Skip to content

Model Library

GoogleReleased April 2, 2026

Gemma 4 31B

Google · Released April 2, 2026

View public research Browse the library

Intelligence score

25

At a glance

Intelligence
25
Speed
55.2tokens/sec
Latency
2.10stime to first token
Input price
$0.14per 1M tokens
Output price
$0.40per 1M tokens
Context window
260Ktokens
Parameters
30.7billions

Summary

Comparison summary

Gemma 4 31B (Non-reasoning) scores 25 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 6). Gemma 4 31B (Non-reasoning) generates output at 55.2 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 102.7 t/s). Gemma 4 31B (Non-reasoning) costs $0.14 per 1M input tokens (better than average, median: $0.15) and $0.40 per 1M output tokens (somewhat higher than average, median: $0.32), based on the median across providers serving the model.

Specifications

Technical specifications

Model nameGemma 4 31B
ProviderGoogle
Release dateApril 2, 2026
Intelligence score25
Speed55.2 tokens/sec
Latency (TTFT)2.10s
Input price$0.14 / 1M tokens
Output price$0.40 / 1M tokens
Context window260,000 tokens
Parameters30.7B
ReasoningNo
Input modalitiestext, image, video
Output modalities—
Open weightsYes
LicenseApache 2
API availability—
SourceModel Intelligence legacy profile: gemma-4-31b-non-reasoning

Pricing

Token prices

Price per 1M tokens

Gemma 4 31B, as listed in the catalog record

Input $0.14 and output $0.40 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$0.14
  2. Output$0.40

Model Intelligence legacy profile: gemma-4-31b-non-reasoning

FAQ · 19

Frequently asked questions

Gemma 4 31B (Non-reasoning) was released on April 2, 2026.

Gemma 4 31B (Non-reasoning) was created by Google.

Gemma 4 31B (Non-reasoning) scores 25 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 6).

Gemma 4 31B (Non-reasoning) generates output at 55.2 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 102.7 t/s).

Gemma 4 31B (Non-reasoning) has a time to first token (TTFT) of 2.10s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 1.54s).

Gemma 4 31B (Non-reasoning) costs $0.14 per 1M input tokens (better than average, median: $0.15) and $0.40 per 1M output tokens (somewhat higher than average, median: $0.32), based on the median across providers serving the model.

Gemma 4 31B (Non-reasoning) costs $0.14 per 1M input tokens and $0.40 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.17 per 1M tokens. Pricing may vary by provider.

No, Gemma 4 31B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Gemma 4 31B (Non-reasoning) supports text, image, and video input.

Gemma 4 31B (Non-reasoning) supports text output.

Yes, Gemma 4 31B (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.

Yes, Gemma 4 31B (Non-reasoning) is multimodal. It can process text, image, and video input and generate text output.

Gemma 4 31B (Non-reasoning) has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Gemma 4 31B (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Gemma 4 31B (Non-reasoning) has 30.7 billion parameters.

Gemma 4 31B (Non-reasoning) is released under the Apache 2.0 license. This license allows commercial use.

Gemma 4 31B (Non-reasoning) achieves a score of 25 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Gemma 4 31B (Non-reasoning) is available via API through 8 providers.

Gemma 4 31B (Non-reasoning) is available through 8 API providers.