Together AI
Inference providerUS Westprices checked Oct 23, 06:00 UTC
Together AI serves 23 models at a verified price. On the 23 it shares with other hosts, it is the cheapest on 3 and charges a median 68% above the cheapest.
Models served2321 with open weights · +2 without a price
Cheapest input, per M$0.05gpt-oss-20b
Uptime, last 24 h98.5%average of its 17 OpenRouter endpoints
Sign-upNot checked yetno free credits stated
| Model | Precision | Context | Tools | Input | Output | Cache |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | fp8 | 1M | ✓ | $0.30 | $1.20 | $0.006 |
| Muse Spark Opencheapest | nvfp4 | 1M | ✓ | $1.25 | $4.25 | $0.15 |
| Nemotron 3.5 Super VL | nvfp4 | 256K | ✓ | $0.15 | $0.50 | $0.02 |
| Tev1 4B Experimentalno verified price | — | 32K | — | — | — | — |
| DeepSeek V4.1 Flash | fp8 | 1M | ✓ | $0.30 | $1.20 | $0.006 |
| GLM-5.3-Flash | fp4 | 1.05M | ✓ | $0.15 | $0.50 | $0.03 |
| Qwen3.8 Flashcheapest | — | 1M | — | $0.15 | $0.47 | — |
| GLM-5.3 | fp4 | 1.05M | — | $1.40 | $4.40 | — |
| DeepSeek V4 Pro 0813 | nvfp4 | 1M | ✓ | $1.32 | $3.96 | $0.13 |
| Qwen3.8 2.4T A95Bcheapest | fp4 | 1.01M | ✓ | $2.00 | $6.00 | $0.25 |
| Muse Glimmer 30B (Meta) | fp8 | 128K | ✓ | $0.35 | $1.50 | $0.04 |
| DeepSeek V4 Flash 0731 | nvfp4 | 1M | ✓ | $0.14 | $0.28 | $0.03 |
| Inkling Small | not checked yet | 512K | — | $0.50 | $1.20 | $0.10 |
| Kimi K3 | not stated by the host | 1M | ✓ | $3.00 | $15.00 | $0.30 |
| Inkling | nvfp4 | 512K | ✓ | $1.00 | $4.05 | $0.17 |
| Ternary Bonsai 27Bno verified price | — | 256K | — | — | — | — |
| GLM 5.2 | fp4 | 1.05M | ✓ | $1.40 | $4.40 | $0.26 |
| Kimi K2.7 Code | not stated by the host | 256K | — | $0.95 | $4.00 | $0.19 |
| MiniMax-M3 | fp4 | 512K | ✓ | $0.30 | $1.20 | $0.06 |
| Gemma 4 31B | fp8 | 256K | — | $0.39 | $0.97 | — |
| Qwen3.5 9B | fp8 | 256K | ✓ | $0.17 | $0.25 | — |
| MiniMax M3.1 Flash | — | 1M | ✓ | $0.15 | $0.60 | $0.015 |
| gpt-oss-120b | mxfp4 | 128K | ✓ | $0.15 | $0.60 | — |
| gpt-oss-20b | not stated by the host | 125K | — | $0.05 | $0.20 | — |
| Llama 3.3 70B | fp8 | 128K | ✓ | $1.04 | $1.04 | — |
10 of 25 models · prices per million tokens · precision and context: read at Together AI's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as Together AI declares them to OpenRouter
| Condition | What it says | Source |
|---|---|---|
| Sign-up | Not checked yet | docs.together.ai |
| Free credits | None stated | — |
| Headquarters region | US West | — |
| Price list | Where its per-token prices are published | together.ai |
| API documentation | Its own docs | docs.together.ai |
| Status page | Outages and incidents, as Together AI reports them | status.together.ai |
| Terms of service | Its terms | together.ai |
| Free model | Ternary Bonsai 27B, free at Together AI | together.ai |
| Discount | Tev1 4B Experimental: free output tokens at Together AI | together.ai |
Links checked Oct 8.