Gemma 4 26B A4B 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 $17.00 on Gemma 4 26B A4B; the next cheaper model in the Budget price tier for this workload, Granite 4.2 8B, does it for $16.50. The price we quote for Gemma 4 26B A4B has changed 28 times since 2026-08-15, most recently on 2026-11-10 when the quoted host changed (-60.3%); it is now the 12th cheapest of 160 models in the Budget price tier. Buying from PrimeIntellect rather than at the price we quote lowers the token price by about 65%. It holds the FinOps Friendly badge: top-40% Arena quality, top-30% Efficiency, not among the dearest 30%, and no stability flag.

• Input: $0.08 per 1M tokens
• Output: $0.10 per 1M tokens
• Batch API (in/out): Not published
• Prompt-cache read: $0.046 per 1M tokens
• Context window: 262K tokens
• Arena ELO: 1434 as of 2026-11-08

Market position

On blended price ($0.094 per 1M tokens at 30% input, 70% output) it is cheaper than 93% of models in the Budget price tier: 12th cheapest of 160. Across every price tier it is cheaper than 96% of priced text models in the catalogue: 12th cheapest of 303. Its Arena ELO of 1434 ranks 62nd of the 160 models that carry one, tied with one other, above 61% of them. With an Arena score of 1434, Gemma 4 26B A4B 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 26B A4B 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 26B parameters. Listed capabilities: Text, Vision, Reasoning, Agents. Filling its 262K context window once costs $0.021 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: PrimeIntellect at $0.014 input / $0.041 output per 1M tokens, 65% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $4.15 there against $17.00 at the price we quote, a difference of $12.85 a month. The dearest, Google, charges 14.1x 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. Io Net's listing is a promotional rate: 10% off its standard rate.

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 26B A4B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.12 input / $0.40 output per 1M tokens. The price we quote has changed 28 times since then, 5 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-10, was -60.3% on the blended price (30% input, 70% output), to $0.08 input / $0.10 output (quoted host changed, not a repricing). Net of all changes, the blended price is -70.3% against 2026-08-15.

23 earlier changes are not listed.

Alternatives to Gemma 4 26B A4B

None of the 4 comparable models below costs less than Gemma 4 26B A4B on the blended price.

• Next cheaper model in the Budget price tier: Qwen3.5-9B (Alibaba) at $0.0904 blended, 4% less.
• Next more expensive: Qwen3.7 Flash (Alibaba) at $0.10 blended, 6% more.

The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against Gemma 4 26B A4B.

• Qwen3.8 27B (Alibaba): $0.15 in / $1.875 out per 1M, Arena ELO 1436 (1344% more expensive, 2 ELO points higher)
• Qwen3.6 Plus (Alibaba): $0.325 in / $1.95 out per 1M, Arena ELO 1436 (1456% more expensive, 2 ELO points higher)
• DeepSeek V4 Flash 0423 (DeepSeek): $0.09 in / $0.18 out per 1M, Arena ELO 1432 (63% more expensive, 2 ELO points lower)
• GPT-5.6 Luna (OpenAI): $0.20 in / $1.20 out per 1M, Arena ELO 1431 (857% more expensive, 3 ELO points lower)

• Cheapest within 15 Arena points: Gemma 4 26B A4B is itself the cheapest of the 42 models scoring within 15 points of its ELO.
• Highest Arena ELO within 20% of this price: Gemma 4 26B A4B itself has the highest score of the 4 models priced within 20% of it.

Other models from Google

The 8 nearest to Gemma 4 26B A4B in price, of 27 other Google models in the catalogue. Prices per 1M tokens, input then output.

• Gemma 3 4B: $0.05 / $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 4 31B: $0.20 / $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

All 28 Google models and prices

Common questions about Gemma 4 26B A4B pricing

How much does Gemma 4 26B A4B cost?

Gemma 4 26B A4B costs $0.08 per 1M input tokens and $0.10 per 1M output tokens at Makora, the host whose rate we quote. The model maker, Google, lists it at $0.15 per 1M input tokens and $0.60 per 1M output tokens. Prices as listed on 2026-11-12.

Which host is cheapest for Gemma 4 26B A4B?

Cheapest host: PrimeIntellect at $0.014 input / $0.041 output per 1M tokens, 65% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $4.15 there against $17.00 at the price we quote, a difference of $12.85 a month. The dearest, Google, charges 14.1x the cheapest. Host rates as listed on 2026-11-12.

Does Gemma 4 26B A4B offer batch or cached pricing?

Yes, for prompt caching only. Cache reads cost $0.046 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.

What would Gemma 4 26B A4B cost per month?

With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $17 on Gemma 4 26B A4B at the list price quoted on 2026-11-12.

Can Gemma 4 26B A4B be self-hosted?

Yes. Gemma 4 26B A4B 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 26B A4B changed?

Gemma 4 26B A4B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.12 input / $0.40 output per 1M tokens. The price we quote has changed 28 times since then, 5 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-10, was -60.3% on the blended price (30% input, 70% output), to $0.08 input / $0.10 output (quoted host changed, not a repricing). Net of all changes, the blended price is -70.3% 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