Gemma 4 26B A4B
Google · Open weights · Released Apr 3, 2026 · google/gemma-4-26b-a4b-it
Best $0.042 in / $0.22 out via Darkbloom · 131K ctx at this price (headline 262K)
262K contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 13 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 24 HOURS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
 Darkbloom | $0.042 | $0.22 | $0.021 | 131K | — | ✕ | ✕ | 5/5 | 100.0% |
 Io Net | $0.052 | $0.225 | $0.022 | 262K | bf16 | ✕ | ✕ | — | 100.0% |
| DEDekaLLM | $0.06 | $0.33 | $0.04 | 262K | bf16 | 1.7s | 78 tok/s | — | 100.0% |
 DeepInfra | $0.07 | $0.34 | — | 262K | fp8 | 0.68s | 30 tok/s | 5/5 | 100.0% |
 NextBit | $0.076 | $0.255 | $0.043 | 262K | bf16 | 1.2s | 87 tok/s | 5/5 | 100.0% |
| MAMakora | $0.08 | $0.32 | $0.032 | 256K | — | 0.88s | 51 tok/s | — | 99.9% |
 Cloudflare | $0.10 | $0.30 | $0.05 | 256K | — | ✕ | ✕ | 5/5 | 99.5% |
 CoreWeave | $0.10 | $0.30 | $0.05 | 262K | bf16 | 0.28s | 87 tok/s | — | 99.9% |
 Novita | $0.13 | $0.40 | — | 262K | bf16 | 1.2s | 25 tok/s | 4/5 | 100.0% |
 Parasail | $0.13 | $0.40 | $0.05 | 262K | bf16 | 1.3s | 30 tok/s | — | 99.4% |
 Venice | $0.13 | $0.40 | $0.05 | 256K | bf16 | 2.1s | 62 tok/s | — | 99.3% |
 SiliconFlow | $0.14 | $0.40 | $0.05 | 262K | fp8 | ✕ | ✕ | 5/5 | 95.4% |
 Google1ST PARTY | $0.15 | $0.60 | — | 262K | — | 0.51s | 115 tok/s | — | 98.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 24 hours ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Input price history · best listed price, observed
↓ 16% SINCE AUG 23, 2026
$0.05 · AUG 23, 2026$0.042 · TODAY
Pricing variants · USD / MTok in / out
STANDARD
$0.042 / $0.22
per MTok in / out
FREE
Free / Free
per MTok in / out
CACHE READ $0.021
Recent changesRSS ↗
Oct 5, 2026endpoint added · makora12 → 13
Oct 3, 2026endpoint removed · makora13 → 12
Oct 1, 2026endpoint removed · reka14 → 13
Sep 27, 2026price decreased · output0.22 → 0.2
Sep 26, 2026endpoint added · io-net12 → 14
Sep 26, 2026endpoint added · reka12 → 14
Sep 23, 2026endpoint added · coreweave11 → 12
Sep 12, 2026endpoint added · dekallm10 → 11
About
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Specifications
Context window262,144
Max output235,929
Modalities inimage, text, video
Modalities outtext
LicenseOpen weights
ReleasedApr 3, 2026
TokenizerGemma
WeightsHugging Face ↗
Open weights
safetensors
Related
Compare with
Embed badge
[](https://modelindex.ai/models/google/gemma-4-26b-a4b-it)Sources
OpenRouter API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks18 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.