Together
25 modelsWebsite
Models via Together
| Model | Input/1M | Output/1M |
|---|---|---|
Llama 3.3 70B Instruct | $0.88 | $0.88 |
Llama 3.1 405B Instruct | $3.50 | $3.50 |
Qwen2.5 72B Instruct | $1.20 | $1.20 |
Qwen3 235B A22B | $0.20 | $0.60 |
Gemma 4 31B | $0.39 | $0.97 |
Llama 3.1 70B Instruct | $0.89 | $0.89 |
Qwen3.6 Plus | $0.50 | $3.00 |
DeepSeek-R1 | $7.00 | $7.00 |
Qwen3.7 Max | $2.50 | $7.50 |
DeepSeek-V4-Pro-Max | $1.74 | $3.48 |
Llama 4 Maverick | $0.27 | $0.85 |
Llama 3.2 90B Instruct | $1.20 | $1.20 |
Kimi K2.6 | $1.20 | $4.50 |
Qwen3.8 Max | $2.50 | $6.25 |
Qwen3.7-Plus | $0.32 | $1.28 |
Kimi K3 | $3.00 | $15.00 |
Llama 4 Scout | $0.18 | $0.59 |
Qwen2.5 7B Instruct | $0.30 | $0.30 |
QwQ-32B-Preview | $1.20 | $1.20 |
Llama 3.2 11B Instruct | $0.18 | $0.18 |
Llama 3.1 8B Instruct | $0.20 | $0.20 |
GLM-5.2 | $1.40 | $4.40 |
DeepSeek-V4-Pro-0813 | $1.32 | $3.96 |
MiniMax M3 | $0.30 | $1.20 |
Gemma 3n E4B Instructed | $20.00 | $40.00 |
Platform Capabilities
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning
Other API Providers
Together pricing and capabilities data updated in 2026. See also cheapest models and model comparisons.