Host
Deepinfra
0 models created · 30 host offerings
Active Models
0
Host Offerings
30
Cheapest Input
—
Largest Context
—
Models Hosted
Page 1 of 2 · 30 offerings
| Model | Creator | In / M | Out / M | Context | Quant | Uptime 30m | Latency | TPS |
|---|---|---|---|---|---|---|---|---|
| Qwen: Qwen3 32B DeepInfra | qwen/qwen3-32b-04-28 | — | $0.080 | $0.280 | 41K | fp8 | 100.00% | 320ms | 54.0 |
| StepFun: Step 3.7 Flash DeepInfra | stepfun/step-3.7-flash-20260528 | Stepfun | $0.200 | $1.15 | 262K | — | 99.44% | 250ms | 145.5 |
| Mistral: Mistral Small 3.2 24B DeepInfra | mistralai/mistral-small-3.2-24b-instruct-2506 | — | $0.075 | $0.200 | 128K | fp8 | 98.83% | — | — |
| Qwen: Qwen3.5-35B-A3B DeepInfra | qwen/qwen3.5-35b-a3b-20260224 | Alibaba | $0.140 | $1.00 | 262K | fp8 | 98.44% | 378ms | 140.0 |
| Qwen: Qwen3.5-122B-A10B DeepInfra | qwen/qwen3.5-122b-a10b-20260224 | Alibaba | $0.290 | $2.40 | 262K | fp4 | 98.10% | 325ms | 79.0 |
| DeepSeek: DeepSeek V4 Flash 0731 DeepInfra | deepseek/deepseek-v4-flash-20260731 | Deepseek | $0.080 | $0.180 | 1.0M | fp8 | 98.03% | 815ms | 29.0 |
| Qwen: Qwen3 30B A3B DeepInfra | qwen/qwen3-30b-a3b-04-28 | Alibaba | $0.120 | $0.500 | 41K | fp8 | 97.80% | 246ms | 68.0 |
| Xiaomi: MiMo-V2.5-Pro DeepInfra | xiaomi/mimo-v2.5-pro-20260422 | Xiaomi | $1.00 | $3.00 | 1.0M | fp8 | 97.45% | 667ms | 86.0 |
| Qwen: Qwen3 VL 30B A3B Instruct DeepInfra | qwen/qwen3-vl-30b-a3b-instruct | Alibaba | $0.150 | $0.600 | 262K | fp8 | 96.94% | 566ms | 21.0 |
| Z.ai: GLM 4.7 DeepInfra | z-ai/glm-4.7-20251222 | Z Ai | $0.400 | $1.75 | 203K | fp4 | 96.71% | 1060ms | 35.0 |
| Qwen: Qwen3.5-27B DeepInfra | qwen/qwen3.5-27b-20260224 | Alibaba | $0.260 | $2.60 | 262K | fp8 | 95.88% | 175ms | 51.0 |
| Xiaomi: MiMo-V2.5 DeepInfra | xiaomi/mimo-v2.5-20260422 | Xiaomi | $0.400 | $2.00 | 262K | bf16 | 95.82% | 443ms | 46.0 |
| Z.ai: GLM 5.2 DeepInfra | z-ai/glm-5.2-20260616 | Z Ai | $0.750 | $2.40 | 1.0M | fp4 | 95.55% | 1691ms | 24.0 |
| Z.ai: GLM 4.6 DeepInfra | z-ai/glm-4.6 | Z Ai | $0.500 | $2.00 | 203K | fp4 | 94.89% | 730ms | 28.0 |
| Qwen: Qwen3 Next 80B A3B Instruct DeepInfra | qwen/qwen3-next-80b-a3b-instruct-2509 | Alibaba | $0.090 | $1.10 | 262K | fp8 | 94.59% | 316ms | 56.0 |
| MiniMax: MiniMax M2.7 DeepInfra | minimax/minimax-m2.7-20260318 | Minimax | $0.250 | $1.00 | 197K | fp8 | 94.54% | 566ms | 72.0 |
| Qwen: Qwen3 235B A22B Instruct 2507 DeepInfra | qwen/qwen3-235b-a22b-07-25 | Alibaba | $0.090 | $0.550 | 262K | fp8 | 94.10% | 368ms | 24.0 |
| Qwen: Qwen3.6 27B DeepInfra | qwen/qwen3.6-27b-20260422 | Alibaba | $0.320 | $3.20 | 262K | fp8 | 93.53% | 479ms | 45.0 |
| Qwen: Qwen3 14B DeepInfra | qwen/qwen3-14b-04-28 | Alibaba | $0.120 | $0.240 | 41K | fp8 | 93.45% | 534ms | 28.0 |
| Mistral: Mistral Nemo DeepInfra | mistralai/mistral-nemo | — | $0.019 | $0.030 | 131K | fp8 | 93.32% | — | — |
| Google: Gemma 4 26B A4B DeepInfra | google/gemma-4-26b-a4b-it-20260403 | $0.070 | $0.340 | 262K | fp8 | 93.24% | 343ms | 30.0 | |
| Qwen: Qwen3.5 397B A17B DeepInfra | qwen/qwen3.5-397b-a17b-20260216 | Alibaba | $0.450 | $3.00 | 262K | fp8 | 93.20% | 639ms | 40.0 |
| DeepSeek: DeepSeek V4 Flash 0423 DeepInfra | deepseek/deepseek-v4-flash-20260423 | Deepseek | $0.090 | $0.180 | 1.0M | fp8 | 93.07% | 966ms | 23.0 |
| Qwen: Qwen3 VL 235B A22B Instruct DeepInfra | qwen/qwen3-vl-235b-a22b-instruct | Alibaba | $0.200 | $0.880 | 262K | fp8 | 92.33% | 990ms | 14.0 |
| Qwen: Qwen3 Coder 480B A35B DeepInfra | qwen/qwen3-coder-480b-a35b-07-25 | Alibaba | $0.300 | $1.00 | 262K | fp4 | 91.35% | 328ms | 25.0 |
- Qwen: Qwen3 32B· fp8$0.080 in$0.280 out41K ctx100.00% up
- StepFun: Step 3.7 FlashStepfun$0.200 in$1.15 out262K ctx99.44% up
- $0.075 in$0.200 out128K ctx98.83% up
- Qwen: Qwen3.5-35B-A3BAlibaba · fp8$0.140 in$1.00 out262K ctx98.44% up
- Qwen: Qwen3.5-122B-A10BAlibaba · fp4$0.290 in$2.40 out262K ctx98.10% up
- DeepSeek: DeepSeek V4 Flash 0731Deepseek · fp8$0.080 in$0.180 out1.0M ctx98.03% up
- Qwen: Qwen3 30B A3BAlibaba · fp8$0.120 in$0.500 out41K ctx97.80% up
- Xiaomi: MiMo-V2.5-ProXiaomi · fp8$1.00 in$3.00 out1.0M ctx97.45% up
- Qwen: Qwen3 VL 30B A3B InstructAlibaba · fp8$0.150 in$0.600 out262K ctx96.94% up
- Z.ai: GLM 4.7Z Ai · fp4$0.400 in$1.75 out203K ctx96.71% up
- Qwen: Qwen3.5-27BAlibaba · fp8$0.260 in$2.60 out262K ctx95.88% up
- Xiaomi: MiMo-V2.5Xiaomi · bf16$0.400 in$2.00 out262K ctx95.82% up
- Z.ai: GLM 5.2Z Ai · fp4$0.750 in$2.40 out1.0M ctx95.55% up
- Z.ai: GLM 4.6Z Ai · fp4$0.500 in$2.00 out203K ctx94.89% up
- Qwen: Qwen3 Next 80B A3B InstructAlibaba · fp8$0.090 in$1.10 out262K ctx94.59% up
- MiniMax: MiniMax M2.7Minimax · fp8$0.250 in$1.00 out197K ctx94.54% up
- Qwen: Qwen3 235B A22B Instruct 2507Alibaba · fp8$0.090 in$0.550 out262K ctx94.10% up
- Qwen: Qwen3.6 27BAlibaba · fp8$0.320 in$3.20 out262K ctx93.53% up
- Qwen: Qwen3 14BAlibaba · fp8$0.120 in$0.240 out41K ctx93.45% up
- Mistral: Mistral Nemo· fp8$0.019 in$0.030 out131K ctx93.32% up
- Google: Gemma 4 26B A4BGoogle · fp8$0.070 in$0.340 out262K ctx93.24% up
- Qwen: Qwen3.5 397B A17BAlibaba · fp8$0.450 in$3.00 out262K ctx93.20% up
- DeepSeek: DeepSeek V4 Flash 0423Deepseek · fp8$0.090 in$0.180 out1.0M ctx93.07% up
- Qwen: Qwen3 VL 235B A22B InstructAlibaba · fp8$0.200 in$0.880 out262K ctx92.33% up
- Qwen: Qwen3 Coder 480B A35BAlibaba · fp4$0.300 in$1.00 out262K ctx91.35% up
Page 1 of 2 · 30 offerings
