Gemma 4 26B A4B pricing across providers
Across tracked provider offerings, input runs $0.042–$0.150 per million tokens and output $0.220–$0.600 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Darkbloom at $0.023 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 12 of 16 offerings publish a cache-read rate; 14 of 16 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Gemma 4 26B A4B
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for Gemma 4 26B A4B
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Darkbloom | unknown | $0.042 | $0.220 | $0.021 | $0.023 | 100.00% |
| Dekallm | bf16 | $0.060 | $0.330 | $0.040 | $0.042 | 100.00% |
| Io Net | bf16 | $0.090 | $0.310 | $0.041 | $0.044 | 100.00% |
| Nextbit promo | bf16 | $0.076 | $0.255 | $0.042 | $0.044 | 100.00% |
| Akashml | fp4 | $0.070 | $0.240 | $0.046 | $0.048 | 100.00% |
| Makora | unknown | $0.070 | $0.240 | $0.046 | $0.048 | 100.00% |
| Hyper | — | $0.098 | $0.334 | $0.049 | $0.052 | — |
| Coreweave | bf16 | $0.100 | $0.300 | $0.050 | $0.052 | 100.00% |
| Cloudflare | unknown | $0.100 | $0.300 | $0.050 | $0.052 | 100.00% |
| Venice | bf16 | $0.130 | $0.400 | $0.050 | $0.054 | 100.00% |
| Parasail | bf16 | $0.130 | $0.400 | $0.050 | $0.054 | 100.00% |
| SiliconFlow | fp8 | $0.140 | $0.400 | $0.050 | $0.054 | 100.00% |
| DeepInfra | — | $0.070 | $0.340 | — | $0.071 | — |
| Primeintellect | bf16 | $0.100 | $0.300 | — | $0.101 | 100.00% |
| Novita | bf16 | $0.130 | $0.400 | — | $0.131 | 100.00% |
| unknown | $0.150 | $0.600 | — | $0.152 | 93.33% |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.