Where is the Gemma 4 31B documentation?

The Gemma 4 31B documentation on OpenRouter includes the LLM Quantization: What fp8 and fp4 Do to Quality and Price blog post and the LLM API Rate Limits: How to Fix OpenAI and Claude 429 Errors blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does Gemma 4 31B cost?

Gemma 4 31B costs $0.10/M input tokens and $0.34/M output tokens, with separate rates for Cache Read at $0.10/M tokens.

What is the context length of Gemma 4 31B?

Gemma 4 31B has a 262,144 token context window. It supports up to 262,144 completion tokens.

Does Gemma 4 31B support tool calling and structured outputs?

Yes. Gemma 4 31B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Gemma 4 31B support?

Gemma 4 31B accepts images, text, and video as input and returns text.

Which providers serve Gemma 4 31B?

Gemma 4 31B is served by 15 providers on OpenRouter: KT, CoreWeave, Venice, Chutes, DeepInfra (fp8), DekaLLM, Crusoe, Friendli and 7 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Gemma 4 31B released?

Gemma 4 31B was released on April 2, 2026.

Google: Gemma 4 31B

google/gemma-4-31b-it

Model weights

Compare

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

Modalities

In / out price

$0.10 / $0.34per 1M

Context

262K

Released

Apr 2, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$0.10	$0.34	$0.10	0.66s	134 tok/s	99.27%
	$0.10	$0.34	$0.10	0.38s	62 tok/s	100.00%
	$0.15	$0.40	$0.06	0.49s	83 tok/s	100.00%
Turbo	$0.135	$0.51	$0.075	0.47s	53 tok/s	100.00%
	$0.14	$0.40	$0.05	1.09s	35 tok/s	90.16%
	$0.20	$0.40	--	0.69s	26 tok/s	99.62%
Priority	$0.30	$0.60	--	0.66s	28 tok/s	99.58%
	$0.75	$1.00	$0.25	1.21s	54 tok/s	98.96%
	$0.14	$0.40	--	0.40s	152 tok/s	99.97%
	$0.12	$0.36	$0.09	0.72s	42 tok/s	99.97%
	$0.15	$0.40	$0.06	0.61s	36 tok/s	100.00%
	$0.34	$0.10	$0.10	0.52s	110 tok/s	99.92%
	$0.20	$0.335	$0.10	1.47s	57 tok/s	99.61%
	$0.14	$0.40	--	0.76s	28 tok/s	96.23%
	$0.12	$0.37	$0.012	3.43s	26 tok/s	98.50%
	$0.14	$0.40	$0.14	0.60s	42 tok/s	99.92%
	$0.38	$1.15	--	6.73s	60 tok/s	85.84%
Not used in Standard routing:Why these endpoints are not used
Flex	$0.16	$0.32	--	0.93s	24 tok/s	99.88%

Input $0.10Output $0.34
134 tok/s99.27% uptime
Input $0.10Output $0.34
62 tok/s100.00% uptime
Input $0.15Output $0.40
83 tok/s100.00% uptime
Input $0.135Output $0.51
Turbo
53 tok/s100.00% uptime
Input $0.14Output $0.40
35 tok/s90.16% uptime
Input $0.20Output $0.40
26 tok/s99.62% uptime
Input $0.30Output $0.60
Priority
28 tok/s99.58% uptime
Input $0.75Output $1.00
54 tok/s98.96% uptime
Input $0.14Output $0.40
152 tok/s99.97% uptime
Input $0.12Output $0.36
42 tok/s99.97% uptime
Input $0.15Output $0.40
36 tok/s100.00% uptime
Input $0.34Output $0.10
110 tok/s99.92% uptime
Input $0.20Output $0.335
57 tok/s99.61% uptime
Input $0.14Output $0.40
28 tok/s96.23% uptime
Input $0.12Output $0.37
26 tok/s98.50% uptime
Input $0.14Output $0.40
42 tok/s99.92% uptime
Input $0.38Output $1.15
60 tok/s85.84% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.16Output $0.32
Flex
24 tok/s99.88% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.1231/M tokens

Output

$0.39/M tokens

Gemma 4 31B — Price history

Price history

No effective price data for this selection

		$0.0558	$0.3692	59.4%	1.0%
		$0.0979	$0.3985	57.8%	6.2%
		$0.0999	$0.3384	35.9%	17.3%
		$0.0999	$0.3383	23.2%	23.8%
		$0.1071	$0.3572	42.6%	1.1%
	Turbo	$0.1086	$0.5083	43.9%	17.9%
		$0.1098	$0.3981	33.4%	0.2%
		$0.1298	$0.3990	22.3%	6.9%
		$0.1398	$0.3980	0.0%	0.6%
		$0.1399	$0.3987	26.1%	2.9%
		$0.1399	$0.3993	13.2%	11.8%
		$0.1502	$0.3345	49.7%	0.7%
		$0.1999	$0.3986	0.0%	6.1%
		$0.2766	$0.0991	26.3%	1.7%
	Priority	$0.2998	$0.5980	0.0%	0.6%
		$0.3692	$1.0000	76.1%	1.1%
		$0.3799	$1.1496	0.0%	0.2%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.1597	$0.3187	0.0%	0.0%

Effective in $0.0558Effective out $0.3692
Token share
1.0%
Effective in $0.0979Effective out $0.3985
Token share
6.2%
Effective in $0.0999Effective out $0.3384
Token share
17.3%
Effective in $0.0999Effective out $0.3383
Token share
23.8%
Effective in $0.1071Effective out $0.3572
Token share
1.1%
Effective in $0.1086Effective out $0.5083
TurboToken share
17.9%
Effective in $0.1098Effective out $0.3981
Token share
0.2%
Effective in $0.1298Effective out $0.3990
Token share
6.9%
Effective in $0.1398Effective out $0.3980
Token share
0.6%
Effective in $0.1399Effective out $0.3987
Token share
2.9%
Effective in $0.1399Effective out $0.3993
Token share
11.8%
Effective in $0.1502Effective out $0.3345
Token share
0.7%
Effective in $0.1999Effective out $0.3986
Token share
6.1%
Effective in $0.2766Effective out $0.0991
Token share
1.7%
Effective in $0.2998Effective out $0.5980
PriorityToken share
0.6%
Effective in $0.3692Effective out $1.0000
Token share
1.1%
Effective in $0.3799Effective out $1.1496
Token share
0.2%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.1597Effective out $0.3187
FlexToken share
0.0%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

152tok/s

P50, best across providers

Latency

0.38s

P50, best provider

Latency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchPrime Intellect84.1%--DeepInfra (fp8)84.9%76.8%DeepInfra (fp4)84.8%76.1%SambaNova84.1%76.5%NovitaAI85.1%73.9%ModelRun84.4%74.3%

+13 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.82%

Availability over the last 3 days

Last 72 hours

Availability 99.82%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.78%

Without Routing

94.98%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Google: Gemma 4 31B (Artificial Analysis and Vals AI)
Source	Benchmark	Score
Artificial Analysis	Gemma 4 31B (Reasoning) Intelligence Index	4.4
Artificial Analysis	Gemma 4 31B (Reasoning) Coding Index	43.4
Artificial Analysis	Gemma 4 31B (Reasoning) Agentic Index	4.2
Artificial Analysis	Gemma 4 31B (Reasoning) GPQA Diamond	85.7%
Artificial Analysis	Gemma 4 31B (Reasoning) HLE	23.6%
Artificial Analysis	Gemma 4 31B (Reasoning) IFBench	75.6%
Artificial Analysis	Gemma 4 31B (Reasoning) τ²-Bench Telecom	59.9%
Artificial Analysis	Gemma 4 31B (Reasoning) AA-LCR	69.7%
Artificial Analysis	Gemma 4 31B (Reasoning) τ-Bench Banking	14.8%
Artificial Analysis	Gemma 4 31B (Reasoning) GDPval-AA	6.3%
Artificial Analysis	Gemma 4 31B (Reasoning) CritPt	1.4%
Artificial Analysis	Gemma 4 31B (Reasoning) SciCode	45.5%
Artificial Analysis	Gemma 4 31B (Reasoning) Terminal-Bench Hard	36.4%
Artificial Analysis	Gemma 4 31B (Reasoning) Terminal-Bench 4.0	0.0%
Artificial Analysis	Gemma 4 31B (Reasoning) Terminal-Bench 2.1	43.4%
Artificial Analysis	Gemma 4 31B (Reasoning) AA-Omniscience Accuracy	19.9%
Artificial Analysis	Gemma 4 31B (Reasoning) AA-Omniscience Non-Hallucination Rate	14.5%
Artificial Analysis	Gemma 4 31B (Non-reasoning) Coding Index	33.2
Artificial Analysis	Gemma 4 31B (Non-reasoning) GPQA Diamond	76.3%
Artificial Analysis	Gemma 4 31B (Non-reasoning) HLE	11.8%
Artificial Analysis	Gemma 4 31B (Non-reasoning) IFBench	53.5%
Artificial Analysis	Gemma 4 31B (Non-reasoning) τ²-Bench Telecom	65.5%
Artificial Analysis	Gemma 4 31B (Non-reasoning) AA-LCR	46.7%
Artificial Analysis	Gemma 4 31B (Non-reasoning) τ-Bench Banking	8.9%
Artificial Analysis	Gemma 4 31B (Non-reasoning) GDPval-AA	2.7%
Artificial Analysis	Gemma 4 31B (Non-reasoning) CritPt	0.0%
Artificial Analysis	Gemma 4 31B (Non-reasoning) Terminal-Bench Hard	30.3%
Artificial Analysis	Gemma 4 31B (Non-reasoning) Terminal-Bench 2.1	29.2%
Vals AI	Gemma 4 31B IT CaseLaw v2	52.6%
Vals AI	Gemma 4 31B IT Finance Agent v1.1	50.8%
Vals AI	Gemma 4 31B IT MortgageTax	61.4%
Vals AI	Gemma 4 31B IT SAGE	82.8%
Vals AI	Gemma 4 31B IT Terminal-Bench 2.0	39.3%

Not currently available through EU in-region routing. In-region routing docs

More models from Google

Gemini 4 Hydrogen

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than Gemini 4 Carbon. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium, high and xhigh reasoning effort.

Text1.0M context$1.50 / $7.50

Gemini 4 Hydrogen (batch)

Text1.0M context$0.75 / $3.75

Gemini Decision 1

Gemini Decision 1 is Google's model for the Decisions API. It answers structured questions about an input state (true/false, multiple choice with up to 255 options, and score with up to 255 levels) and returns a confidence for every answer, plus a legend and probabilities for score questions.

It reads text, images, audio, video, and documents (PDF, CSV, and Office files) sent inline as base64 or by public URL. Every question needs instructions.

Decisions$0.10 / $0

Gemini 4 Carbon

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium and high reasoning effort.

Text1.0M context$2 / $10

Gemini 4 Carbon (batch)

Text1.0M context$1 / $5

Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native audio in 16:9 or 9:16, from 360p drafts up to 4K, and supports text-to-video, image-to-video, first and last frame interpolation, subject and video references with improved reference management, and editing or extending an uploaded video. Multi-turn editing and extension of a prior generation is supported through previous_job_id.

Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Text131K context$1.50 / $9

Gemini Omni 1.1 Flash

Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and last frame interpolation, subject and video references (up to three reference clips), and editing or extending an uploaded video, and generates clips from 360p drafts up to 4K with native audio in 16:9 or 9:16. Multi-turn editing and extension of a prior generation is supported through previous_job_id, up to 40 seconds of total video.

Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Text131K context$1.50 / $9

Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.

Text1.0M context$2 / $10

Gemini 4 Argon (batch)

Text1.0M context$1 / $5

Nano Banana 2.1

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization, mask- and ink-based editing, and factual accuracy, and renders photorealistic skin tones, detailed materials, lighting, and coherent backgrounds. It accepts text and image inputs, returns images with optional text, and supports 1K, 2K, and 4K output plus extended aspect ratios via the image_config API Parameter.

Image66K context$1.50 / $30

Gemini 3.5 Transcribe

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio can be up to one hour, or 30 minutes when timestamps or diarization are enabled.

Transcription$2 / $12

Gemini 3.8 Flash Lite TTS

Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside Gemini 3.8 Flash TTS. It is suited for conversational voice-agent pipelines, high-volume read-aloud, and voice replication workloads where latency and cost matter more than maximum expressiveness.

It accepts the same speech configuration as Gemini 3.1 Flash TTS Preview, including the 30 prebuilt studio voices, and supports Google's Voice Design and Voice Replication through voice_... identifiers.

Speech$0.50 / $6

Gemini 3.8 Flash TTS

Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successor to Gemini 3.1 Flash TTS Preview. It is the creative tier of the 3.8 TTS family, suited for narration, character work, and multi-speaker dialogue where voice fidelity, acting nuance, and regional dialect coverage matter more than latency.

It accepts the same speech configuration as its predecessor, including the 30 prebuilt studio voices, and supports Google's Voice Design (custom voices from a text description) and Voice Replication (voices cloned from a short sample) through voice_... identifiers.

Speech$0.50 / $9

Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Text1.0M context$0.75 / $3.75

Gemini 3.8 Flash (batch)

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Text1.0M context$0.375 / $1.875

Gemini 3.7 Flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.

Text1.0M context$0.75 / $3.75

Gemini 3.7 Flash (batch)

Text1.0M context$0.375 / $1.875

Gemini 3.6 Flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.

Text1.0M context$0.75 / $3.75

Gemini 3.6 Flash (batch)

Text1.0M context$0.375 / $1.875

Gemini 3.5 Flash Lite

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

Text1.0M context$0.30 / $2.50

Google: Gemma 4 31B

Providers