D
DeepInfra
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-09-192026-10-18
Inference Latency
Meta: Llama 3.1 8B Instruct488ms TTFT · 31 TPS
Mistral: Mistral Nemo1021ms TTFT · 19 TPS
OpenAI: gpt-oss-20b355ms TTFT · 69 TPS
OpenAI: gpt-oss-120b352ms TTFT · 56 TPS
OpenAI: gpt-oss-120b (exacto)500ms TTFT · 64 TPS
NVIDIA: Nemotron Nano 9B V2244ms TTFT · 119 TPS
Google: Gemma 3 12B3056ms TTFT · 10 TPS
Sao10K: Llama 3 8B Lunaris202ms TTFT · 93 TPS
Mistral: Mistral Small 3361ms TTFT · 46 TPS
Google: Gemma 3 12B404ms TTFT · 61 TPS
Google: Gemma 3 4B830ms TTFT · 57 TPS
inclusionAI: Ling 3.0 Flash492ms TTFT · 63 TPS
NVIDIA: Nemotron 3.5 Lightning551ms TTFT · 213 TPS
DeepSeek: DeepSeek V4 Flash 0731455ms TTFT · 64 TPS
IBM: Granite 4.2 8B608ms TTFT · 94 TPS
inclusionAI: Ling 3.0 Flash VL592ms TTFT · 48 TPS
Microsoft: Phi 4456ms TTFT · 70 TPS
Google: Gemma 4 26B A4B 465ms TTFT · 45 TPS
Google: Gemma 3 12B519ms TTFT · 40 TPS
Z.ai: GLM 5.3 Flash858ms TTFT · 51 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Meta: Llama 3.1 8B Instruct | $0.02 | $0.04 | 488ms | 31 |
| OpenAI: gpt-oss-20b (batch) | $0.02 | $0.11 | — | — |
| Mistral: Mistral Nemo | $0.03 | $0.03 | 1021ms | 19 |
| OpenAI: gpt-oss-120b (batch) | $0.03 | $0.14 | — | — |
| OpenAI: gpt-oss-20b | $0.03 | $0.14 | 355ms | 69 |
| OpenAI: gpt-oss-120b | $0.04 | $0.17 | 352ms | 56 |
| OpenAI: gpt-oss-120b (exacto) | $0.04 | $0.19 | 500ms | 64 |
| NVIDIA: Nemotron Nano 9B V2 | $0.04 | $0.16 | 244ms | 119 |
| Google: Gemma 3 12B | $0.04 | $0.12 | 3056ms | 10 |
| Sao10K: Llama 3 8B Lunaris | $0.04 | $0.05 | 202ms | 93 |
| Mistral: Mistral Small 3 | $0.05 | $0.08 | 361ms | 46 |
| Google: Gemma 3 12B | $0.05 | $0.15 | 404ms | 61 |
| Google: Gemma 3 4B | $0.05 | $0.10 | 830ms | 57 |
| Microsoft: Phi 4 | $0.06 | $0.11 | — | — |
| Z.ai: GLM 5.3 Flash (batch) | $0.06 | $0.20 | — | — |
| inclusionAI: Ling 3.0 Flash | $0.06 | $0.18 | 492ms | 63 |
| NVIDIA: Nemotron 3.5 Lightning | $0.06 | $0.16 | 551ms | 213 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.06 | $0.18 | 455ms | 64 |
| IBM: Granite 4.2 8B | $0.06 | $0.25 | 608ms | 94 |
| inclusionAI: Ling 3.0 Flash VL | $0.06 | $0.18 | 592ms | 48 |
| Microsoft: Phi 4 | $0.07 | $0.14 | 456ms | 70 |
| Google: Gemma 4 26B A4B | $0.07 | $0.34 | 465ms | 45 |
| Qwen: Qwen3 Next 80B A3B Instruct | $0.07 | $0.88 | — | — |
| Google: Gemma 3 12B | $0.08 | $0.22 | 519ms | 40 |
| Z.ai: GLM 5.3 Flash | $0.08 | $0.25 | 858ms | 51 |
| Mistral: Mistral Small 3.2 24B | $0.08 | $0.20 | 497ms | 37 |
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.08 | $0.24 | 4115ms | 48 |
| Meta: Llama 4 Scout | $0.08 | $0.24 | 3155ms | 25 |
| Google: Gemma 3 27B | $0.08 | $0.16 | 1676ms | 26 |
| Qwen: Qwen3 32B | $0.08 | $0.28 | 344ms | 35 |
| NVIDIA: Nemotron 3 Super | $0.09 | $0.40 | 3619ms | 71 |
| DeepSeek: DeepSeek V4 Flash 0423 | $0.09 | $0.18 | 908ms | 39 |
| Qwen: Qwen3 Next 80B A3B Instruct | $0.09 | $1.10 | 509ms | 102 |
| Qwen: Qwen3 235B A22B Instruct 2507 | $0.09 | $0.55 | 447ms | 14 |
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.10 | $0.29 | 878ms | 89 |
| Qwen: Qwen3.6 35B A3B | $0.10 | $0.95 | 542ms | 106 |
| Meta: Llama 3.3 70B Instruct | $0.10 | $0.32 | 494ms | 18 |
| Meta: Llama 4 Scout | $0.10 | $0.30 | 559ms | 39 |
| Qwen: Qwen3.5-9B | $0.10 | $0.15 | 1331ms | 9 |
| NVIDIA: Nemotron 3.5 Super VL | $0.10 | $0.40 | 561ms | 315 |
| DeepSeek: DeepSeek V4.1 Flash (batch) | $0.11 | $0.34 | — | — |
| DeepSeek: DeepSeek V4.1 Flash | $0.11 | $0.34 | 4149ms | 34 |
| Qwen: Qwen3 30B A3B | $0.12 | $0.50 | 1230ms | 102 |
| Qwen: Qwen3 14B | $0.12 | $0.24 | 763ms | 58 |
| Xiaomi: MiMo-V2.6-Flash | $0.13 | $0.27 | 2455ms | 25 |
| Google: Gemma 4 31B | $0.14 | $0.51 | 602ms | 24 |
| Qwen: Qwen3 Next 80B A3B Instruct | $0.14 | $1.65 | 436ms | 92 |
| DeepSeek: DeepSeek V4.1 Flash | $0.14 | $0.42 | 736ms | 67 |
| Qwen: Qwen3.5-35B-A3B | $0.14 | $1.00 | 551ms | 141 |
| Meta: Llama Guard 4 12B | $0.14 | $0.14 | — | — |
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.15 | $0.44 | 1055ms | 88 |
| Qwen: Qwen3.8 27B | $0.15 | $1.88 | 1401ms | 32 |
| Qwen: Qwen3 VL 30B A3B Instruct | $0.15 | $0.60 | 714ms | 22 |
| Meta: Llama 4 Scout | $0.15 | $0.45 | 3229ms | 10 |
| Google: Gemma 4 31B | $0.16 | $0.32 | 4953ms | 17 |
| Meta: Llama Guard 4 12B | $0.18 | $0.18 | — | — |
| NVIDIA: Nemotron 3.5 Content Safety | $0.20 | $0.20 | 290ms | 199 |
| Qwen: Qwen3 VL 235B A22B Instruct | $0.20 | $0.88 | 1925ms | 11 |
| Google: Gemma 4 31B | $0.20 | $0.40 | 633ms | 20 |
| NVIDIA: Nemotron Nano 12B 2 VL | $0.20 | $0.60 | 458ms | 48 |
| Qwen: Qwen2.5 VL 32B Instruct | $0.20 | $0.60 | 617ms | 26 |
| AllenAI: Olmo 3.1 32B Instruct | $0.20 | $0.60 | 586ms | 37 |
| DeepSeek: DeepSeek V3.1 Terminus (exacto) | $0.21 | $0.79 | 1372ms | 18 |
| inclusionAI: Ling 3.1 Flash | $0.21 | $0.63 | 963ms | 74 |
| DeepSeek: DeepSeek V4.1 Flash | $0.21 | $0.63 | 456ms | 63 |
| DeepSeek: DeepSeek V4 Flash Vision Exp | $0.22 | $0.65 | 1243ms | 90 |
| MiniMax: MiniMax M3 | $0.22 | $0.88 | 2827ms | 34 |
| DeepSeek: DeepSeek V3.1 | $0.25 | $0.95 | 767ms | 9 |
| DeepSeek: DeepSeek V3 | $0.26 | $0.71 | — | — |
| DeepSeek: DeepSeek V3.2 | $0.26 | $0.38 | 1027ms | 23 |
| Qwen: Qwen3.5-27B | $0.26 | $2.60 | 344ms | 78 |
| Meta: Llama Guard 4 12B | $0.27 | $0.27 | — | — |
| MiniMax: MiniMax M3 | $0.28 | $1.10 | 973ms | 44 |
| Google: Gemma 4 31B | $0.30 | $0.60 | 553ms | 20 |
| Qwen: Qwen3 Coder 480B A35B | $0.30 | $1.00 | 807ms | 73 |
| Meta: Muse Glimmer 30B | $0.30 | $1.20 | 936ms | 139 |
| DeepSeek: DeepSeek V3 | $0.32 | $0.89 | 525ms | 22 |
| Qwen: Qwen3.6 27B | $0.32 | $3.20 | 720ms | 60 |
| Z.ai: GLM 4.7 | $0.32 | $1.40 | — | — |
| Meta: Llama 3.2 11B Vision Instruct | $0.35 | $0.35 | 580ms | 43 |
| Qwen2.5 72B Instruct | $0.36 | $0.40 | 721ms | 21 |
| NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 | $0.40 | $0.40 | 142ms | 32 |
| Z.ai: GLM 4.7 | $0.40 | $1.75 | 1033ms | 26 |
| Meta: Llama 3.1 70B Instruct | $0.40 | $0.40 | 380ms | 33 |
| MythoMax 13B | $0.40 | $0.40 | 230ms | 48 |
| NVIDIA: Nemotron 3 Ultra | $0.40 | $1.76 | 10415ms | 91 |
| Z.ai: GLM 4.6 | $0.40 | $1.60 | 4256ms | 64 |
| Xiaomi: MiMo-V2.6-Pro | $0.43 | $0.87 | 1653ms | 30 |
| Thinking Machines: Inkling Small | $0.45 | $1.20 | 960ms | 93 |
| Z.ai: GLM 5.2 | $0.45 | $1.44 | 5699ms | 49 |
| Z.ai: GLM 5.3 (batch) | $0.45 | $2.00 | — | — |
| Qwen: Qwen3.5 397B A17B | $0.45 | $3.00 | 749ms | 47 |
| NVIDIA: Nemotron 3 Ultra | $0.50 | $2.20 | 1317ms | 94 |
| Z.ai: GLM 4.6 | $0.50 | $2.00 | 612ms | 56 |
| DeepSeek: R1 0528 | $0.50 | $2.15 | 727ms | 24 |
| Mistral: Mixtral 8x7B Instruct | $0.54 | $0.54 | — | — |
| Z.ai: GLM 5.2 | $0.56 | $1.80 | 1408ms | 81 |
| Z.ai: GLM 5.3 | $0.56 | $2.50 | 1193ms | 80 |
| Nous: Hermes 3 70B Instruct | $0.70 | $0.70 | 757ms | 28 |
| MoonshotAI: Kimi K2.6 | $0.75 | $3.50 | 667ms | 89 |
| Tencent: Hy4 preview | $0.83 | $2.50 | 2633ms | 25 |
| Sao10K: Llama 3.1 Euryale 70B v2.2 | $0.85 | $0.85 | 355ms | 41 |
| Thinking Machines: Inkling | $0.95 | $4.05 | 1127ms | 71 |
| Nous: Hermes 3 405B Instruct | $1.00 | $1.00 | 820ms | 20 |
| StepFun: Step 5 Preview | $1.00 | $2.70 | 382ms | 44 |
| NVIDIA: Llama 3.1 Nemotron 70B Instruct | $1.20 | $1.20 | — | — |
| DeepSeek: DeepSeek V4 Pro 0423 | $1.30 | $2.60 | 916ms | 77 |
| DeepSeek: DeepSeek V4 Pro 0813 | $1.30 | $2.60 | 1324ms | 59 |
| MoonshotAI: Kimi K3 (batch) | $2.28 | $11.40 | — | — |
| MoonshotAI: Kimi K3 | $2.85 | $14.25 | 1054ms | 55 |
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.