Developer API Pricing ↗
“Paid Tier, per 1M tokens in USD [...] $0.75 through December 31, 2026. $1.50 starting January 1, 2027. [...] Used to improve our products | Yes | No”
Read 2026-09-06 · official pricing · Report a correction
Regions
- DeepInfra
- Serverless inference runs on DeepInfra's own inference-optimised infrastructure in US-based data centers. No region selector is documented for the shared inference API.
- Google Gemini API
- Google publishes availability as a country list rather than deployment regions: the Gemini API and Google AI Studio are listed as available in 230 countries and territories, counted from the page's own list, which publishes no total. Country and territory availability for access, not a choice of data region.
Sources (2) →Sources ↓
- Machine Learning Models and Infrastructure | DeepInfra ↗
“DeepInfra runs on our own cutting-edge inference optimised infrastructure, in secure US-based data centers.”
Read 2026-09-13 · official site · Report a correction
- Available regions for Google AI Studio and Gemini API | Google AI for Developers ↗
“The Gemini API and Google AI Studio are available in the following countries and territories.”
Read 2026-09-13 · official docs · Report a correction
Input price, top model
- DeepInfra
- $1.30 per million input tokens for DeepSeek-V4-Pro, the most expensive model in its catalogue. Cached input is $0.10.
- Google Gemini API
- $0.75 per million input tokens for Gemini 3.8 Flash through 31 December 2026, then $1.50. Gemini 3.1 Pro, still preview, is $2.00 for prompts up to 200k tokens and $4.00 above.
Sources (2) →Sources ↓
- Pricing — DeepInfra ↗
“DeepSeek-V4-Pro 1024k $1.30 / $0.10 cached $2.60”
Read 2026-09-06 · official pricing · Report a correction
- Gemini Developer API Pricing ↗
“Gemini 3.8 Flash [...] Input price | Free of charge | $0.75 through December 31, 2026. $1.50 starting January 1, 2027. [...] Gemini 3.1 Pro Preview [...] Input price | Not available | $2.00, prompts <= 200k tokens $4.00, prompts > 200k tokens”
Read 2026-09-06 · official pricing · Report a correction
Output price, top model
- DeepInfra
- $2.60 per million output tokens for DeepSeek-V4-Pro.
- Google Gemini API
- $3.75 per million output tokens for Gemini 3.8 Flash through 31 December 2026, then $7.50. Thinking tokens are billed as output.
Sources (2) →Sources ↓
- Pricing — DeepInfra ↗
“DeepSeek-V4-Pro 1024k $1.30 / $0.10 cached $2.60”
Read 2026-09-06 · official pricing · Report a correction
- Gemini Developer API Pricing ↗
“Output price (including thinking tokens) | Free of charge | $3.75 through December 31, 2026. $7.50 starting January 1, 2027.”
Read 2026-09-06 · official pricing · Report a correction
Input price, cheapest model
- DeepInfra
- $0.06 per million input tokens for DeepSeek-V4-Flash-0731, with cached input at $0.015 and output at $0.18. DeepSeek itself charges $0.44 at peak for the same checkpoint and Fireworks $0.22.
- Google Gemini API
- $0.30 per million input tokens for Gemini 3.5 Flash-Lite, with output at $2.50.
Sources (2) →Sources ↓
- Pricing — DeepInfra ↗
“DeepSeek-V4-Flash-0731 1024k $0.06 / $0.015 cached $0.18”
Read 2026-09-06 · official pricing · Report a correction
- Gemini Developer API Pricing ↗
“Gemini 3.5 Flash-Lite [...] Input price | Free of charge | $0.30 (text / image / video / audio) Output price (including thinking tokens) | Free of charge | $2.50”
Read 2026-09-06 · official pricing · Report a correction
Context window
1024k tokens on the DeepSeek V4 models it serves; 160k on the V3 generation. The window is the model's rather than a platform limit.
1,048,576 tokens for Gemini 3.8 Flash. Read from the Vertex AI model card: the Gemini API docs build their model cards client-side and publish no figure a fetch can read.
Sources (2) →Sources ↓
- Pricing — DeepInfra ↗
“DeepSeek-V4-Pro 1024k [...] DeepSeek-V3.2 160k $0.26 / $0.13 cached $0.38”
Read 2026-09-06 · official pricing · Report a correction
- Gemini 3.8 Flash — Vertex AI model card, Google Cloud ↗
“Token limits Context window 1,048,576 Maximum output tokens 65,536”
Read 2026-09-06 · official docs · Report a correction
Max output tokens
- DeepInfra
- Hard cap of 16384 output tokens per response for most models on the chat completions API; the exact limit is model-dependent.
- Google Gemini API
- 65,536 tokens for Gemini 3.8 Flash, and Google counts thinking tokens as output.
Sources (2) →Sources ↓
- Chat Completions - DeepInfra ↗
“The maximum number of tokens that can be generated in a single response is model-dependent, with a hard cap of 16384 tokens for most models.”
Read 2026-09-13 · official docs · Report a correction
- Gemini 3.8 Flash — Vertex AI model card, Google Cloud ↗
“Token limits Context window 1,048,576 Maximum output tokens 65,536”
Read 2026-09-06 · official docs · Report a correction
Batch discount
- DeepInfra
- Batch API jobs are billed 20% below real-time pricing, with results returned within 24 hours.
- Google Gemini API
- 50% off through the Batch API, which is a paid-tier feature.
Sources (2) →Sources ↓
- Introduction to Batch API - DeepInfra ↗
“get the results back within 24 hours, billed at 20% below real-time pricing”
Read 2026-09-13 · official docs · Report a correction
- Gemini Developer API Pricing ↗
“Batch API (50% cost reduction) [...] Access to Context caching”
Read 2026-09-06 · official pricing · Report a correction
Rate limits
- DeepInfra
- Default 200 concurrent requests per model per account (429 above it); a limit increase can be requested in the dashboard.
- Google Gemini API
- Tied to a usage tier — Free, then Tier 1/2/3 unlocked by cumulative spend — and enforced as requests per minute, input tokens per minute and requests per day. Google publishes no numbers in the docs: limits are viewed in AI Studio and are stated not to be guaranteed.
Sources (2) →Sources ↓
- Rate Limits - DeepInfra ↗
“Every account has a default limit of 200 concurrent requests per model [...] You can request a rate limit increase in your”
Read 2026-09-13 · official docs · Report a correction
- Rate limits — Gemini API ↗
“Rate limits depend on a variety of factors (such as your usage tier) and can be viewed in Google AI Studio. [...] Specified rate limits are not guaranteed and actual capacity may vary. [...] Usage tier | Qualification | Billing tier cap Free | Active project or free trial | N/A Tier 1 | Set up and link an active billing account | $250”
Read 2026-09-06 · official docs · Report a correction
ISO 27001
- DeepInfra
- Security measures stated to comply with ISO 27001 standards in the privacy policy; no certificate or issuing body is published.
- Google Gemini API
- Google commits to maintain ISO/IEC 27001:2013 certification for the Processor Services, which include Gemini API Paid Services. Contractual commitment in the DPA the Gemini API terms incorporate, not a Gemini-specific ISO certificate.
Sources (2) →Sources ↓
- Privacy Policy — DeepInfra ↗
“Our security measures comply with SOC 2 and ISO 27001 standards and include technical and organizational measures for GDPR and HIPAA”
Read 2026-09-13 · official site · Report a correction
- Data Processing Addendum for Products Where Google is a Data Processor ↗
“means ISO/IEC 27001:2013 certification or a comparable certification for the Processor Services. [...] 7.4 Security Certification. To evaluate and help ensure the continued effectiveness of the Security Measures, Google will maintain the ISO 27001 Certification or other appropriate measures to demonstrate the effectiveness of the Security Measures.”
Read 2026-09-13 · official site · Report a correction
GDPR / data residency
- DeepInfra
- Privacy Policy: data may be transferred, stored and processed outside your jurisdiction, specifically in the United States; EU residents keep GDPR rights.
- Google Gemini API
- Processed under Google's Data Processing Addendum on the paid tier; abuse-detection logs may be stored or cached in any country where Google has facilities. Scope: the logs Google keeps for Paid Services to detect Prohibited Use Policy violations.
Sources (2) →Sources ↓
- DeepInfra Privacy Policy ↗
“Your data may be transferred, stored, and processed outside of your jurisdiction, specifically in the United States. [...] If you are a resident of the European Union you may have additional rights under the General Data Protection Regulation.”
Read 2026-09-13 · official site · Report a correction
- Gemini API Additional Terms of Service | Google AI for Developers ↗
“will process your prompts and responses in accordance with the Data Processing Addendum for Products Where Google is a Data Processor [...] This data may be stored transiently or cached in any country in which Google or its agents maintain facilities.”
Read 2026-09-13 · official site · Report a correction
Encryption at rest
- DeepInfra
- Inference inputs and outputs are not stored to disk; bulk-inference data may be stored on disk in encrypted form, then deleted.
- Google Gemini API
- Google security policies mandate encryption at rest for all user data; personal data is encrypted at the storage level, generally using AES256. From the processor DPA that the Gemini API Additional Terms incorporate for Paid Services.
Sources (2) →Sources ↓
- Data Privacy - DeepInfra ↗
“Input data is not stored to disk during inference [...] we may need to store data for a longer period, potentially on disk in encrypted form”
Read 2026-09-13 · official docs · Report a correction
- Data Processing Addendum for Products Where Google is a Data Processor ↗
“Google's security policies mandate encryption at rest for all user data, including personal data. [...] All personal data is encrypted at the storage level, generally using AES256.”
Read 2026-09-13 · official site · Report a correction
Role-based access control
- DeepInfra
- Team roles are member and admin; an admin can change roles, but all team members share the same API tokens and models.
- Google Gemini API
- The only IAM role published for the Gemini API is a service agent role for GCS reads; the reference states there are no IAM permissions for the service.
Sources (2) →Sources ↓
- Okta SSO - DeepInfra ↗
“Admin can change team member roles (member / admin) [...] All team members share the same API tokens and models [...] For per-user isolation (separate tokens and models per person), contact us”
Read 2026-09-13 · official docs · Report a correction
- Gemini API roles and permissions | Identity and Access Management (IAM) | Google Cloud Documentation ↗
“Gemini API offers the following service agent roles. [...] There are no IAM permissions for this service.”
Read 2026-09-13 · official docs · Report a correction
Dedicated infrastructure
- DeepInfra
- Private model deployments run on dedicated GPU infrastructure - your weights, your endpoint, your isolation - not shared with other users.
- Google Gemini API
- Provisioned throughput is offered as optional access on the Enterprise tier, which the pricing page says is powered by Gemini Enterprise Agent Platform.
Sources (2) →Sources ↓
- Deploy Private Models - DeepInfra ↗
“DeepInfra allows you to deploy your own models on dedicated infrastructure [...] data stays on dedicated infrastructure, not shared with other users”
Read 2026-09-13 · official docs · Report a correction
- Gemini Developer API pricing | Gemini API | Google AI for Developers ↗
“For enterprise deployments, powered by Gemini Enterprise Agent Platform [...] All features in Paid, plus optional access to: [...] Provisioned throughput”
Read 2026-09-13 · official pricing · Report a correction
When these numbers change, hear about it. Sources are re-checked monthly; a repricing goes out as a short note.
Documented by only one.
These criteria are published by one provider and not the other. An absence here means we have not found a source, not that the feature is missing — except where we say we read the other provider's own page on a given date and it does not state it. Those rows lean, and the provider can correct them with a link.
Questions this comparison answers.
Entry paid plan: DeepInfra or Google Gemini API?
DeepInfra: No minimum spend and no seat fees - billing is pay-per-token usage only, with no charge for idle GPU time.
Google Gemini API: $5 minimum prepaid credit to move from the Free Tier to the Paid Tier; the minimum credit purchase is $5 and the maximum $5,000. No monthly plan fee — usage is billed per token. Applies to the Prepay billing plan; some accounts are offered or assigned Postpay instead.
Free tier: DeepInfra or Google Gemini API?
DeepInfra: No
Google Gemini API: Yes
Should I choose DeepInfra or Google Gemini API?
Pick DeepInfra if Running open-weight models at the lowest published per-token rates here — DeepSeek-V4-Flash at $0.06 per million input is a fraction of what the lab itself charges — with dedicated H100s at $2.20 an hour if throughput demands it.
Pick Google Gemini API if Getting to a working prototype without a card, then staying on the cheapest frontier-adjacent rates in this set — $0.75 per million input tokens is well under half what Anthropic and OpenAI charge for their top models.
Comments are hosted by EchoThread, which sets cookies and offers social sign-in. Like the analytics on this site, it does not load until you accept — see the privacy page.