theserverless.dev InferenceList

Models

Showing 51–100 of 194 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Together × Clear
Model Provider Modality Input ↑ Output Context
Deepseek Coder 33B Instruct Together text $0.8/1M $0.8/1M 16K
Gemma-2 Instruct (27B) Together text $0.8/1M $0.8/1M 8K
Qwen 2.5 14B Instruct Together text $0.8/1M $0.8/1M 33K
Qwen 2.5 Coder 32B Instruct Together text $0.8/1M $0.8/1M 16K
Llama 3.1 Nemotron 70B Instruct HF Together text $0.88/1M $0.88/1M 33K
Meta Llama 3 70B Instruct Turbo Together text $0.88/1M $0.88/1M 8K
Meta Llama 3.1 70B Instruct Turbo Together text $0.88/1M $0.88/1M 131K
Qwen2 72B Instruct Together text $0.9/1M $0.9/1M 33K
Kimi K2.7 Code Together text $0.95/1M $4/1M 262K
GLM 5 Fp4 Together text $1/1M $3.2/1M 203K
Inkling FP4 Together text $1/1M $4.05/1M 524K
Meta Llama 3.3 70B Instruct Turbo Together text $1.04/1M $1.04/1M 131K
Kimi K2.6 Fp4 Together text $1.2/1M $4.5/1M 262K
Qwen QwQ-32B Together text $1.2/1M $1.2/1M 131K
Qwen2-VL (72B) Instruct Together text $1.2/1M $1.2/1M 33K
Qwen2.5 72B Instruct Together text $1.2/1M $1.2/1M 33K
Qwen2.5 72B Instruct Turbo Together text $1.2/1M $1.2/1M 131K
Muse Spark Open 816B A42B Together text $1.25/1M $4.25/1M 1.0M
DeepSeek V4 Pro 0813 Together text $1.32/1M $3.96/1M 1.0M
GLM 5.1 FP4 Together text $1.4/1M $4.4/1M 203K
GLM 5.2 Together text $1.4/1M $4.4/1M 1.0M
GLM 5.3 Together text $1.4/1M $4.4/1M 1.0M
DeepSeek R1 Distill Qwen 14B Together text $1.6/1M $1.6/1M 131K
Qwen2.5-VL (72B) Instruct Together text $1.95/1M $8/1M 33K
DeepSeek R1 Distill Llama 70B Together text $2/1M $2/1M 131K
Qwen3 Coder 480B A35B Instruct Fp8 Together text $2/1M $2/1M 262K
Qwen3.8-2.4T-A95B Together text $2/1M $6/1M 1.0M
Qwen3.7 Max Together text $2.5/1M $7.5/1M 1M
DeepSeek R1 0528 NVFP4 Together text $3/1M $7/1M 164K
Kimi K3 Together text $3/1M $15/1M 1.0M
Meta Llama 3.1 405B Instruct Together text $3.5/1M $3.5/1M 4K
Cogito V1 Preview Llama 70B Together text Not published— Not published— 131K
Cogito V1 Preview Llama 70B Turbo Together text Not published— Not published— 131K
Cogito V1 Preview Llama 8B Together text Not published— Not published— 131K
Cogito V1 Preview Qwen 14B Together text Not published— Not published— 131K
Cogito V1 Preview Qwen 32B Together text Not published— Not published— 131K
Deepcoder 14B Preview Together text Not published— Not published— 131K
Deepseek OCR 2 Together text Not published— Not published— 8K
DeepSeek R1 Distill Qwen 7B Together text Not published— Not published— 131K
Devstral Small 2505 Together text Not published— Not published— 131K
EssentialAI Rnj-1 Instruct Together text Not published— Not published— 33K
Facebook CWM Together text Not published— Not published— 131K
Gemma 2 9B It Together text Not published— Not published— 8K
Gemma 2B It Together text Not published— Not published— 8K
Gemma 3 1b it Together text Not published— Not published— 33K
Gemma 3 1B Pt Together text Not published— Not published— 33K
Gemma 3 270M It Together text Not published— Not published— 33K
Gemma 3 270M It Lora Together text Not published— Not published— 33K
Gemma 3 27B It Together text Not published— Not published— 66K
Gemma 3 27B It Lora Together text Not published— Not published— —

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