LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 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·Vertex
$0.15 / $0.60
Blended $0.26 · Cache read $0.015
Lowest paid·NanoGPTGateway
$0.035 / $0.094
Blended $0.05 · 16.1× spread
4 more $0 channels
Context
262,144
Output limit
128,000
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

Gemma 4 26B A4B IT by google is offered by 37 providers on this page. Public prices are shown for 32 of them. Its official list price is $0.15 per 1M input tokens and $0.60 per 1M output tokens. The lowest paid channel is NanoGPT at $0.035 / $0.094 per 1M, about 5.2× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 4 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 89 tokens per second, with 0.93s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 32,768 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-04.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Reasoning

Intelligence—
Value—
Output speed89 tok/s
TTFT0.93 s

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

Available at 37 providers32 with public prices · 4 free

  • ProviderInput / Output
  • GoogleOfficialFirst-party
    Free
    Context 262,144Output limit 32,768
  • OpenRouterGateway
    google/gemma-4-26b-a4b-it:free
    Free
    Context 262,144Output limit 32,768
  • AIHubMixGateway
    gemma-4-26b-a4b-it-free
    Free
    Context 262,144Output limit 32,768
  • NaNGateway
    gemma4
    Free
    Context 262,144Output limit 32,768
  • NanoGPTGateway
    $0.035 / $0.094
    Cache read $0.018Context 262,144Output limit 131,072
  • Kilo GatewayGateway
    $0.04 / $0.15
    Cache read $0.01Context 262,144Output limit 235,929
  • EmpirioLabs AIGateway
    gemma-4-26b-a4b
    $0.05 / $0.29
    Cache read $0.025Context 262,144Output limit 32,768
  • NanoGPTGateway
    google/gemma-4-26b-a4b-it:thinking
    $0.07 / $0.24
    Cache read $0.046Context 262,144Output limit 131,072
  • LLM GatewayGateway
    $0.065 / $0.28
    Cache read $0.0097Context 262,144Output limit 32,768
  • DevPass (LLM Gateway)Gateway
    $0.065 / $0.28
    Cache read $0.0097Context 262,144Output limit 32,768
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GoogleOfficialFirst-partyFree——262,14432,768
OpenRouter
google/gemma-4-26b-a4b-it:free
GatewayFree——262,14432,768
AIHubMix
gemma-4-26b-a4b-it-free
GatewayFree——262,14432,768
NaN
gemma4
GatewayFree——262,14432,768
NanoGPTGateway$0.035$0.094$0.018—262,144131,072
Kilo GatewayGateway$0.04$0.15$0.01—262,144235,929
EmpirioLabs AI
gemma-4-26b-a4b
Gateway$0.05$0.29$0.025—262,14432,768
NanoGPT
google/gemma-4-26b-a4b-it:thinking
Gateway$0.07$0.24$0.046—262,144131,072
LLM GatewayGateway$0.065$0.28$0.0097—262,14432,768
DevPass (LLM Gateway)Gateway$0.065$0.28$0.0097—262,14432,768

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

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

Interleaved thinking (reasoning between tool calls) is declared by 7 of 37 providers.

8 / 37 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1NanoGPT$9.67
2Kilo Gateway$11.90
3LLM Gateway$20.43
4DevPass (LLM Gateway)$20.43
5EmpirioLabs AI$21.50
6OrcaRouter$22.20
18Vertex · Official$43.80

4 more channels offer $0 (Google, OpenRouter, AIHubMix etc.); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to NanoGPT to save $34.13/mo (78%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.60$02026-08-052026-11-18
2026-11-18Input list $0.15Output list $0.60Min blended $0.05

Artificial Analysis evaluations16 items

GPQA Diamond79.2%
Humanity's Last Exam19.3%
HLE-Diamond6.2%
MMMU-Pro69.3%
CritPt0.0%
SciCode40.1%
Terminal-Bench Hard13.6%
Terminal-Bench 2.139.0%
τ²-Bench Telecom43.6%
τ³-Bench Banking12.0%
AutomationBench-AA1.9%
ITBench-AA23.6%
AA-Briefcase316
GDPval-AA573
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 scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Gemma 4 Uncensoredsame series—Gemma 4 12B Starry Oceansame series—Gemma 4 26B A4B Chimera X Hereticsame series—Gemma 4 31B ITcheaper alternative$0 / $0Nemotron 3 Ultra 550B A55Bcheaper alternative$0 / $0GPT-5 Nanocheaper alternative$0.05 / $0.40GLM-4.7-Flashcheaper alternative$0 / $0Gemma 4 26B A4B Cybersecuritysame lab—
Data partly from models.dev (MIT) · Vertex official docs ↗