Gemma 3 27B API Pricing / Price per 1M tokens
Gemini(Google) • API Price Comparison
Also known as: google-gemini-gemma-3-27b-it · google gemini gemma 3 27b it · googlegeminigemma327bit · google-gemini-gemma3-27b-it · google gemini gemma3 27b it · gemma-3-27b · gemma327b · gemma3-27b · gemma3 27b
API pricing and token costs at a glance
Updated on · Published currencies / per 1M tokens; cheapest ranked by input
| Channel | Input / 1M | Output / 1M | Cache read / 1M | Updated / verified on |
|---|---|---|---|---|
| Official | No official quote recorded | |||
| OpenRouterLowest input | USD 0.08 | USD 0.35 | USD 0.04 | 2026-10-31 |
Metered API cost = input tokens / 1M × input rate + output tokens / 1M × output rate. At the lowest-input-rate channel, 1M input plus 250K output tokens costs approximately USD 0.16749999999999998. This excludes caching, tools, retries and other service fees; the lowest input rate does not guarantee the lowest total bill.
— means the price or date is not recorded. Cross-currency ranking uses exchange rates.
Gemma 3 27B is a large language model by Gemini(Google) with a 128K-token context window. Across the 1 API channels tracked here, input pricing ranges from $0.08 per 1M input tokens; the cheapest is OpenRouter at $0.08 per 1M input tokens. None of the tracked channels are directly reachable from mainland China without a proxy or VPN. It is also available through subscription plans such as Gemini Free, Gemini Code Assist Individual, Gemini Code Assist Standard, Gemini Code Assist Enterprise. Prices are collected daily from official provider pages and every tracked channel, then cross-checked by a data-accuracy audit.
Model performance benchmarks
Scores retain their original benchmark, version and metric. We do not combine them into a site-wide score; results from different versions are not directly comparable.
💳 Subscription Plans
Plans from Gemini(Google) come first, followed by linked third-party plans; each group is organized by product line.
Official plans
These are the model producer’s plans. A plan may not include this exact model; check the official site for current model availability and allowances.
💬 Chat subscriptions
5 plansMonthly access to the assistant apps and their model line-up.
- Plan price: S$0.00/month
- Payment methods: Credit card / Debit card / Google Pay
Conditions and details
- Currency SGD, unit per month
- Published free tier
- EstimateFeatures, message caps, context and rate limits come from the same plan row; lines marked Estimate are not guaranteed allowances
- Does the subscription allowance cover third-party models?: Unknown
Conditions and details
- Currency USD, unit per month
- On 2026-10-18 the public Gemini subscriptions HTML listed Google AI Plus at $4.99/month.
- That figure is not stored here and is not a confirmed list price
- EstimateFeatures, message caps, context and rate limits come from the same plan row; lines marked Estimate are not guaranteed allowances
- Does the subscription allowance cover third-party models?: Unknown
- Plus/Pro US price not identified on the page; prices withheld.
Conditions and details
- Currency USD, unit per month
- On 2026-10-18 the public Gemini subscriptions HTML listed $19.99/month next to about 4x Free usage, the tier above Plus.
- This row is still an unknown price
- EstimateFeatures, message caps, context and rate limits come from the same plan row; lines marked Estimate are not guaranteed allowances
- Does the subscription allowance cover third-party models?: Unknown
- Plus/Pro US price not identified on the page; prices withheld.
- Plan price: $99.99/month
- Payment methods: Credit card / Debit card / Google Pay
Conditions and details
- Currency USD, unit per month
- EstimateFeatures, message caps, context and rate limits come from the same plan row; lines marked Estimate are not guaranteed allowances
- Does the subscription allowance cover third-party models?: Unknown
- US consumer tier.
- Plan price: $199.99/month
Conditions and details
- Currency USD, unit per month
- EstimateFeatures, message caps, context and rate limits come from the same plan row; lines marked Estimate are not guaranteed allowances
- Does the subscription allowance cover third-party models?: Unknown
- US consumer tier.
⌨️ Coding plans
3 plansEditor and CLI coding agents, metered in prompts rather than tokens.
- Recorded plan allowance: 1000 requests per day
- Plan price: $0.00/month
- Accessible from mainland China
Conditions and details
- Currency USD, unit per month
- Published free tier
- EstimateFeatures, message caps, context and rate limits come from the same plan row; lines marked Estimate are not guaranteed allowances
- Does the subscription allowance cover third-party models?: Unknown
- Available in China
- Free.
- 6000 code completions + 240 chats/day.
- Gemini 2.5 now, Gemini 3 waitlist.
- IDE plugin (VSCode/JetBrains/Android Studio).
- Recorded plan allowance: 1500 requests per day
- Plan price: $22.80/month
- Billed annually $228.00
- Accessible from mainland China
Conditions and details
- Currency USD, unit per month
- EstimateFeatures, message caps, context and rate limits come from the same plan row; lines marked Estimate are not guaranteed allowances
- Does the subscription allowance cover third-party models?: Unknown
- Available in China
- Per-user.
- $22.80/mo month-to-month or $19/mo annual.
- 1500 model requests/day shared CLI+Agent.
- Gemini 2.5 + Gemini 3 waitlist.
- Recorded plan allowance: 2000 requests per day
- Plan price: $54.00/month
- Billed annually $540.00
- Accessible from mainland China
Conditions and details
- Currency USD, unit per month
- EstimateFeatures, message caps, context and rate limits come from the same plan row; lines marked Estimate are not guaranteed allowances
- Does the subscription allowance cover third-party models?: Unknown
- Available in China
- Per-user.
- $54/mo month-to-month or $45/mo annual.
- 2000 model requests/day.
- Private repo customization (GitHub/GitLab/Bitbucket) + Apigee.
Which plan is right for you?
💬 Chat subscriptions: Monthly access to the assistant apps and their model line-up.
⌨️ Coding plans: Editor and CLI coding agents, metered in prompts rather than tokens.
| Channel | Type | Input / 1M | Output / 1M | Rate Limit | China | vs Official | |
|---|---|---|---|---|---|---|---|
OpenRouter6 variants💰 Best Price | Aggregator | $0.08 | $0.35 | - | - | - | |
Show all price variants for this channelOpenRouter Auto / default routeDefault $0.08 / $0.35 per 1M default_route Cheapest endpoint: DeepInfra $0.08 / $0.16 per 1M cheapest_endpoint DeepInfra | google/gemma-3-27b-it $0.08 / $0.16 per 1M upstream_provider NextBit | google/gemma-3-27b-it $0.08 / $0.35 per 1M upstream_provider Nebius | google/gemma-3-27b-it $0.10 / $0.30 per 1M upstream_provider Novita | google/gemma-3-27b-it $0.12 / $0.20 per 1M upstream_provider | |||||||
| Usage Level | Tokens/Month | OpenRouter |
|---|---|---|
| 🐣 Light | 0.1M in + 0.1M out | $0.03 |
| 📊 Medium | 1.0M in + 0.5M out | $0.26 |
| 🚀 Heavy | 10.0M in + 5.0M out | $2.55 |
| 🏢 Enterprise | 100.0M in + 50.0M out | $25.50 |
Frequently asked questions about gemma-3-27b
How much does the Gemma 3 27B API cost?
The lowest input rate is USD 0.08 per 1M tokens; output on that channel is USD 0.35 per 1M tokens.
Which channel has the cheapest Gemma 3 27B API?
OpenRouter has the lowest input rate: USD 0.08 per 1M tokens. Cross-currency ranking uses exchange rates; compare output and cache prices separately.
What is the Gemma 3 27B cache-read price?
OpenRouter: USD 0.04 per 1M cache-read tokens.
When was Gemma 3 27B pricing last updated?
Updated on 2026-10-31. This is the latest recorded price update or verification; see the table for individual channel dates.
Is there a free Gemma 3 27B API?
No available recorded channel lists both input and output at zero. Missing prices, free cache reads or a free chat tier do not establish a free API; check provider terms for trial credits.
How do I calculate Gemma 3 27B token costs and monthly spend?
Metered API cost = input tokens / 1M × input rate + output tokens / 1M × output rate. At the lowest-input-rate channel, 1M input plus 250K output tokens costs approximately USD 0.16749999999999998. This excludes caching, tools, retries and other service fees; the lowest input rate does not guarantee the lowest total bill.