ModelPriceWatch.com
Last scan 2026-10-12 Models tracked 281 Providers 37 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

Gemma-4-31B-it-Pearl

by Together · 31B parameters

Retired budget open weights cheap tier
Email me when Gemma-4-31B-it-Pearl gets cheaper
Retired on . No longer served on the endpoint we price — the figures below are kept for historical reference only.
Availability: Together no longer serves pearl-ai/gemma-4-31b-it. This row was held on watch rather than retired for four weeks because Together's two first-party surfaces disagreed: the serverless-models card dropped the SKU on 2026-09-02 while www.together.ai/pricing still listed a 'Gemma 4 31B' at $0.39/$0.97. That listing is a different model, not this one: our stored 2026-08-17 capture of the same pricing table carries both lines at once, 'Gemma 4 31B $0.39 $0.97' and 'Gemma-4-31B-it-Pearl $0.28 $0.86'. On 2026-09-06 the Pearl listing is gone from the pricing table as well, so both first-party surfaces now agree, on three time-separated card reads (2026-09-02, 2026-09-04, 2026-09-06). The unattributed Gemma 4 31B at $0.39/$0.97 is still sold by Together and is not tracked here. Together published no retirement date, so the date above is the day we confirmed it was gone.

Today's price · per 1M tokens

Input

$0.280

per 1M tokens

Output

$0.860

per 1M tokens

Blended

$0.425

blended $/1M — 3:1 weighted input:output

Source: official Together pricing · read MODELPRICEWATCH.COM · 2026-10-12

Price receipt

We read Together's own pricing page on and found Gemma-4-31B-it-Pearl listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is 0db20f21ed.

Overview

Google's Gemma 4 31B on Together (Pearl variant). $0.28/$0.86 per 1M tokens. Together no longer serves the Pearl variant; the price shown is what it last cost, not a rate you can buy today.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 1/4
Text ✓ Image Audio Video
Output
Text ✓
Features 1/9
Prompt caching Reasoning Coding Fast inference Long context Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Percentile vs all tracked models 57.5th1 independent measurement
Percentile per $/Mtok 133.7

We hold no per-benchmark accuracy scores for this model yet, so it has no accuracy average. That is a gap in our coverage, not a sign the model is untested — independent evaluators often publish a composite index for a new model long before releasing its per-benchmark numbers. The percentile above is its standing across the independent composites below.

Independent composite scores
  • LMSYS Chatbot Arena: 1451.1 ELO (Human preference)
How it stacks up
  • Ranks #61 of 194 comparably-measured models by percentile score, across 1 independent measurement
  • Ranks #17 of 194 comparably-tested models by normalized performance per dollar

Source: LMSYS Chatbot Arena (UC Berkeley) · updated · See full rankings →

Specifications

Provider
Together
Context window
32K tokens
Modality
text
Parameters
31B
Open source
Yes — open weights available
Released
Status
Retired ended
Last updated
Tags
open-weightsbudgetretired

Availability verified: — per Together's own deprecation notice

Try on Together Official pricing page