DeepInfra vs Together: 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

TTogether

2.19× typical advantage

12 exact models with complete recent speed data

Lowest token cost

DDeepInfra

$0.7437 / 1M

13 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	Together
ZA GLM 5.2Winner · Together z-ai/glm-5.2	DeepInfra Blended price $1.62 / 1M 500-token response 42.37 s Response starts 0.70 s Output speed 12.0 tok/s Route uptime N/a Context 1M Route deepinfra/fp4	Together Blended price $2.4 / 1M 500-token response 8.95 s Response starts 0.88 s Output speed 62.0 tok/s Route uptime 94.55% Context 262.1K Route together
M Kimi K2.7 CodeWinner · Together moonshotai/kimi-k2.7-code	DeepInfra Blended price $1.66 / 1M 500-token response 15.92 s Response starts 0.77 s Output speed 33.0 tok/s Route uptime 100.00% Context 262.1K Route deepinfra/fp4	Together Blended price $1.9667 / 1M 500-token response 3.47 s Response starts 0.49 s Output speed 168.0 tok/s Route uptime 99.29% Context 262.1K Route together
N Nemotron 3 UltraWinner · Together nvidia/nemotron-3-ultra-550b-a55b	DeepInfra Blended price $1.0667 / 1M 500-token response 40.05 s Response starts 4.33 s Output speed 14.0 tok/s Route uptime 95.48% Context 262.1K Route deepinfra/fp4	Together Blended price $1.6 / 1M 500-token response 9.29 s Response starts 0.81 s Output speed 59.0 tok/s Route uptime 99.13% Context 512.3K Route together
M MiniMax M3Winner · Together minimax/minimax-m3	DeepInfra Blended price $0.6 / 1M 500-token response 24.78 s Response starts 0.97 s Output speed 21.0 tok/s Route uptime 98.34% Context 524.3K Route deepinfra/bf16	Together Blended price $0.6 / 1M 500-token response 7.16 s Response starts 0.75 s Output speed 78.0 tok/s Route uptime 98.82% Context 524.3K Route together
D DeepSeek V4 ProWinner · DeepInfra deepseek/deepseek-v4-pro	DeepInfra Blended price $1.7333 / 1M 500-token response 18.19 s Response starts 0.94 s Output speed 29.0 tok/s Route uptime 98.79% Context 1M Route deepinfra/fp4	Together Blended price $2.32 / 1M 500-token response 16.18 s Response starts 0.56 s Output speed 32.0 tok/s Route uptime 93.72% Context 512K Route together
M Kimi K2.6Winner · Together moonshotai/kimi-k2.6	DeepInfra Blended price $1.6667 / 1M 500-token response 12.84 s Response starts 0.93 s Output speed 42.0 tok/s Route uptime 99.94% Context 262.1K Route deepinfra/fp4	Together Blended price $2.3 / 1M 500-token response 5.21 s Response starts 0.54 s Output speed 107.0 tok/s Route uptime 99.73% Context 262.1K Route together
G Gemma 4 31BWinner · DeepInfra google/gemma-4-31b-it	DeepInfra Blended price $0.2033 / 1M 500-token response 22.57 s Response starts 0.83 s Output speed 23.0 tok/s Route uptime 99.06% Context 262.1K Route deepinfra/turbo	Together Blended price $0.4733 / 1M 500-token response 24.13 s Response starts 2.39 s Output speed 23.0 tok/s Route uptime 83.73% Context 262.1K Route together
M MiniMax M2.7Winner · Together minimax/minimax-m2.7	DeepInfra Blended price $0.5 / 1M 500-token response 16.88 s Response starts 0.75 s Output speed 31.0 tok/s Route uptime 98.77% Context 196.6K Route deepinfra/fp8	Together Blended price $0.6 / 1M 500-token response 4.62 s Response starts 0.52 s Output speed 122.0 tok/s Route uptime 98.83% Context 196.6K Route together/fp4
Q Qwen3.5-9B qwen/qwen3.5-9b	DeepInfra Blended price $0.1167 / 1M 500-token response N/a Response starts N/a Output speed N/a Route uptime N/a Context 262.1K Route deepinfra/bf16	Together Blended price $0.1967 / 1M 500-token response 12.73 s Response starts 0.54 s Output speed 41.0 tok/s Route uptime 99.00% Context 262.1K Route together
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	Together Blended price $0.3 / 1M 500-token response 8.63 s Response starts 0.30 s Output speed 60.0 tok/s Route uptime 93.50% Context 131.1K Route together
O gpt-oss-20bWinner · Together openai/gpt-oss-20b	DeepInfra Blended price $0.0667 / 1M 500-token response 5.15 s Response starts 0.35 s Output speed 104.0 tok/s Route uptime 99.78% Context 131.1K Route deepinfra/bf16	Together Blended price $0.1 / 1M 500-token response 2.95 s Response starts 0.23 s Output speed 184.0 tok/s Route uptime N/a Context 131.1K Route together
ML Llama Guard 4 12BWinner · Together meta-llama/llama-guard-4-12b	DeepInfra Blended price $0.18 / 1M 500-token response 50.29 s Response starts 0.29 s Output speed 10.0 tok/s Route uptime 100.00% Context 163.8K Route deepinfra/bf16	Together Blended price $0.2 / 1M 500-token response 29.54 s Response starts 0.13 s Output speed 17.0 tok/s Route uptime 100.00% Context 1M Route together
ML Llama 3.3 70B InstructWinner · DeepInfra 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	Together Blended price $1.04 / 1M 500-token response 16.41 s Response starts 0.79 s Output speed 32.0 tok/s Route uptime 97.87% Context 131.1K Route together/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.