ModelBench
Google logo
Models/Google

Gemma 4 31B IT

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Source-linked gemma Open weights Released 2026-04-02
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.1/1M tokens
Output price$0.35/1M tokens
Context window262.144K
Max output32.768K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
? Structured output Unknown
✓ Attachments Yes
✓ Vision input Yes
✓ Open weights Yes
Creator
Google
Model family
gemma
Knowledge cutoff
Not documented
License
Not documented
Release date
2026-04-02
Model ID
google/gemma-4-31b-it
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering Gemma 4 31B IT
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Google gemma-4-31b-it 262.144K Not listed Not listed - ReasoningToolsJSON Docs
Kenari gemma-4-31b-it 262.144K Not listed Not listed - ReasoningToolsJSON Docs
Nvidia google/gemma-4-31b-it 256K Not listed Not listed - ReasoningTools Docs
UnoRouter gemma-4-31b-it:free 262.144K Not listed Not listed - ReasoningToolsJSON Docs
OpenRouter google/gemma-4-31b-it 262.144K $0.1 $0.34 $0.1 ReasoningToolsJSON Docs
CrofAI gemma-4-31b-it 262.144K $0.1 $0.3 $0.02 ReasoningToolsJSON Docs
NanoGPT google/gemma-4-31b-it 262.144K $0.1 $0.35 - ReasoningJSON Docs
LLM Gateway gemma-4-31b-it 262.144K $0.102 $0.297 $0.012 ReasoningToolsJSON Docs
Lilac google/gemma-4-31b-it 262.1K $0.11 $0.35 - ReasoningToolsJSON Docs
OrcaRouter google/gemma-4-31b-it 262.144K $0.13 $0.38 - ReasoningToolsJSON Docs
NEAR AI Cloud google/gemma-4-31B-it 262.144K $0.13 $0.4 $0.026 ReasoningToolsJSON Docs
Deep Infra google/gemma-4-31B-it 262.144K $0.13 $0.38 - ReasoningToolsJSON Docs
SiliconFlow google/gemma-4-31B-it 262.144K $0.13 $0.4 - ToolsJSON Docs
FastRouter google/gemma-4-31b-it 262.144K $0.13 $0.38 - ReasoningToolsJSON Docs
Vercel AI Gateway google/gemma-4-31b-it 262.144K $0.14 $0.4 - ToolsJSON Docs
Hugging Face google/gemma-4-31B-it 262.144K $0.14 $0.4 - ReasoningToolsJSON Docs
NovitaAI google/gemma-4-31b-it 262.144K $0.14 $0.4 - ReasoningToolsJSON Docs
Merge Gateway google/gemma-4-31b-it 262.144K $0.14 $0.4 - Reasoning Docs
Abacus google/gemma-4-31b-it 262.144K $0.14 $0.4 - ReasoningToolsJSON Docs
Friendli google/gemma-4-31B-it 262.144K $0.14 $0.4 - ReasoningToolsJSON Docs
Kilo Gateway google/gemma-4-31b-it 262.144K $0.14 $0.4 - ReasoningTools Docs
ai& google/gemma-4-31b-it 262.144K $0.2 $0.5 - ReasoningToolsJSON Docs
Tinfoil gemma4-31b 256K $0.4 $1 - ReasoningToolsJSON Docs
Pioneer google/gemma-4-31B-it 32.768K $0.5 $0.5 $0.5 ReasoningToolsJSON Docs
Cerebras gemma-4-31b 131.072K $0.99 $1.49 - ReasoningToolsJSON Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
Agentic Index - Unversioned - indexTop 8 reported models
Claude Opus 5
55.3
GPT-5.6 Sol
54.0
Anthropic: Claude Fable 5 (batch)
52.8
Claude Fable 5
52.8
Kimi K3
50.1
GPT-5.6 Terra
47.4
Anthropic: Claude Opus 4.8 (batch)
47.2
Gemma 4 31B IT
14.4
Coding Index - Unversioned - indexTop 8 reported models
Claude Opus 5
78.0
GPT-5.6 Sol
77.4
GPT-5.6 Terra
76.7
Anthropic: Claude Fable 5 (batch)
76.5
Claude Fable 5
76.5
Kimi K3
76.2
OpenAI: GPT-5.5 (batch)
74.9
Gemma 4 31B IT
43.4
Intelligence Index - Unversioned - indexTop 8 reported models
Claude Opus 5
60.7
Anthropic: Claude Fable 5 (batch)
59.9
Claude Fable 5
59.9
GPT-5.6 Sol
58.9
Kimi K3
57.1
Anthropic: Claude Opus 4.8 (batch)
55.7
Anthropic: Claude Opus 4.8
55.7
Gemma 4 31B IT
29.4
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
Max Output Tokens262144 → 32768
Price Completion0.33999999999999997 → 0.35
Price Prompt0.09999999999999999 → 0.1
Max Output Tokens32768 → 262144
Price Completion0.35 → 0.33999999999999997
Price Prompt0.1 → 0.09999999999999999
Max Output Tokens262144 → 32768
Price Completion0.33999999999999997 → 0.35
Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/google/gemma-4-31b-it
curl
curl "https://www.modelbench.lol/api/v1/models/google/gemma-4-31b-it"