modelbenchmark.io
All hosts

together_ai

60 models listed here. Prices are this host's, not the vendor list price.

ai-21-1b-41b—$0.80$0.80
ai-4-1b-8b—$0.20$0.20
ai-41-1b-80b—$0.90$0.90
ai-8-1b-21b—$0.30$0.30
ai-81-1b-110b—$1.80$1.80
ai-up-to-4b—$0.10$0.10
codellama-34b-instruct———
DeepSeek V4 Flash1M$0.14$0.28
DeepSeek V4 Pro512K$1.74$3.48
DeepSeek-R1128K$3.00$7.00
deepseek-r1-0528-tput128K$0.55$2.19
DeepSeek/DeepSeek-V3.2-Exp66K$1.25$1.25
E5 Multi-Lingual Large Embeddings 0.6B1K$0.02$0.02
Gemma 3n E4b It33K$0.06$0.12
Gemma 4 31B IT262K$0.39$0.97
glm-4-5-air-fp8128K$0.20$1.10
GLM-4.6200K$0.60$2.20
GLM-4.7200K$0.45$2.00
GLM-5.21M$1.40$4.40
GLM-5.31M$1.40$4.40
GLM-5.3-Flash1M$0.15$0.50
gpt-oss-120b131K$0.15$0.60
gpt-oss-20b131K$0.05$0.20
Inkling524K$1.00$4.05
Inkling Small Thinking524K$0.50$1.20
Kimi K2 0905262K$1.00$3.00
Kimi K2.5256K$0.50$2.80
Kimi K2.7 Code262K$0.95$4.00
Kimi K31M$3.00$15.00
Llama 3.1 405B Instruct Turbo—$3.50$3.50
Llama 3.3 70B Turbo131K$1.04$1.04
Llama 4 Maverick 17B FP8—$0.27$0.85
Llama 4 Scout 17B 16E Instruct—$0.18$0.59
llama-3-2-3b-instruct-turbo———
llama-3-3-70b-instruct-turbo-free—freefree
meta-llama-3-1-70b-instruct-turbo—$0.88$0.88
meta-llama-3-1-8b-instruct-turbo—$0.18$0.18
MiniMax-M3524K$0.30$1.20
Mistral Small 3———
Mistral-7B-Instruct-v0.3———
Mistral: Mixtral 8x7B Instruct—$0.60$0.60
Muse Glimmer 30B131K$0.35$1.50
Nemotron 3 Ultra 550B A55B512K$0.60$3.60
Qwen 2.5 7B Instruct Turbo———
qwen-2-1-5b-instruct33K$0.10$0.10
qwen2-5-72b-instruct-turbo———
Qwen3 235B A22B Instruct 2507 FP8262K$0.20$6.00
Qwen3 235B A22B Thinking 2507256K$0.65$3.00
Qwen3 Coder 480B A35B Instruct256K$2.00$2.00
qwen3-235b-a22b-fp8-tput40K$0.20$0.60
Qwen3-Next 80B-A3B (Thinking)262K$0.15$1.50
Qwen3-Next 80B-A3B Instruct262K$0.15$1.50
Qwen3.5 397B-A17B262K$0.60$3.60
Qwen3.5 9B262K$0.17$0.25
Qwen3.6 Plus1M$0.50$3.00
Qwen3.7 Max1M$2.50$7.50
Qwen3.7 Plus1M$0.32$1.28
Qwen3.8 2.4T A95B1M$2.50$6.25
Qwen3.8 Flash1M$0.15$0.47
ternary-bonsai-27b262Kfreefree