Inferact/Qwen3.8-2.4T-A95B-NVFP4
Input$2
Output$6
Cache$0.20
← ProvidersQwen3.8 2.4T A95B GLM-5.3current · Recent price · checked 2026-11-01 V4 Flashdeprecated · Not a current offering · checked 2026-11-01 GLM-5.3-Flashcurrent · Recent price · checked 2026-11-01 Ornith 1.5 35B A3Bcurrent · Recent price · checked 2026-11-01 Qwen3.8 27Bcurrent · Recent price · checked 2026-11-01 Nemotron 3.5 Lightningcurrent · Recent price · checked 2026-11-01
Inference provider
RunInfra
Browse observed model offerings and paired prices from the source-backed catalog. Availability and provider policies should be checked with the provider before deployment.
7 models7 offeringsChecked 2026-11-01
Models and prices
USD per million tokens. Each price links to its observation source.
7 matching offerings
deprecated · Not a current offering · checked 2026-11-01
zai-org/GLM-5.3
Input$1.30
Output$4.20
Cache$0.13
deepseek-ai/DeepSeek-V4-Flash-0731
Input$0.13
Output$0.27
Cache$0.01
zai-org/GLM-5.3-Flash
Input$0.11
Output$0.45
Cache$0.03
ornith-ai/Ornith-1.5-35B-A3B
Input$0.10
Output$0.40
Cache$0.01
Qwen/Qwen3.8-27B
Input$0.10
Output$0.40
Cache$0.01
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Input$0.05
Output$0.15
Cache$0.01
| Model | Status | Input | Output | Cache read | Retrieved |
|---|---|---|---|---|---|
| Qwen3.8 2.4T A95BInferact/Qwen3.8-2.4T-A95B-NVFP4 | deprecatedNot a current offering | $2 | $6 | $0.20 | 2026-11-01 |
| GLM-5.3zai-org/GLM-5.3 | currentRecent price | $1.30 | $4.20 | $0.13 | 2026-11-01 |
| V4 Flashdeepseek-ai/DeepSeek-V4-Flash-0731 | deprecatedNot a current offering | $0.13 | $0.27 | $0.01 | 2026-11-01 |
| GLM-5.3-Flashzai-org/GLM-5.3-Flash | currentRecent price | $0.11 | $0.45 | $0.03 | 2026-11-01 |
| Ornith 1.5 35B A3Bornith-ai/Ornith-1.5-35B-A3B | currentRecent price | $0.10 | $0.40 | $0.01 | 2026-11-01 |
| Qwen3.8 27BQwen/Qwen3.8-27B | currentRecent price | $0.10 | $0.40 | $0.01 | 2026-11-01 |
| Nemotron 3.5 Lightningnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | currentRecent price | $0.05 | $0.15 | $0.01 | 2026-11-01 |
About these observations
The catalog records model and price observations; it does not measure this provider’s latency, uptime, data retention, or regional availability. Follow each row’s source to verify a quote before choosing a provider.