Skip to content
Together AI

Together AI

Inference API Provider

Reputation:
78/100
together.ai

Provider Overview

Type

inference

Billing

Per token

Egress

Free

SLA Uptime

99.9%

Autoscaling

Yes

Cold Start

None

Model Pricing (20)

ModelInput $/MOutput $/MLatencyThroughputContext
phi-3-mini-128kCheapest$0.10$0.100.15s220 t/s128k
llama-3.1-8b$0.18$0.180.2s200 t/s128k
qwen-2.5-7b$0.20$0.200.2s180 t/s32k
codellama-7b$0.20$0.200.15s200 t/s16k
codellama-13b$0.22$0.220.2s150 t/s16k
gemma-2-9b$0.30$0.300.2s160 t/s8k
phi-4-14b$0.30$0.300.2s140 t/s16k
deepseek-v3$0.50$0.500.4s70 t/s64k
qwen-2.5-32b$0.50$0.500.3s110 t/s32k
qwen-2.5-coder-32b$0.50$0.500.3s105 t/s32k
phi-3-medium-128k$0.50$0.500.25s120 t/s128k
mixtral-8x7b$0.60$0.600.3s100 t/s33k
codellama-34b$0.78$0.780.4s70 t/s16k
gemma-2-27b$0.80$0.800.3s85 t/s8k
llama-3.1-70b$0.88$0.880.4s80 t/s128k
llama-3.3-70b$0.88$0.880.35s85 t/s128k
qwen-2.5-72b$0.90$0.900.4s75 t/s32k
mixtral-8x22b$1.20$1.200.5s60 t/s66k
llama-3.1-405b$3.50$3.500.8s35 t/s128k
deepseek-r1$3.00$7.502s30 t/s64k

Reputation Details

Pricing
70
Reliability
90
Features
75

Highlights

  • Good pricing
  • 99.9%+ SLA
  • Autoscaling supported
  • Fast cold start

Compare with Others

ProviderOverallPricingReliabilityFeaturesModels
Together AI7870907520
Fireworks AI7870907514
Groq8690907510
DeepInfra8690907521
DeepSeek727070753