About Together
Inference platform hosting 200+ open-source models with simple per-token pricing. Strong coverage of Qwen, GLM, Kimi, MiniMax, and DeepSeek variants.
13 models
All Together models
Sorted by blended cost (cheapest first). Prices per 1M tokens.
| Model | Input | Output | Blended | Relative cost | Context | Status |
|---|---|---|---|---|---|---|
| LFM2 24B A2B | $0.030 | $0.120 | $0.075 |
128K | Current | |
| gpt-oss-120B | $0.150 | $0.600 | $0.375 |
128K | Current | |
| Gemma-4-31B-it-Pearl | $0.280 | $0.860 | $0.570 |
128K | Current | |
| MiniMax M2.5 | $0.300 | $1.20 | $0.750 |
128K | Current | |
| MiniMax M3 | $0.300 | $1.20 | $0.750 |
1M | Current | |
| Qwen3.7-Plus | $0.320 | $1.28 | $0.800 |
128K | Current | |
| Llama 3.3 70B | $1.04 | $1.04 | $1.04 |
128K | Current | |
| NVIDIA Nemotron 3 Ultra | $0.600 | $3.60 | $2.10 |
128K | Current | |
| Qwen3.5-397B-A17B | $0.600 | $3.60 | $2.10 |
128K | Current | |
| Kimi K2.7 Code | $0.950 | $4.00 | $2.48 |
256K | Current | |
| Qwen3.7-Max | $1.25 | $3.75 | $2.50 |
128K | Current | |
| DeepSeek V4 Pro | $1.74 | $3.48 | $2.61 |
1M | Current | |
| GLM-5.2 | $1.40 | $4.40 | $2.90 |
128K | Current |
Quick stats
Open-weight models
12 open-weight models available from this provider.