StatusOperational Live status
LLMAPI discountUp to −25%
Models on LLMAPI11
From$0.18 / 1M blended
RegionsGlobal
Best uptime (24h)100.00%
Verdict
Google offers the Gemini family of multimodal models with long context support, available through AI Studio for developers and Vertex AI for enterprises. Through LLMAPI you reach 7 Google models on the same OpenAI-compatible endpoint as every other provider, so switching between them is a one-string change.
Good fit for
- Text Generation
- Vision / Image Understanding
- Multimodal (any-to-any)
- Long Context
- Cheapest per Token
- Best Price-to-Performance
Consider another provider for
- No code generation models in this catalog
- No image generation models in this catalog
- No video generation models in this catalog
- No video understanding models in this catalog
Key facts
Where a provider does not document something we say so rather than guess. Everything LLMAPI records about Google, in one table.
Overview | |
| Provider | |
| Website | google.com |
| Best for | Multimodal workloads and very long context at aggressive price points |
| Models on LLMAPI | 11 |
| Popular models | Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash Lite, Gemini 3.5 Flash, Gemini 3.1 Flash Lite |
Access & routing | |
| API compatibility | OpenAI-compatible — /v1/chat/completions |
| Model ID prefix | google/<model> |
| Regions | Global |
| Fallback | Configurable — on 429 or 5xx the router switches to any other model or provider on your list |
| Billing | One invoice across every provider, with per-key spend limits |
| Volume discount | Eligible |
Performance (median across listed models) | |
| Blended price / 1M | $1.5 |
| Uptime (24h) | 99.89% (median across listed models) |
Modality | |
| Tags | |
Capability | |
| Tags | |
Price & performance | |
| Tags | |
Workflow | |
| Tags | |
Audience | |
| Tags | |
Privacy & data | |
| Inference location | US, EU and multi-region endpoints |
| Data residency | Regional endpoints for EU and other locations |
| Default retention | Prompt logging off by default on paid tiers |
| Zero-data retention | Default No prompt storage on paid API tiers by default |
| Training on API data | No Paid tier data is not used to train models |
| Human review | Only where abuse review applies |
Compliance & lifecycle | |
| Certifications | SOC 2 · ISO 27001 · GDPR DPA · HIPAA BAA available |
| Deprecation notice | Versioned models with published retirement dates |
| Operational status | Operational Live status |
Prices and context from the OpenRouter public catalogue; uptime and output speed from OpenRouter provider endpoints; quality scores from LiveBench. Refreshed nightly — last updated 2026-09-29. — means no figure is published for that model.
Best Google models
A quick view of how Google 's 7 models compare on intelligence, output speed and price — so you can pick the right one for your use case.
Most intelligent
#1text-embedding-00441
#2Gemma 3 27B36
#3Gemini 2.5 Pro33
#4Gemma 3n30
Intelligence index · 7 models
Fastest
#1Gemma 3n409 t/s
#2Gemma 3 27B326 t/s
#3text-embedding-004290 t/s
#4Gemini 2.5 Flash-Lite239 t/s
Output tokens / second · 7 models
Lowest price
#1Gemini 2.5 Flash-Lite$3.71
#2text-embedding-004$3.81
#3Gemini 2.5 Pro$6.00
#4Gemma 3 27B$6.31
Blended price per 1M tokens · 7 models
Compared with other hosts
How Google sits against the rest of the catalog, using the same measurements shown on every provider page.
- Price. Median blended price of $6.31 per 1M tokens — 3% above the $6.13 median across all 50 providers in the catalog.
- Throughput. Median output speed of 239 tokens/s, 31% slower than the 348 tok/s catalog median.
- Catalog depth. 7 models listed, against a catalog average of 5 per provider.
- Integration. Identical to every other provider here — same endpoint, same SDK, same keys, so a switch costs one string change.
Median blended price per 1M tokens
lower is better| $6.31 | ||
| Alibaba Cloud | $6.23 | |
| Wafer | $6.22 | |
| SambaNova | $6.20 | |
| Arcee AI | $6.07 | |
| Anthropic | $6.63 |
Median output speed
higher is better| 239 tok/s | ||
| Alibaba Cloud | 150 tok/s | |
| Wafer | 303 tok/s | |
| SambaNova | 954 tok/s | |
| Arcee AI | 369 tok/s | |
| Anthropic | 365 tok/s |
Figures are medians across the models listed on each provider page and are refreshed with the catalog.
Models & pricing
Every Google model reachable with your LLMAPI key. Click a column heading to sort.
| Model | API model name | Uptime 24h | Price / 1M | Context |
|---|---|---|---|---|
| Gemini 3.8 Flash | gemini-3.8-flash | 99.16% | $ 1.5 | 1000 k |
| Gemini 3.7 Flash | gemini-3.7-flash | 99.89% | $ 1.5 | 1049 k |
| Gemini 3.6 Flash | gemini-3.6-flash | 100.00% | $ 1.5 | 1049 k |
| Gemini 3.5 Flash Lite | gemini-3.5-flash-lite | 99.97% | $ 0.85 | 1049 k |
| Gemini 3.5 Flash | gemini-3.5-flash | 99.95% | $ 3.38 | 1049 k |
| Gemini 3.1 Flash Lite | gemini-3.1-flash-lite | 99.99% | $ 0.56 | 1049 k |
| Gemini 3.1 Pro (Preview) | gemini-3.1-pro-preview | 100.00% | $ 4.5 | 1049 k |
| Gemini 3 Flash (Preview) | gemini-3-flash-preview | 99.63% | $ 1.13 | 1049 k |
| Gemini 2.5 Flash Lite | gemini-2.5-flash-lite | 99.54% | $ 0.18 | 1049 k |
| Gemini 2.5 Flash | gemini-2.5-flash | 90.06% | $ 0.85 | 1049 k |
| Gemini 2.5 Pro | gemini-2.5-pro | 93.51% | $ 3.44 | 1049 k |
Price is a blended per-1M-token figure; latency is time to first token and throughput is output tokens per second, measured on the LLMAPI edge.
Cost calculator
Pick a model, enter your traffic, and see the monthly bill at LLMAPI rates.
Estimates use the blended per-1M-token price shown in the table above. Word counts differ by language — Cyrillic and CJK text uses 2–3× more tokens per word.
Google via LLMAPI
Same models, same features, one key. Prefix the model ID with google/ and point your OpenAI client at our base URL.
# Python · OpenAI SDK from openai import OpenAI client = OpenAI( base_url="https://api.llmapi.ai/v1", api_key="LLMAPI_KEY", ) r = client.chat.completions.create( model="google/gemini-2-5-pro", messages=[{"role": "user", "content": "Hello"}], )
| Pricing | Eligible for LLMAPI volume discounts; billed on one invoice with every other provider. |
| Features | Full pass-through — tool calling, JSON schema, streaming, vision and reasoning behave exactly as on Google’s own API. |
| Fallback | Configurable. On 429 or 5xx the router switches to any model or provider on your fallback list. |
| Regions | Global |
| Your data | LLMAPI stores request metadata only — model, token counts, latency and status. No prompt or completion content. |
Capabilities & use cases
Each tag below is its own catalog page listing every provider that shares it.
Developer resources
Where to go next.
Join thousands of developers building on one API key
Every provider in the catalog, one key, one invoice.
Questions
How do I call Google models through LLMAPI?
Point any OpenAI-compatible client at https://api.llmapi.ai/v1 and use the model ID google/gemini-2-5-pro. No other change is needed.
Does Google cost more through LLMAPI?
No. This provider is eligible for LLMAPI volume discounts, so heavy usage lands below list price.
Which regions are used?
Global
What happens if the provider returns an error?
On 429 or 5xx responses the router falls back to any other model or provider on your configured list, so requests keep succeeding.
How many Google models are available?
7 at the moment, all listed in the models table above and updated as the provider ships new ones.
Related providers
Providers covering similar use cases.