LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemma 4 26B A4B IT

google·google/gemma-4-26b-a4b-it·BETA·Open weights·gemma series
Open Gemma instruction model for efficient chat and self-hosted deployments

Specs & pricing

Input / output per 1M tokens
Official price
Price undisclosed
Lowest paid·Kilo GatewayGateway
$0.042 / $0.22
Blended $0.087 · 6× spread
1 more $0 channels
Context
262,144
Output limit
32,768
Knowledge cutoff
2025-04
Released / updated
2026-04-02 / 2026-04-02
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoPDF
Weights
Hugging Face

Quality & performanceArtificial Analysis · Intelligence Index v4.3 · rep. tier Reasoning

Intelligence16.7
Value193
Coding39.3
Agentic2.9
Output speed—
TTFT—
Value formulaIQ 16.7 ÷ min blended $0.086 = 193
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 13.1 · 99 tok/s
ReasoningIQ 16.7

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 26 providers23 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NaN
gemma4
GatewayFree——262,14432,768
Kilo GatewayGateway$0.042$0.22$0.021—262,144235,929
EmpirioLabs AI
gemma-4-26b-a4b
Gateway$0.05$0.29$0.025—262,14432,768
OrcaRouterGateway$0.06$0.33$0.0075—262,14432,768
Deep Infra
google/gemma-4-26B-A4B-it
Cloud$0.07$0.34——262,14432,768
RequestyGateway$0.07$0.34$0.07—262,144262,144
DevPass (LLM Gateway)Gateway$0.07$0.34——262,14432,768
LLM GatewayGateway$0.07$0.34——262,14432,768
OpenRouterGateway$0.09$0.30$0.05—262,144235,929
Cloudflare Workers AICloud$0.10$0.30$0.05—256,000 ⚠16,384
GoogleOfficialFirst-party————262,14432,768hostTable.undisclosed

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokens ≥ 128 ≤ 32,768Toggle (on / off)

Interleaved thinking (reasoning between tool calls) is declared by 1 of 26 providers.

7 / 26 providers expose no reasoning control (reasoning_options: []).

Your usage cost

1Kilo Gateway$16.88
2EmpirioLabs AI$21.50
3OrcaRouter$22.20
4OpenRouter$28.20
5Cloudflare Workers AI$29.00
6CoreWeave$29.00

1 more channels offer $0 (NaN); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.13$02026-08-052026-08-232026-08-05 · Min blended $0.132026-08-06 · Min blended $0.132026-08-07 · Min blended $0.132026-08-08 · Min blended $0.132026-08-09 · Min blended $0.132026-08-10 · Min blended $0.132026-08-11 · Min blended $0.132026-08-12 · Min blended $0.132026-08-13 · Min blended $0.132026-08-21 · Min blended $0.102026-08-23 · Min blended $0.087

Artificial Analysis evaluations9 items

GPQA Diamond79.2%
Humanity's Last Exam19.3%
SciCode40.0%
Terminal-Bench Hard13.6%
Terminal-Bench 2.139.0%
τ²-Bench Telecom43.6%
τ³-Bench Banking12.0%
AA-LCR65.7%
IFBench72.5%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

Gemma 4 26B A4B Cybersecuritysame series$0.11 / $0.33Gemma 4 31B Split-Untiedsame series$0.10 / $0.30Gemma 4 12B Semancersame series$0.05 / $0.25
Data partly from models.dev (MIT)