Together
Serves 19 models, cheapest of all providers for 2.
Checked Oct 21, 2026
19
models
2
cheapest provider for
95.8%
uptime, last 1 days
20%
worst 30-minute reading
Models on Together
| Model | Input / 1M | Output / 1M | Context | Uptime | Price rank |
|---|---|---|---|---|---|
| Muse Spark Open | $1.25 | $4.25 | 1.05M | 98.9% | cheapest of 5 |
| Qwen3.8 2.4T A95B | $2.00 | $6.00 | 1.01M | 98.4% | cheapest of 5 |
| Beam 1.0 501B A23B | $0.40 | $1.20 | 1.05M | 100% | 3 others |
| DeepSeek V4 Flash 0731 | $0.14 | $0.28 | 1.05M | 96.5% | 25 others |
| DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 1.05M | 94.2% | 22 others |
| DeepSeek V4.1 Flash | $0.30 | $1.20 | 1.05M | 96.5% | 37 others |
| DeepSeek V4.1 Flash 1017 | $0.30 | $1.20 | 1.05M | 99.9% | 24 others |
| Glimpse | $0.60 | $3.00 | 262K | 99.3% | only provider |
| GLM 5.2 | $1.40 | $4.40 | 1.05M | 92.7% | 33 others |
| GLM 5.3 | $1.40 | $4.40 | 1.05M | 91.9% | 46 others |
| GLM 5.3 Flash | $0.15 | $0.50 | 1.05M | 87.2% | 34 others |
| gpt-oss-120b | $0.15 | $0.60 | 131K | 97.3% | 23 others |
| Inkling | $1.00 | $4.05 | 524K | 98.2% | 1 others |
| Kimi K3 | $3.00 | $15.00 | 1.05M | 99.7% | 27 others |
| Llama 3.3 70B Instruct | $1.04 | $1.04 | 131K | 92.1% | 10 others |
| MiniMax M3 | $0.30 | $1.20 | 524K | 99.8% | 13 others |
| Muse Glimmer 30B | $0.35 | $1.50 | 131K | 92.6% | 1 others |
| Nemotron 3.5 Super VL | $0.15 | $0.50 | 262K | 86.1% | 5 others |
| Qwen3.5-9B | $0.17 | $0.25 | 262K | 99% | 4 others |
Uptime as reported by OpenRouter for this provider’s endpoints. All providers · methodology