↑↓ move↵ openesc close

Overage / Compare / LLM APIs

DeepInfra vs Hugging Face Inference pricing

Verified 2026-10-24 (1 day ago)Source: DeepInfra: deepinfra.com/pricing, Hugging Face Inference: huggingface.co/pricingVerified shows the older of the two.

Monthly cost at three volumes

These services do not bill on a shared metric, so a like-for-like cost is unlisted.

Cheapest model per service, USD per 1M tokens

Cheapest priced model of each service
ServiceCheapest modelInputOutputModels listed
DeepInfraMeta-Llama-3.1-8B-Instruct-Turbo$0.02$0.0460
Hugging Face Inferenceplan pricingunlistedunlistedn/a

Every model

Every model of both services, USD per 1M tokens
ModelServiceInputOutput
Meta-Llama-3.1-8B-Instruct-TurboDeepInfra$0.02$0.04
Mistral-Nemo-Instruct-2407DeepInfra$0.029$0.03
gemma-3-12b-itDeepInfra$0.05$0.15
gemma-3-4b-itDeepInfra$0.05$0.10
Mistral-Small-24B-Instruct-2501DeepInfra$0.05$0.08
DeepSeek-V4-Flash-0731DeepInfra$0.06$0.18
NVIDIA-Nemotron-3.5-LightningDeepInfra$0.06$0.16
gemma-4-26B-A4B-itDeepInfra$0.07$0.34
phi-4DeepInfra$0.07$0.14
Mistral-Small-3.2-24B-Instruct-2506DeepInfra$0.075$0.20
Qwen3-32BDeepInfra$0.08$0.28
gemma-3-27b-itDeepInfra$0.08$0.16
NVIDIA-Nemotron-3-Super-120B-A12BDeepInfra$0.085$0.40
DeepSeek-V4-FlashDeepInfra$0.09$0.18
Qwen3-Next-80B-A3B-InstructDeepInfra$0.09$1.10
Qwen3-235B-A22B-Instruct-2507DeepInfra$0.09$0.55
gemma-4-31B-it-turboDeepInfra$0.09$0.34
Qwen3.6-35B-A3BDeepInfra$0.10$0.95
Qwen3.5-9BDeepInfra$0.10$0.15
Llama-4-Scout-17B-16EDeepInfra$0.10$0.30
Llama-3.3-70B-Instruct-TurboDeepInfra$0.10$0.32
Qwen3-30B-A3BDeepInfra$0.12$0.50
Qwen3-14BDeepInfra$0.12$0.24
Qwen3.5-35B-A3BDeepInfra$0.14$1
Qwen3-VL-30B-A3B-InstructDeepInfra$0.15$0.60
NVIDIA-Nemotron-3.5-Super-VLDeepInfra$0.15$0.50
Llama-Guard-4-12BDeepInfra$0.18$0.18
Qwen3-VL-235B-A22B-InstructDeepInfra$0.20$0.88
gemma-4-31B-itDeepInfra$0.20$0.40
Nemotron-Content-Safety-3.5DeepInfra$0.20$0.20
deepseek-ai/DeepSeek-V4-Flash-Vision-ExpDeepInfra$0.2156$0.6468
DeepSeek-V3.1DeepInfra$0.25$0.95
gemini-3.1-flash-liteDeepInfra$0.25$1.50
DeepSeek-V3.2DeepInfra$0.26$0.38
Qwen3.5-27BDeepInfra$0.26$2.60
gemma-4-31B-it-UltraDeepInfra$0.27$0.76
Qwen3-Coder-480B-A35B-Instruct-TurboDeepInfra$0.30$1
gemini-2.5-flashDeepInfra$0.30$2.50
DeepSeek-V3DeepInfra$0.32$0.89
Qwen3.6-27BDeepInfra$0.32$3.20
Qwen2.5-72B-InstructDeepInfra$0.36$0.40
Meta-Llama-3.1-70B-Instruct-TurboDeepInfra$0.40$0.40
Qwen3.5-397B-A17BDeepInfra$0.45$3
DeepSeek-R1-0528DeepInfra$0.50$2.15
NVIDIA-Nemotron-3-Ultra-550B-A55BDeepInfra$0.50$2.20
Kimi-K2.6DeepInfra$0.75$3.50
claude-haiku-4-5DeepInfra$1$5
gemini-2.5-proDeepInfra$1.25$10
DeepSeek-V4-ProDeepInfra$1.30$2.60
gemini-3.5-flashDeepInfra$1.50$9
Qwen3.8-MaxDeepInfra$1.65$4.951
gemini-3.1-proDeepInfra$2$12
Qwen3.7-MaxDeepInfra$2.50$7.50
Kimi-K3DeepInfra$2.85$14.25
claude-sonnet-5DeepInfra$3$15
claude-sonnet-4-6DeepInfra$3$15
claude-opus-5DeepInfra$5$25
claude-opus-4-7DeepInfra$5$25
claude-opus-4-8DeepInfra$5$25
claude-fable-5DeepInfra$10$50

Models are compared by name and price, never by position. Pick one model per service, or "Cheapest model", in the cost table above.

Tiers, aligned by position

Tiers of DeepInfra and Hugging Face Inference aligned by position: free, entry, mid, top
PositionDeepInfraHugging Face Inference
Freeno tierno tier
Entryno tier$9 / moPRO Account
Midno tier$20 / moTeam
Topno tier$50 / moEnterprise

Tightest rate limit

Tightest documented rate limit of each service
MeasureDeepInfraHugging Face Inference
Tightest limitunlistedunlisted

Changes in the last 90 days

No changes recorded.

No change detected for either service in the last 90 days.