DeepInfra vs Nebius: LLM provider comparison

At a glance

Metric winners

There is no overall score. Each winner answers one specific question using only directly comparable data.

Fastest on shared models

NNebius

1.27× typical advantage

8 exact models with complete recent speed data

Lowest token cost

DDeepInfra

$0.3635 / 1M

8 exact models using a 1K-input/500-output mix

Most models available

DDeepInfra

87 models

Complete catalog coverage across all indexed modalities

Shared-model benchmark summary

Model	DeepInfra	Nebius
ZA GLM 5.1Winner · DeepInfra z-ai/glm-5.1	DeepInfra Blended price $1.8667 / 1M 500-token response 18.81 s Response starts 1.57 s Output speed 29.0 tok/s Route uptime 99.92% Context 202.8K Route deepinfra/fp4	Nebius Blended price $2.4 / 1M 500-token response 28.52 s Response starts 0.74 s Output speed 18.0 tok/s Route uptime 67.68% Context 202.8K Route nebius/fp8
N Nemotron 3 SuperWinner · Nebius nvidia/nemotron-3-super-120b-a12b	DeepInfra Blended price $0.19 / 1M 500-token response 41.88 s Response starts 6.16 s Output speed 14.0 tok/s Route uptime 90.39% Context 262.1K Route deepinfra/bf16	Nebius Blended price $0.5 / 1M 500-token response 7.85 s Response starts 1.67 s Output speed 81.0 tok/s Route uptime 99.41% Context 262.1K Route nebius/fp4
N Nemotron 3 Nano 30B A3BWinner · DeepInfra nvidia/nemotron-3-nano-30b-a3b	DeepInfra Blended price $0.1 / 1M 500-token response 8.83 s Response starts 1.25 s Output speed 66.0 tok/s Route uptime 99.22% Context 262.1K Route deepinfra/fp4	Nebius Blended price $0.12 / 1M 500-token response 12.83 s Response starts 0.33 s Output speed 40.0 tok/s Route uptime 96.57% Context 262.1K Route nebius/fp8
O gpt-oss-120bWinner · DeepInfra openai/gpt-oss-120b	DeepInfra Blended price $0.0813 / 1M 500-token response 12.10 s Response starts 0.47 s Output speed 43.0 tok/s Route uptime 94.64% Context 131.1K Route deepinfra/bf16	Nebius Blended price $0.3 / 1M 500-token response 6.62 s Response starts 0.67 s Output speed 84.0 tok/s Route uptime 97.33% Context 131.1K Route nebius/fp4
Q Qwen3 235B A22B Instruct 2507Winner · Nebius qwen/qwen3-235b-a22b-2507	DeepInfra Blended price $0.2433 / 1M 500-token response 26.72 s Response starts 0.40 s Output speed 19.0 tok/s Route uptime 98.78% Context 262.1K Route deepinfra/fp8	Nebius Blended price $0.3333 / 1M 500-token response 13.68 s Response starts 0.52 s Output speed 38.0 tok/s Route uptime 98.77% Context 262.1K Route nebius/fp8
Q Qwen3 32BWinner · DeepInfra qwen/qwen3-32b	DeepInfra Blended price $0.1467 / 1M 500-token response 15.38 s Response starts 0.23 s Output speed 33.0 tok/s Route uptime 99.99% Context 41K Route deepinfra/fp8	Nebius Blended price $0.1667 / 1M 500-token response 20.66 s Response starts 0.66 s Output speed 25.0 tok/s Route uptime 99.27% Context 41K Route nebius/base
G Gemma 3 27BWinner · DeepInfra google/gemma-3-27b-it	DeepInfra Blended price $0.1067 / 1M 500-token response 30.09 s Response starts 0.68 s Output speed 17.0 tok/s Route uptime 99.95% Context 131.1K Route deepinfra/fp8	Nebius Blended price $0.1667 / 1M 500-token response 28.44 s Response starts 0.66 s Output speed 18.0 tok/s Route uptime 93.99% Context 110K Route nebius/fp8
ML Llama 3.3 70B InstructWinner · Nebius meta-llama/llama-3.3-70b-instruct	DeepInfra Blended price $0.1733 / 1M 500-token response 31.59 s Response starts 0.34 s Output speed 16.0 tok/s Route uptime 98.39% Context 131.1K Route deepinfra/turbo	Nebius Blended price $0.22 / 1M 500-token response 21.28 s Response starts 0.45 s Output speed 24.0 tok/s Route uptime 97.93% Context 131.1K Route nebius/fp8

A per-model winner combines blended price and estimated 500-token response time with equal proportional weight. Ties and rows missing either measurement receive no badge. Comparison data calculated Jul 16, 2026, 8:19 AM UTC. Values use one deterministic route per provider and model; missing measurements remain visible as N/a.