T
Together
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-05-222026-06-20
Inference Latency
LiquidAI: LFM2-24B-A2B185ms TTFT · 59 TPS
OpenAI: gpt-oss-20b458ms TTFT · 93 TPS
Google: Gemma 3n 4B277ms TTFT · 31 TPS
Meta: Llama 3 8B Instruct573ms TTFT · 59 TPS
EssentialAI: Rnj 1 Instruct532ms TTFT · 67 TPS
OpenAI: gpt-oss-120b296ms TTFT · 99 TPS
Qwen: Qwen3.5-9B477ms TTFT · 31 TPS
Qwen: Qwen3 235B A22B Instruct 2507773ms TTFT · 30 TPS
Mistral: Mistral 7B Instruct v0.2315ms TTFT · 78 TPS
Meta: Llama Guard 4 12B117ms TTFT · 19 TPS
Qwen: Qwen2.5 7B Instruct594ms TTFT · 96 TPS
MiniMax: MiniMax M2.7655ms TTFT · 70 TPS
MiniMax: MiniMax M31015ms TTFT · 42 TPS
Google: Gemma 4 31B1077ms TTFT · 35 TPS
Qwen: Qwen3.5 397B A17B434ms TTFT · 121 TPS
NVIDIA: Nemotron 3 Ultra573ms TTFT · 87 TPS
MoonshotAI: Kimi K2.7 Code740ms TTFT · 95 TPS
Z.ai: GLM 5869ms TTFT · 102 TPS
Meta: Llama 3.3 70B Instruct1194ms TTFT · 23 TPS
MoonshotAI: Kimi K2.6529ms TTFT · 119 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| LiquidAI: LFM2-24B-A2B | $0.03 | $0.12 | 185ms | 59 |
| OpenAI: gpt-oss-20b | $0.05 | $0.20 | 458ms | 93 |
| Google: Gemma 3n 4B | $0.06 | $0.12 | 277ms | 31 |
| Meta: Llama 3 8B Instruct | $0.14 | $0.14 | 573ms | 59 |
| EssentialAI: Rnj 1 Instruct | $0.15 | $0.15 | 532ms | 67 |
| OpenAI: gpt-oss-120b | $0.15 | $0.60 | 296ms | 99 |
| Qwen: Qwen3.5-9B | $0.17 | $0.25 | 477ms | 31 |
| Arcee AI: Spotlight | $0.18 | $0.18 | — | — |
| Qwen: Qwen3 235B A22B Instruct 2507 | $0.20 | $0.60 | 773ms | 30 |
| Mistral: Mistral 7B Instruct | $0.20 | $0.20 | — | — |
| Mistral: Mistral 7B Instruct v0.3 | $0.20 | $0.20 | — | — |
| Meta: LlamaGuard 2 8B | $0.20 | $0.20 | — | — |
| Mistral: Mistral 7B Instruct v0.2 | $0.20 | $0.20 | 315ms | 78 |
| Meta: Llama Guard 4 12B | $0.20 | $0.20 | 117ms | 19 |
| Qwen: Qwen2.5 7B Instruct | $0.30 | $0.30 | 594ms | 96 |
| MiniMax: MiniMax M2.7 | $0.30 | $1.20 | 655ms | 70 |
| MiniMax: MiniMax M3 | $0.30 | $1.20 | 1015ms | 42 |
| Google: Gemma 4 31B | $0.39 | $0.97 | 1077ms | 35 |
| Arcee AI: Coder Large | $0.50 | $0.80 | — | — |
| Qwen: Qwen3.5 397B A17B | $0.60 | $3.60 | 434ms | 121 |
| NVIDIA: Nemotron 3 Ultra | $0.60 | $3.60 | 573ms | 87 |
| Arcee AI: Virtuoso Large | $0.75 | $1.20 | — | — |
| Arcee AI: Maestro Reasoning | $0.90 | $3.30 | — | — |
| MoonshotAI: Kimi K2.7 Code | $0.95 | $4.00 | 740ms | 95 |
| Z.ai: GLM 5 | $1.00 | $3.20 | 869ms | 102 |
| Meta: Llama 3.3 70B Instruct | $1.04 | $1.04 | 1194ms | 23 |
| MoonshotAI: Kimi K2.6 | $1.20 | $4.50 | 529ms | 119 |
| Deep Cogito: Cogito v2.1 671B | $1.25 | $1.25 | 343ms | 13 |
| Z.ai: GLM 5.1 | $1.40 | $4.40 | 951ms | 74 |
| DeepSeek: DeepSeek V4 Pro | $1.74 | $3.48 | 654ms | 70 |
Community Reviews
4.5★★★★★(2 reviews)
clouduser42
★★★★★2025-06-15
Reliable service, great API documentation.
mlresearcher
★★★★☆2025-06-10
Good performance but support could be faster.