Inference provider
DeepInfra
70 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
70
Median output speed
90 t/s
Median latency
450ms
Median price / 1M
$0.337
Catalogue
Strongest and fastest on this provider
What the catalogue looks like at the top end, on the two axes that usually decide the choice.
Highest Intelligence Index
Among models this provider serves
- MiMo-V2.6-ProXiaomi46.3
- GLM 5.3Z.ai44.8
- Step 5 PreviewStepFun43.7
- Kimi K3Moonshot AI43.6
- GLM 5.3 FlashZ.ai41.8
- Ling 3.1 FlashInclusionAI41.1
- V4.1 FlashDeepSeek39.5
- MiMo-V2.6-FlashXiaomi37.9
- V4 Pro 0813DeepSeek36.0
- V4 Pro 0423DeepSeek36.0
View as table
| Model | Intelligence |
|---|---|
| MiMo-V2.6-Pro (Xiaomi) | 46.3 |
| GLM 5.3 (Z.ai) | 44.8 |
| Step 5 Preview (StepFun) | 43.7 |
| Kimi K3 (Moonshot AI) | 43.6 |
| GLM 5.3 Flash (Z.ai) | 41.8 |
| Ling 3.1 Flash (InclusionAI) | 41.1 |
| V4.1 Flash (DeepSeek) | 39.5 |
| MiMo-V2.6-Flash (Xiaomi) | 37.9 |
| V4 Pro 0813 (DeepSeek) | 36.0 |
| V4 Pro 0423 (DeepSeek) | 36.0 |
Fastest output
Median tokens per second
- gpt-oss-120bOpenAI641 t/s
- 461 t/s
- gpt-oss-20bOpenAI410 t/s
- Qwen3.8 27BQwen409 t/s
- GLM 5.2Z.ai368 t/s
- V4.1 FlashDeepSeek296 t/s
- 255 t/s
- Nemotron 3.5 LightningNVIDIA226 t/s
- V4 Flash 0731DeepSeek223 t/s
- Gemma 4 31BGoogle193 t/s
View as table
| Model | Tokens/s |
|---|---|
| gpt-oss-120b (OpenAI) | 641 |
| Llama 3.1 8B Instruct (Meta) | 461 |
| gpt-oss-20b (OpenAI) | 410 |
| Qwen3.8 27B (Qwen) | 409 |
| GLM 5.2 (Z.ai) | 368 |
| V4.1 Flash (DeepSeek) | 296 |
| Nemotron 3.5 Content Safety (NVIDIA) | 255 |
| Nemotron 3.5 Lightning (NVIDIA) | 226 |
| V4 Flash 0731 (DeepSeek) | 223 |
| Gemma 4 31B (Google) | 193 |
Full catalogue
All 70 models on DeepInfra
Filter by creator
70 of 70 models| MiMo-V2.6-Pro Xiaomiopen | 46.3 | $0.09 |
| GLM 5.3 Z.aiopen | 44.8 | $0.39 |
| Step 5 Preview StepFunopen | 43.7 | $0.27 |
| Kimi K3 Moonshot AIopen | 43.6 | $1.22 |
| GLM 5.3 Flash Z.aiopen | 41.8 | $0.05 |
| Ling 3.1 Flash InclusionAI | 41.1 | $0.02 |
| V4.1 Flash DeepSeekopen | 39.5 | $0.07 |
| MiMo-V2.6-Flash Xiaomiopen | 37.9 | $0.03 |
| V4 Pro 0813 DeepSeekopen | 36.0 | $0.38 |
| V4 Pro 0423 DeepSeekopen | 36.0 | $0.20 |
| V4 Flash 0731 DeepSeekopen | 34.3 | $0.05 |
| V4 Flash 0423 DeepSeekopen | 34.3 | $0.02 |
| Qwen3.8 27B Qwenopen | 33.7 | $0.19 |
| GLM 5.2 Z.aiopen | 33.7 | $0.56 |
| MiniMax M3 MiniMaxopen | 29.2 | $0.11 |
| Kimi K2.6 Moonshot AIopen | 27.0 | $0.31 |
| Inkling Small Thinking Machinesopen | 25.7 | $0.12 |
| Inkling Thinking Machinesopen | 25.0 | $0.37 |
| Ling 3.0 Flash VL InclusionAIopen | 24.6 | $0.02 |
| Qwen3.5-27B Qwenopen | 22.9 | $0.22 |
| GLM 4.7 Z.aiopen | 22.2 | $0.21 |
| Qwen3.6 27B Qwenopen | 21.4 | $0.27 |
| Ling 3.0 Flash InclusionAIopen | 20.1 | $0.006 |
| Qwen3.5-35B-A3B Qwenopen | 19.3 | $0.09 |
| Qwen3.5 397B A17B Qwenopen | 18.4 | $0.31 |
| Qwen3.6 35B A3B Qwenopen | 18.2 | $0.09 |
| V3.2 DeepSeekopen | 16.0 | $0.08 |
| GLM 4.6 Z.aiopen | 14.9 | $0.18 |
| Nemotron 3.5 Lightning NVIDIAopen | 12.9 | $0.02 |
| gpt-oss-120b OpenAIopen | 11.6 | $0.06 |
| Qwen3.5-9B Qwenopen | 11.2 | $0.02 |
| Granite 4.2 8B IBM Graniteopen | 11.1 | $0.02 |
| Qwen3 VL 235B A22B Instruct Qwenopen | 9.9 | $0.06 |
| Qwen3 Next 80B A3B Instruct Qwenopen | 9.6 | $0.03 |
| gpt-oss-20b OpenAIopen | 9.0 | $0.008 |
| Qwen3 VL 30B A3B Instruct Qwenopen | 7.9 | $0.02 |
| Qwen2.5 72B Instruct Qwenopen | 7.7 | $0.03 |
| Llama 4 Scout Metaopen | 6.5 | $0.02 |
| Hermes 3 70B Instruct Nous Researchopen | 6.0 | $0.05 |
| Phi 4 Microsoftopen | 5.9 | $0.007 |