Providers /DeepInfra
Models
101
Data residency
No answer on record
00
Editorial by LLMap · updated Aug 4, 2026Our take
DeepInfra is a hosted inference provider that usually undercuts the competition on price for downloadable models. It carries one of the widest catalogues of downloadable-model offers we track and is often the cheapest row in a price table.
Use this for cost-sensitive production on downloadable models. Check its price first. Pick it for long-tail model access: 61 offers covers models few others host. Skip it if your workload requires independently verified SOC 2 or a guaranteed EU data-residency endpoint.
Strengths
- Price floor for many catalogue models.
- Deepest downloadable-model catalogue — 61 tracked offers.
Trade-offs
- Compliance posture is less documented: SOC 2 and EU endpoint are both unverified in our data.
01
Point your tools here
API base URL
https://api.deepinfra.com/v1/openaiModel IDs on this page are LLMap's own slugs, built for browsing and comparing — not what DeepInfra's API expects. Its own model identifier lives in the docs above.
02
Privacy & data handling
These answers cover requests sent to DeepInfra through OpenRouter, as OpenRouter records them, last read 4 hours ago. For DeepInfra's own API we hold no answer: check its terms. SOC 2 and the data processing agreement below are hand-checked, not part of that sync.
Trains on prompts
✗No
Logs prompts
✗No
✓Offered
No answer on record
No answer on record
Prompt retention: none.
03
Models & pricing
Claude Fable 5Direct—$10.00 / $50.00 /1M1M4 hours agoClaude Haiku 4.5Direct—$1.00 / $5.00 /1M200K4 hours agoClaude Opus 4.7Direct—$5.00 / $25.00 /1M1M4 hours agoClaude Opus 4.8Direct—$5.00 / $25.00 /1M1M4 hours agoClaude Opus 5Direct—$5.00 / $25.00 /1M1M4 hours agoClaude Opus 5.5Direct—$4.00 / $20.00 /1M1M4 hours agoClaude Sonnet 4.6Direct—$3.00 / $15.00 /1M1M4 hours agoClaude Sonnet 5Direct—$3.00 / $15.00 /1M1M4 hours agoClaude Sonnet 5.5Direct—$2.00 / $10.00 /1M1M4 hours agoDeepSeek V3fp4Direct and through OpenRouter685B$0.32 / $0.89 /1M164K4 hours agoDeepSeek V3 0324fp4Direct685B$0.24 / $0.90 /1M164K9 days agoDeepSeek V3.1fp4Direct and through OpenRouter685B$0.25 / $0.95 /1M164K4 hours agoDeepSeek V3.2fp4Direct and through OpenRouter685B$0.26 / $0.38 /1M164K4 hours agoDeepSeek V4.1 Flashfp8Direct and through OpenRouter763B$0.20 / $0.60 /1Mdirect$0.14 / $0.42 /1Mthrough OpenRouter1M4 hours agoDeepSeek V4 Flashfp8Direct and through OpenRouter291B$0.060 / $0.18 /1M1M4 hours agoDeepSeek V4 Flash Vision Expfp8Direct and through OpenRouter305B$0.44 / $1.32 /1Mdirect$0.22 / $0.65 /1Mthrough OpenRouter1M4 hours agoDeepSeek V4 Profp8Direct and through OpenRouter1.6T$1.30 / $2.60 /1M1M4 hours agoGemini 2.5 FlashDirect—$0.30 / $2.50 /1M1M4 hours agoGemini 2.5 ProDirect—$1.25 / $10.00 /1M1M4 hours agoGemini 3.1 Flash LiteDirect—$0.25 / $1.50 /1M1M4 hours agoGemini 3.5 FlashDirect—$1.50 / $9.00 /1M1M4 hours agoGemini 3.7 FlashDirect—$0.75 / $3.75 /1M1M4 hours agoGemma 3 12Bbf16Direct and through OpenRouter12.2B$0.050 / $0.15 /1M131K4 hours agoGemma 3 27Bfp8Direct and through OpenRouter27.4B$0.080 / $0.16 /1M131K4 hours agoGemma 3 4Bbf16Direct and through OpenRouter4.3B$0.050 / $0.10 /1M131K4 hours agoGemma 4 26B A4Bfp8Direct and through OpenRouter25.8B$0.070 / $0.34 /1M262K4 hours agoGemma 4 31Bturbo tier · fp4Through OpenRouter31.3B$0.090 / $0.34 /1M262K4 hours agoGemma 4 31Bfp8Direct and through OpenRouter31.3B$0.15 / $0.40 /1M262K4 hours agoGemma 4 E4B itbf16Direct8B$0.020 / $0.10 /1M131K7 days agoGLM 4.6fp4Direct and through OpenRouter357B$0.50 / $2.00 /1M203K4 hours agoGLM 4.7fp4Direct and through OpenRouter358B$0.40 / $1.75 /1M203K4 hours ago direct16 hours ago through OpenRouterGLM 4.7 Flashbf16Direct31.2B$0.060 / $0.40 /1M203K28 days agoGLM 5fp4Direct754B$0.60 / $2.08 /1M203K28 days agoGLM 5.1fp4Direct754B$1.05 / $3.50 /1M203K7 days agoGLM 5.2fp4Direct and through OpenRouter753B$0.75 / $2.40 /1Mdirect$0.56 / $1.80 /1Mthrough OpenRouter1M4 hours agoGLM 5.3fp4Direct and through OpenRouter—$0.90 / $4.00 /1Mdirect$0.56 / $2.50 /1Mthrough OpenRouter1M4 hours agoGLM 5.3 Flashfp4Direct and through OpenRouter321B$0.15 / $0.50 /1Mdirect$0.075 / $0.25 /1Mthrough OpenRouter1M4 hours agogpt-oss-120bbf16Direct and through OpenRouter120B$0.037 / $0.17 /1M131K4 hours agogpt-oss-120bturbo tier · bf16Through OpenRouter120B$0.15 / $0.60 /1M131K4 hours agogpt-oss-safeguard-20bbf16Direct and through OpenRouter21.5B$0.030 / $0.14 /1M131K4 hours agoGranite 4.2 8Bbf16Direct and through OpenRouter8.8B$0.060 / $0.25 /1M131K4 hours agoHermes 3 405B Instructfp8Direct and through OpenRouter406B$1.00 / $1.00 /1M131K4 hours agoHermes 3 70B Instructfp8Direct and through OpenRouter70.6B$0.70 / $0.70 /1M131K4 hours agoHy3fp4Direct and through OpenRouter299B$0.13 / $0.53 /1M262K4 hours agoHy4 previewfp8Direct and through OpenRouter780B$0.83 / $2.50 /1M1M4 hours agoInklingfp8Direct and through OpenRouter952B$0.95 / $4.05 /1M524K4 hours agoInkling Smallfp8Direct and through OpenRouter266B$0.45 / $1.20 /1M524K4 hours agoKimi K2.5fp4Direct1.1T$0.45 / $2.25 /1M262K31 days agoKimi K2.6fp4Direct and through OpenRouter1.1T$0.75 / $3.50 /1M262K4 hours agoKimi K2.7 Codefp4Direct1.1T$0.68 / $3.40 /1M262K9 days agoKimi K3bf16Direct and through OpenRouter2.8T$2.85 / $14.25 /1M1M4 hours agoLing-3.0-flashfp4Direct and through OpenRouter128B$0.060 / $0.18 /1M262K4 hours agoLing-3.0-flashfp16Direct and through OpenRouter128B$0.060 / $0.18 /1M131K4 hours agoLing-3.0-flashbf16Through OpenRouter128B$0.060 / $0.18 /1M131K4 hours agoLing-3.0-flashDirect128B$0.060 / $0.18 /1M131K4 hours agoLlama 3.1 70B Instructturbo tier · fp8Through OpenRouter70.6B$0.40 / $0.40 /1M131K10 hours agoLlama 3.1 8B Instructfp8Through OpenRouter8B$0.020 / $0.040 /1M131K4 hours agoLlama 3.1 Euryale 70B v2.2fp8Direct and through OpenRouter70.6B$0.85 / $0.85 /1M131K4 hours agoLlama 3.3 70B Instructturbo tier · fp8Through OpenRouter70.6B$0.10 / $0.32 /1M131K4 hours agoLlama 3 8B Lunaristurbo tier · fp8Through OpenRouter8B$0.040 / $0.050 /1M8K4 hours agoLlama 4 Scoutfp8Direct and through OpenRouter109B$0.10 / $0.30 /1M328K4 hours agoLlama Guard 4 12Bbf16Direct and through OpenRouter12B$0.18 / $0.18 /1M164K4 hours agoMiMo-V2.5fp8Direct311B$0.14 / $0.28 /1M262K9 days agoMiMo-V2.5Direct311B$0.40 / $2.00 /1M262K36 days agoMiMo-V2.5-Profp8Direct1T$1.00 / $3.00 /1M1M9 days agoMiMo-V2.6-Flashfp8Direct and through OpenRouter—$0.14 / $0.28 /1M1M4 hours agoMiniMax M2.7fp8Direct229B$0.25 / $1.00 /1M197K28 days agoMiniMax M3fp8Direct and through OpenRouter427B$0.28 / $1.10 /1M524K4 hours agoMistral Nemofp8Direct and through OpenRouter12.2B$0.019 / $0.030 /1M131K4 hours agoMistral Small 3fp8Direct and through OpenRouter23.6B$0.050 / $0.080 /1M33K4 hours agoMistral Small 3.2 24Bfp8Direct and through OpenRouter24B$0.075 / $0.20 /1M128K4 hours agoMuse Glimmer 30Bbf16Direct and through OpenRouter29.8B$0.30 / $1.20 /1M131K4 hours agoMythoMax 13Bfp16Direct and through OpenRouter13B$0.40 / $0.40 /1M4K4 hours agoNemotron 3.5 Content Safetybf16Direct and through OpenRouter4.3B$0.20 / $0.20 /1M131K4 hours agoNemotron 3.5 Lightningbf16Direct and through OpenRouter31.6B$0.060 / $0.16 /1M262K4 hours agoNemotron 3 Nano 30B A3Bfp4Direct and through OpenRouter31.6B$0.050 / $0.20 /1M262K4 hours agoNemotron 3 Superbf16Direct and through OpenRouter124B$0.085 / $0.40 /1M262K4 hours agoNemotron 3 Ultrafp4Direct and through OpenRouter561B$0.50 / $2.20 /1M262K4 hours agoPhi 4bf16Direct and through OpenRouter14.7B$0.070 / $0.14 /1M16K4 hours agoQwen2.5 72B Instructfp8Direct and through OpenRouter72.7B$0.36 / $0.40 /1M33K4 hours agoQwen3 14Bfp8Direct and through OpenRouter14.8B$0.12 / $0.24 /1M41K4 hours agoQwen3 235B A22B Instruct 2507fp8Direct and through OpenRouter235B$0.090 / $0.55 /1M262K4 hours agoQwen3 235B A22B Thinking 2507fp8Direct235B$0.23 / $2.30 /1M262K46 days agoQwen3 30B A3B Instruct 2507fp8Direct and through OpenRouter30.5B$0.12 / $0.50 /1M41K4 hours agoQwen3 32Bfp8Direct and through OpenRouter32.8B$0.080 / $0.28 /1M41K4 hours agoQwen3.5-122B-A10Bfp4Direct125B$0.29 / $2.40 /1M262K7 days agoQwen3.5-27Bfp8Direct and through OpenRouter27.8B$0.26 / $2.60 /1M262K4 hours agoQwen3.5-35B-A3Bfp8Direct and through OpenRouter36B$0.14 / $1.00 /1M262K4 hours agoQwen3.5 397B A17Bfp8Direct and through OpenRouter403B$0.45 / $3.00 /1M262K4 hours agoQwen3.5-9Bbf16Direct and through OpenRouter9.7B$0.10 / $0.15 /1M262K4 hours agoQwen3.6 27Bfp8Direct and through OpenRouter27.8B$0.32 / $3.20 /1M262K4 hours agoQwen3.6 35B A3Bfp8Direct and through OpenRouter36B$0.10 / $0.95 /1M262K4 hours ago direct10 hours ago through OpenRouterQwen3.7 MaxDirect—$2.50 / $7.50 /1M256K4 hours agoQwen3.8 2.4T A95Bfp4Direct and through OpenRouter2.4T$2.00 / $6.00 /1M262K4 hours agoQwen3.8 27Bbf16Direct and through OpenRouter27.8B$0.20 / $2.50 /1Mdirect$0.15 / $1.88 /1Mthrough OpenRouter262K4 hours agoQwen3.8 FlashDirect—$0.11 / $0.38 /1M1M4 hours agoQwen3.8 MaxDirect—$1.65 / $4.95 /1M256K4 hours agoQwen3 Coder 480B A35Bturbo tier · fp4Through OpenRouter480B$0.30 / $1.00 /1M262K4 hours agoQwen3 MaxDirect—$1.20 / $6.00 /1M256K4 hours agoQwen3 Max ThinkingDirect—$1.20 / $6.00 /1M256K4 hours agoQwen3 Next 80B A3B Instructfp8Direct and through OpenRouter81.3B$0.090 / $1.10 /1M262K4 hours agoQwen3 VL 235B A22B Instructfp8Direct and through OpenRouter236B$0.20 / $0.88 /1M262K4 hours agoQwen3 VL 30B A3B Instructfp8Direct and through OpenRouter31.1B$0.15 / $0.60 /1M262K4 hours agoR1 0528fp4Direct and through OpenRouter685B$0.50 / $2.15 /1M164K4 hours agoSeed-2.0-CodeDirect—$0.50 / $3.00 /1M256K4 hours agoSeed-2.0-MiniDirect—$0.10 / $0.40 /1M256K4 hours agoStep 3.7 FlashmodeloptDirect201B$0.20 / $1.15 /1M262K7 days ago