theserverless.dev InferenceList

Models

Showing 201–250 of 269 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
nim/nvidia/llama-3.3-nemotron-super-49b-v1 Together text Not published— Not published— 16K
Nvidia Nemotron 3 Nano 30B A3b Bf16 Together text Not published— Not published— 262K
Nvidia Nemotron 3 Super 120B A12b Bf16 Together text Not published— Not published— 262K
Nvidia Nemotron 3 Super 120B A12b Fp8 Together text Not published— Not published— 262K
Nvidia Nemotron 3.5 ASR Streaming 0.6B Together audio Not published— Not published— 448
Nvidia Parakeet TDT 0.6B V3 Together audio Not published— Not published— 448
P-Image-Ideogram Together image Not published— Not published— —
PixVerse v5 Together video Not published— Not published— —
PixVerse v5.6 Together video Not published— Not published— —
PixVerse v6 Together video Not published— Not published— —
Qwen 2 (1.5B) Together text Not published— Not published— 33K
Qwen 2 (72B) Together text Not published— Not published— 33K
Qwen 2 (7B) Together text Not published— Not published— 33K
Qwen Image Together image Not published— Not published— —
Qwen Image 2.0 Together image Not published— Not published— —
Qwen Image 2.0 Pro Together image Not published— Not published— —
Qwen2.5 1.5B Together text Not published— Not published— 131K
Qwen2.5 1.5B Instruct Together text Not published— Not published— 33K
Qwen2.5 14B Together text Not published— Not published— 131K
Qwen2.5 32B Together text Not published— Not published— 131K
Qwen2.5 32B Instruct Together text Not published— Not published— 33K
Qwen2.5 3B Instruct Together text Not published— Not published— 33K
Qwen2.5 72B Together text Not published— Not published— 131K
Qwen2.5 7B Together text Not published— Not published— 131K
Qwen2.5 7B Instruct Together text Not published— Not published— 33K
Qwen3 0.6B Together text Not published— Not published— 41K
Qwen3 0.6B Base Together text Not published— Not published— 33K
Qwen3 1.7B Together text Not published— Not published— 41K
Qwen3 1.7B Base Together text Not published— Not published— 33K
Qwen3 14B Together text Not published— Not published— 2K
Qwen3 14B Base Together text Not published— Not published— 33K
Qwen3 235B A22b Instruct 2507 Fp8 Together text Not published— Not published— 262K
Qwen3 30B A3b Together text Not published— Not published— 41K
Qwen3 30B A3b Base Together text Not published— Not published— 33K
Qwen3 30B A3B Instruct 2507 Lora Together text Not published— Not published— 262K
Qwen3 32B Together text Not published— Not published— 41K
Qwen3 4B Base Together text Not published— Not published— 33K
Qwen3 4B Instruct 2507 Together text Not published— Not published— 262K
Qwen3 8B Together text Not published— Not published— 41K
Qwen3 8B Base Together text Not published— Not published— 33K
Qwen3 8B Lora Together text Not published— Not published— 41K
Qwen3 Coder 30B A3b Instruct Together text Not published— Not published— 262K
Qwen3 Next 80B A3b Instruct Fp8 Together text Not published— Not published— —
Qwen3 TTS 12Hz 1.7B CustomVoice Together audio Not published— Not published— —
Qwen3-VL-235B-A22B-Instruct-FP8 Together text Not published— Not published— 262K
Qwen3.5 122B A10b Fp8 Together text Not published— Not published— 262K
Qwen3.5 2B Lora Together text Not published— Not published— 262K
Qwen3.5 35B A3b Together text Not published— Not published— 262K
Qwen3.5 35B A3B Lora Together text Not published— Not published— 262K
Qwen3.5 9B Fp8 Together text Not published— Not published— 262K

Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.