DeepInfra
87 indexed models
- Headquarters
United States
- Server regions
- N/a
- Model types
- 67 text, 15 embeddings, 5 speech
Start typing to search.
Same-model provider benchmark
Compare DeepInfra and DigitalOcean on 15 exact shared text models. ProviderBench keeps speed, price, and catalog coverage separate so naturally faster model catalogs cannot distort the result.
87 indexed models
16 indexed models
At a glance
There is no overall score. Each winner answers one specific question using only directly comparable data.
| Metric | DeepInfra | DigitalOcean |
|---|---|---|
| Typical 500-token response | 16.56 s | 32.65 s |
| Typical response start | 0.93 s | 1.13 s |
| Typical output speed | 32.0 tok/s | 16.0 tok/s |
| Blended token price | $0.967 / 1M | $0.989 / 1M |
| Typical route uptime | 99.20% | 98.97% |
Visual comparison
Estimated seconds using recent median response-start and output-speed data. Lower is better.
DeepInfra has the lower typical same-model response ratio across 15 measured models.
USD per 1 million tokens using a 1,000-input/500-output mix. Lower is better.
DeepInfra has the lower typical price ratio across 15 priced shared models.
| Model | DeepInfra | DigitalOcean |
|---|---|---|
GLM 5.2Winner · DigitalOcean z-ai/glm-5.2 | DeepInfra
| DigitalOcean
|
DeepSeek V4 ProWinner · DeepInfra deepseek/deepseek-v4-pro | DeepInfra
| DigitalOcean
|
DeepSeek V4 FlashWinner · DeepInfra deepseek/deepseek-v4-flash | DeepInfra
| DigitalOcean
|
MiMo-V2.5-ProWinner · DigitalOcean xiaomi/mimo-v2.5-pro | DeepInfra
| DigitalOcean
|
MiMo-V2.5Winner · DigitalOcean xiaomi/mimo-v2.5 | DeepInfra
| DigitalOcean
|
Kimi K2.6Winner · DigitalOcean moonshotai/kimi-k2.6 | DeepInfra
| DigitalOcean
|
GLM 5.1Winner · DeepInfra z-ai/glm-5.1 | DeepInfra
| DigitalOcean
|
Nemotron 3 SuperWinner · DeepInfra nvidia/nemotron-3-super-120b-a12b | DeepInfra
| DigitalOcean
|
Qwen3.5 397B A17BWinner · DeepInfra qwen/qwen3.5-397b-a17b | DeepInfra
| DigitalOcean
|
MiniMax M2.5Winner · DigitalOcean minimax/minimax-m2.5 | DeepInfra
| DigitalOcean
|
GLM 5Winner · DeepInfra z-ai/glm-5 | DeepInfra
| DigitalOcean
|
Kimi K2.5Winner · DeepInfra moonshotai/kimi-k2.5 | DeepInfra
| DigitalOcean
|
DeepSeek V3.2Winner · DeepInfra deepseek/deepseek-v3.2 | DeepInfra
| DigitalOcean
|
gpt-oss-120bWinner · DeepInfra openai/gpt-oss-120b | DeepInfra
| DigitalOcean
|
Llama 4 MaverickWinner · DeepInfra meta-llama/llama-4-maverick | DeepInfra
| DigitalOcean
|
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 . Values use one deterministic route per provider and model; missing measurements remain visible as N/a.
DeepInfra vs DigitalOcean analysis
DeepInfra and DigitalOcean share 15 indexed text models, including GLM 5.2, DeepSeek V4 Pro, DeepSeek V4 Flash, MiMo-V2.5-Pro, MiMo-V2.5. DeepInfra has the stronger typical response-time result on the directly measured set.
15 shared models currently have complete response-start and output-speed measurements on both providers. The speed comparison uses per-model ratios before taking the median, so naturally faster model catalogs do not improve the result.
15 shared models have complete input and output prices on both providers. Prices use the same 1,000-input/500-output-token mix and are normalized to one million tokens for readability.
DeepInfra has 87 indexed models and lists no published server regions; DigitalOcean has 16 models and lists no regions. Verify data residency, privacy terms, limits, and production latency directly before choosing.
Related same-model benchmarks
Explore qualified alternatives with the most shared measured models. Recommendations include comparisons for both DeepInfra and DigitalOcean.