T
Together
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
96.7%2026-09-192026-10-18
Inference Latency
LiquidAI: LFM2-24B-A2B173ms TTFT · 68 TPS
Google: Gemma 3n 4B307ms TTFT · 30 TPS
DeepSeek: DeepSeek V4 Flash 0731694ms TTFT · 59 TPS
Meta: Llama 3 8B Instruct791ms TTFT · 29 TPS
Z.ai: GLM 5.3 Flash434ms TTFT · 151 TPS
OpenAI: gpt-oss-120b317ms TTFT · 119 TPS
EssentialAI: Rnj 1 Instruct201ms TTFT · 121 TPS
NVIDIA: Nemotron 3.5 Super VL597ms TTFT · 132 TPS
Qwen: Qwen3.5-9B176ms TTFT · 102 TPS
Mistral: Mistral 7B Instruct v0.2315ms TTFT · 78 TPS
MiniMax: MiniMax M3653ms TTFT · 86 TPS
DeepSeek: DeepSeek V4.1 Flash344ms TTFT · 192 TPS
Meta: Muse Glimmer 30B333ms TTFT · 88 TPS
Reflection: Beam 1.0 501B A23B94ms TTFT · 152 TPS
Elorian: Glimpse692ms TTFT · 134 TPS
Thinking Machines: Inkling570ms TTFT · 134 TPS
Meta: Llama 3.3 70B Instruct612ms TTFT · 60 TPS
Meta: Muse Spark Open578ms TTFT · 98 TPS
DeepSeek: DeepSeek V4 Pro 0813839ms TTFT · 126 TPS
Z.ai: GLM 5.2329ms TTFT · 164 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| LiquidAI: LFM2-24B-A2B | $0.03 | $0.12 | 173ms | 68 |
| Google: Gemma 3n 4B | $0.06 | $0.12 | 307ms | 30 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.14 | $0.28 | 694ms | 59 |
| Meta: Llama 3 8B Instruct | $0.14 | $0.14 | 791ms | 29 |
| Z.ai: GLM 5.3 Flash | $0.15 | $0.50 | 434ms | 151 |
| OpenAI: gpt-oss-120b | $0.15 | $0.60 | 317ms | 119 |
| EssentialAI: Rnj 1 Instruct | $0.15 | $0.15 | 201ms | 121 |
| NVIDIA: Nemotron 3.5 Super VL | $0.15 | $0.50 | 597ms | 132 |
| Qwen: Qwen3.5-9B (batch) | $0.17 | $0.25 | — | — |
| Qwen: Qwen3.5-9B | $0.17 | $0.25 | 176ms | 102 |
| Arcee AI: Spotlight | $0.18 | $0.18 | — | — |
| Mistral: Mistral 7B Instruct | $0.20 | $0.20 | — | — |
| Meta: LlamaGuard 2 8B | $0.20 | $0.20 | — | — |
| Mistral: Mistral 7B Instruct v0.2 | $0.20 | $0.20 | 315ms | 78 |
| Mistral: Mistral 7B Instruct v0.3 | $0.20 | $0.20 | — | — |
| MiniMax: MiniMax M3 | $0.30 | $1.20 | 653ms | 86 |
| DeepSeek: DeepSeek V4.1 Flash | $0.30 | $1.20 | 344ms | 192 |
| MiniMax: MiniMax M3 (batch) | $0.30 | $1.20 | — | — |
| Meta: Muse Glimmer 30B | $0.35 | $1.50 | 333ms | 88 |
| Google: Gemma 4 31B (batch) | $0.39 | $0.97 | — | — |
| Reflection: Beam 1.0 501B A23B | $0.40 | $1.20 | 94ms | 152 |
| Arcee AI: Coder Large | $0.50 | $0.80 | — | — |
| Thinking Machines: Inkling Small (batch) | $0.50 | $1.20 | — | — |
| NVIDIA: Nemotron 3 Ultra (batch) | $0.60 | $3.60 | — | — |
| Elorian: Glimpse | $0.60 | $3.00 | 692ms | 134 |
| Arcee AI: Virtuoso Large | $0.75 | $1.20 | — | — |
| Arcee AI: Maestro Reasoning | $0.90 | $3.30 | — | — |
| MoonshotAI: Kimi K2.7 Code (batch) | $0.95 | $4.00 | — | — |
| Thinking Machines: Inkling | $1.00 | $4.05 | 570ms | 134 |
| Thinking Machines: Inkling (batch) | $1.00 | $4.05 | — | — |
| Meta: Llama 3.3 70B Instruct | $1.04 | $1.04 | 612ms | 60 |
| Deep Cogito: Cogito v2.1 671B | $1.25 | $1.25 | — | — |
| Meta: Muse Spark Open | $1.25 | $4.25 | 578ms | 98 |
| DeepSeek: DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 839ms | 126 |
| Z.ai: GLM 5.2 | $1.40 | $4.40 | 329ms | 164 |
| Z.ai: GLM 5.3 | $1.40 | $4.40 | 607ms | 80 |
| Qwen: Qwen3.8 2.4T A95B | $2.00 | $6.00 | 346ms | 164 |
| Qwen: Qwen3.8 2.4T A95B (batch) | $2.00 | $6.00 | — | — |
| MoonshotAI: Kimi K3 | $3.00 | $15.00 | 1621ms | 32 |
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.