Together AI models
A research-driven AI cloud infrastructure provider
| Model | Context | Input | Output | Latency | Throughput | Cache | Web Search | Capabilities | ZDR | No Training | Regional Inference | Free Tier | Released |
|---|
| 1M | $0.15/M | $0.50/M | 1.3 s | 85 tps | Read$0.03/M | — | +1 | 08/26/2026 | |||||
| 1M | $1.40/M | $4.40/M | 0.3 s | 73 tps | Read$0.26/M | — | 08/18/2026 | ||||||
| 131K | $0.35/M | $1.50/M | 0.2 s | 93 tps | Read$0.04/M | — | +1 | 08/10/2026 | |||||
| 256K | $2.50/M | $6.25/M | 0.3 s | — | Read$0.50/M | — | 08/03/2026 | ||||||
| 1M | $0.14/M | $0.28/M | 0.7 s | 138 tps | Read$0.03/M | — | 07/31/2026 | ||||||
| 1M | $0.50/M | $1.20/M | 0.3 s | 322 tps | Read$0.10/M | — | +2 | 07/30/2026 | |||||
| 1M | $3/M | $15/M | 1.1 s | 64 tps | Read$0.30/M | — | +2 | 07/16/2026 | |||||
| 256K | $1.20/M | $4.05/M | 0.6 s | 113 tps | Read$0.20/M | — | +1 | 07/15/2026 | |||||
| 256K | $1.40/M | $4.40/M | 0.2 s | 58 tps | Read$0.26/M | — | 06/16/2026 | ||||||
| 1M | $0.60/M | $3.60/M | — | — | Read$0.20/M | — | 06/04/2026 | ||||||
| 1M | $2.10/M | $4.40/M | — | — | Read$0.20/M | — | 04/23/2026 | ||||||
| 256K | $0.39/M | $0.97/M | 1.0 s | 9 tps | — | — | +1 | 04/02/2026 | |||||
| 1M | $0.50/M | $3/M | — | — | — | — | +1 | 04/02/2026 | |||||
| 128K | $0.15/M | $0.60/M | 0.4 s | 57 tps | — | — | 08/05/2025 | ||||||
| 131K | $0.05/M | $0.20/M | 0.3 s | 58 tps | — | — | 08/05/2025 |