Gemma 4 31B API pricing

Google · Budget price tier · Apache 2.0 · released 2026-04. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.

A support ticket workload of 100K requests a month costs $50.00 on Gemma 4 31B; the next cheaper model in the Budget price tier for this workload, Hunyuan A13B Instruct, does it for $49.50. The price we quote for Gemma 4 31B has changed 4 times since 2026-08-15, most recently by +28.3% on 2026-10-15; it is now the 66th cheapest of 160 models in the Budget price tier. Buying from Modal rather than at the price we quote lowers the token price by about 49%. It holds the FinOps Friendly badge: top-40% Arena quality, top-30% Efficiency, not among the dearest 30%, and no stability flag.

• Input: $0.20 per 1M tokens
• Output: $0.40 per 1M tokens
• Batch API (in/out): Not published
• Prompt-cache read: Not published
• Context window: 262K tokens
• Arena ELO: 1443 as of 2026-11-08

Market position

On blended price ($0.34 per 1M tokens at 30% input, 70% output) it is cheaper than 59% of models in the Budget price tier: 66th cheapest of 160. Across every price tier it is cheaper than 78% of priced text models in the catalogue: 66th cheapest of 303. Its Arena ELO of 1443 ranks 48th of the 160 models that carry one, tied with 2 others, above 69% of them. With an Arena score of 1443, Gemma 4 31B clears OptimNow's Standard working quality threshold: Standard (Arena 1420+), used for meeting summary, invoice processing and call summary. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.

Licence, size and capabilities

Gemma 4 31B is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token. Its published size is 31B parameters. Listed capabilities: Text, Vision, Reasoning, Agents. Filling its 262K context window once costs $0.0524 in input tokens at list price.

Pricing by host

A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 15 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.

Cheapest host: Modal at $0.34 input / $0.10 output per 1M tokens, 49% below the price we quote on the blended price (30% input, 70% output). The dearest, SiliconFlow, charges 5.4x the cheapest.

List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest.

Monthly cost at 100K requests, by business use case

From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Google publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.

Price history

Gemma 4 31B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.10 input / $0.34 output per 1M tokens. The price we quote has changed 4 times since then. The latest change, on 2026-10-15, was +28.3% on the blended price (30% input, 70% output), to $0.20 input / $0.40 output. Net of all changes, the blended price is +26.9% against 2026-08-15.

Alternatives to Gemma 4 31B

1 of the 4 comparable models below costs less than Gemma 4 31B: MiMo-V2.6-Flash undercuts it by 30%, and scores 8 Arena points higher.

• Next cheaper model in the Budget price tier: Nex-N2.6 (nex-agi) at $0.316 blended, 7% less.
• Next more expensive: DeepSeek V3.2 (DeepSeek) at $0.344 blended, 1% more.

The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against Gemma 4 31B.

• Hy3 (Tencent): $0.132 in / $0.528 out per 1M, Arena ELO 1439 (20% more expensive, 4 ELO points lower)
• Qwen3.8 27B (Alibaba): $0.15 in / $1.875 out per 1M, Arena ELO 1436 (299% more expensive, 7 ELO points lower)
• Qwen3.6 Plus (Alibaba): $0.325 in / $1.95 out per 1M, Arena ELO 1436 (330% more expensive, 7 ELO points lower)
• MiMo-V2.6-Flash (Xiaomi): $0.14 in / $0.28 out per 1M, Arena ELO 1451 (30% cheaper, 8 ELO points higher)

• Cheapest within 15 Arena points: Gemma 4 26B A4B (Google), 72% cheaper, 9 ELO points lower, out of 43 models in that band.
• Highest Arena ELO within 20% of this price: DeepSeek V4.1 Flash (DeepSeek), 16% cheaper, 20 ELO points higher, out of 13 models in that price band.

Other models from Google

The 8 nearest to Gemma 4 31B in price, of 27 other Google models in the catalogue. Prices per 1M tokens, input then output.

• Gemma 4 26B A4B: $0.08 / $0.10
• Gemma 3 12B: $0.05 / $0.15
• Gemma 3 27B: $0.08 / $0.35
• Gemini 2.5 Flash Lite: $0.10 / $0.40
• Gemma 2 27B: $0.65 / $0.65
• Gemini 3.1 Flash Lite: $0.25 / $1.50
• Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image): $0.25 / $1.50
• Gemini 2.5 Flash: $0.30 / $2.50

All 28 Google models and prices

Common questions about Gemma 4 31B pricing

How much does Gemma 4 31B cost?

Gemma 4 31B costs $0.20 per 1M input tokens and $0.40 per 1M output tokens at DeepInfra, the host whose rate we quote. DeepInfra serves a quantized fp8 build, which is not the same product as the full-precision model. Prices as listed on 2026-11-12.

Which host is cheapest for Gemma 4 31B?

Cheapest host: Modal at $0.34 input / $0.10 output per 1M tokens, 49% below the price we quote on the blended price (30% input, 70% output). The dearest, SiliconFlow, charges 5.4x the cheapest. Host rates as listed on 2026-11-12.

Does Gemma 4 31B offer batch or cached pricing?

No. Neither a batch rate nor a prompt-cache rate is published for Gemma 4 31B as of 2026-11-12.

What would Gemma 4 31B cost per month?

With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $50 on Gemma 4 31B at the list price quoted on 2026-11-12.

Can Gemma 4 31B be self-hosted?

Yes. Gemma 4 31B is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token.

Has the price of Gemma 4 31B changed?

Gemma 4 31B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.10 input / $0.34 output per 1M tokens. The price we quote has changed 4 times since then. The latest change, on 2026-10-15, was +28.3% on the blended price (30% input, 70% output), to $0.20 input / $0.40 output. Net of all changes, the blended price is +26.9% against 2026-08-15.

Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.

These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.

Build the business case · Get a FinOps review

LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server