Providers /DeepInfra
Models
150
Regions
—
00
Editorial by LLMap · updated Aug 2, 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
Privacy & data handling
- ✓
- Yes
- ✗
- No
- No answer on record
The colour says whether the answer favours you, not whether it is a yes — not training on your prompts earns a green cross, no zero-retention option earns a red one.
Trains on your prompts
✗No
Logs prompts
✗No
✓Offered
No answer on record
Prompt retention: none.
02
Models & pricing
Claude Fable 5—$10.00 / $50.00 /1M1M5h agoClaude Haiku 4.5—$1.00 / $5.00 /1M200K5h agoClaude Opus 4.7—$5.00 / $25.00 /1M1M5h agoClaude Opus 4.8—$5.00 / $25.00 /1M1M5h agoClaude Opus 5—$5.00 / $25.00 /1M1M5h agoClaude Sonnet 4.6—$3.00 / $15.00 /1M1M5h agoClaude Sonnet 5—$2.00 / $10.00 /1M1M5h agoDeepSeek V3685B$0.32 / $0.89 /1M164K5h agoDeepSeek V3685B$0.32 / $0.89 /1M164K5h agoDeepSeek V3 0324685B$0.24 / $0.90 /1M164K5h agoDeepSeek V3 0324685B$0.24 / $0.90 /1M164K7h agoDeepSeek V3.1 Terminus685B$0.25 / $0.95 /1M164K5h agoDeepSeek V3.1 Terminus685B$0.25 / $0.95 /1M164K5h agoDeepSeek V3.2685B$0.26 / $0.38 /1M164K5h agoDeepSeek V3.2685B$0.26 / $0.38 /1M164K5h agoDeepSeek V4 Flash291B$0.090 / $0.18 /1M1M5h agoDeepSeek V4 Flash291B$0.090 / $0.18 /1M1M5h agoDeepSeek V4 Pro1.6T$1.30 / $2.60 /1M1M5h agoDeepSeek V4 Pro1.6T$1.30 / $2.60 /1M1M5h agoGemini 2.5 Flash—$0.30 / $2.50 /1M1M5h agoGemini 2.5 Pro—$1.25 / $10.00 /1M1M5h agoGemini 3.1 Flash Lite—$0.25 / $1.50 /1M1M5h agoGemini 3.5 Flash—$1.50 / $9.00 /1M1M5h agoGemma 3 12B12.2B$0.050 / $0.15 /1M131K5h agoGemma 3 12B12.2B$0.050 / $0.15 /1M131K5h agoGemma 3 27B27.4B$0.080 / $0.16 /1M131K5h agoGemma 3 27B27.4B$0.080 / $0.16 /1M131K5h agoGemma 3 4B4.3B$0.050 / $0.10 /1M131K5h agoGemma 3 4B4.3B$0.050 / $0.10 /1M131K5h agoGemma 4 26B A4B26.5B$0.070 / $0.34 /1M262K5h agoGemma 4 26B A4B26.5B$0.070 / $0.34 /1M262K5h agoGemma 4 31B32.7B$0.13 / $0.38 /1M262K7h agoGemma 4 31B32.7B$0.090 / $0.34 /1M262K5h agoGemma 4 31B32.7B$0.090 / $0.34 /1M262K6d agoGemma 4 31B32.7B$0.13 / $0.38 /1M262K5h agoGLM 4.6357B$0.50 / $2.00 /1M203K5h agoGLM 4.6357B$0.50 / $2.00 /1M203K5h agoGLM 4.7358B$0.40 / $1.75 /1M203K5h agoGLM 4.7358B$0.40 / $1.75 /1M203K5h agoGLM 4.7 Flash31.2B$0.060 / $0.40 /1M203K5h agoGLM 4.7 Flash31.2B$0.060 / $0.40 /1M203K5h agoGLM 5754B$0.60 / $2.08 /1M203K5h agoGLM 5754B$0.60 / $2.08 /1M203K5h agoGLM 5.1754B$1.05 / $3.50 /1M203K5h agoGLM 5.1754B$1.05 / $3.50 /1M203K5h agoGLM 5.2753B$0.75 / $2.40 /1M1M5h agoGLM 5.2753B$0.75 / $2.40 /1M1M5h agogpt-oss-120b120B$0.037 / $0.17 /1M131K5h agogpt-oss-120b120B$0.037 / $0.17 /1M131K5h agogpt-oss-120b120B$0.15 / $0.60 /1M131K5h agogpt-oss-safeguard-20b21.5B$0.030 / $0.14 /1M131K5h agogpt-oss-safeguard-20b21.5B$0.030 / $0.14 /1M131K5h agoHermes 3 405B Instruct406B$1.00 / $1.00 /1M131K5h agoHermes 3 405B Instruct406B$1.00 / $1.00 /1M131K5h agoHermes 3 70B Instruct70.6B$0.70 / $0.70 /1M131K5h agoHermes 3 70B Instruct70.6B$0.70 / $0.70 /1M131K5h agoHy3299B$0.14 / $0.58 /1M262K5h agoHy3299B$0.14 / $0.58 /1M262K5h agoInkling952B$0.95 / $4.05 /1M524K5h agoInkling952B$0.95 / $4.05 /1M524K5h agoInkling Small266B$0.45 / $1.20 /1M524K5h agoInkling Small266B$0.45 / $1.20 /1M524K5h agoKimi K2.51.1T$0.45 / $2.25 /1M262K5h agoKimi K2.51.1T$0.45 / $2.25 /1M262K5h agoKimi K2.61.1T$0.75 / $3.50 /1M262K5h agoKimi K2.61.1T$0.75 / $3.50 /1M262K5h agoKimi K2.7 Code1.1T$0.74 / $3.50 /1M262K5h agoKimi K2.7 Code1.1T$0.74 / $3.50 /1M262K5h agoLlama 3.1 70B Instruct70.6B$0.40 / $0.40 /1M131K5h agoLlama 3.1 70B Instruct70.6B$0.40 / $0.40 /1M131K6d agoLlama 3.1 8B Instruct8B$0.020 / $0.040 /1M131K5h agoLlama 3.1 Euryale 70B v2.270.6B$0.85 / $0.85 /1M131K5h agoLlama 3.1 Euryale 70B v2.270.6B$0.85 / $0.85 /1M131K5h agoLlama 3.3 70B Instruct70.6B$0.10 / $0.32 /1M131K5h agoLlama 3.3 70B Instruct70.6B$0.10 / $0.32 /1M131K6d agoLlama 3 8B Lunaris8B$0.040 / $0.050 /1M8K5h agoLlama 3 8B Lunaris8B$0.040 / $0.050 /1M8K6d agoLlama 4 Maverick402B$0.20 / $0.80 /1M1M6d agoLlama 4 Maverick402B$0.20 / $0.80 /1M1M5h agoLlama 4 Scout109B$0.10 / $0.30 /1M328K5h agoLlama 4 Scout109B$0.10 / $0.30 /1M328K5h agoLlama Guard 4 12B12B$0.18 / $0.18 /1M164K5h agoLlama Guard 4 12B12B$0.18 / $0.18 /1M164K5h agoMiMo-V2.5311B$0.40 / $2.00 /1M262K5h agoMiMo-V2.5311B$0.40 / $2.00 /1M262K5h agoMiMo-V2.5-Pro1T$1.00 / $3.00 /1M1M13h agoMiMo-V2.5-Pro1T$1.00 / $3.00 /1M1M5h agoMiniMax M2.7229B$0.38 / $1.70 /1M197K5h agoMiniMax M2.7229B$0.25 / $1.00 /1M197K5h agoMiniMax M2.7229B$0.25 / $1.00 /1M197K5h agoMiniMax M3427B$0.30 / $1.20 /1M524K5h agoMiniMax M3427B$0.30 / $1.20 /1M524K5h agoMistral Nemo12.2B$0.019 / $0.030 /1M131K5h agoMistral Nemo12.2B$0.019 / $0.030 /1M131K7h agoMistral Small 323.6B$0.050 / $0.080 /1M33K5h agoMistral Small 323.6B$0.050 / $0.080 /1M33K5h agoMistral Small 3.2 24B24B$0.075 / $0.20 /1M128K5h agoMistral Small 3.2 24B24B$0.075 / $0.20 /1M128K5h agoMythoMax 13B13B$0.40 / $0.40 /1M4K5h agoMythoMax 13B13B$0.40 / $0.40 /1M4K5h agoNemotron 3 Nano 30B A3B31.6B$0.050 / $0.20 /1M262K13h agoNemotron 3 Nano 30B A3B31.6B$0.050 / $0.20 /1M262K5h agoNemotron 3 Super124B$0.085 / $0.40 /1M262K3d agoNemotron 3 Super124B$0.085 / $0.40 /1M262K5h agoNemotron 3 Ultra561B$0.50 / $2.20 /1M262K19h agoNemotron 3 Ultra561B$0.50 / $2.20 /1M262K5h agoPhi 414.7B$0.070 / $0.14 /1M16K5h agoPhi 414.7B$0.070 / $0.14 /1M16K5h agoQwen2.5 72B Instruct72.7B$0.36 / $0.40 /1M33K5h agoQwen2.5 72B Instruct72.7B$0.36 / $0.40 /1M33K5h agoQwen3 14B14.8B$0.12 / $0.24 /1M41K5h agoQwen3 14B14.8B$0.12 / $0.24 /1M41K5h agoQwen3 235B A22B Instruct 2507235B$0.090 / $0.55 /1M262K7h agoQwen3 235B A22B Instruct 2507235B$0.090 / $0.55 /1M262K5h agoQwen3 235B A22B Thinking 2507235B$0.23 / $2.30 /1M262K5h agoQwen3 235B A22B Thinking 2507235B$0.23 / $2.30 /1M262K5h agoQwen3 30B A3B Instruct 250730.5B$0.12 / $0.50 /1M41K5h agoQwen3 30B A3B Instruct 250730.5B$0.12 / $0.50 /1M41K5h agoQwen3 32B32.8B$0.080 / $0.28 /1M41K5h agoQwen3 32B32.8B$0.080 / $0.28 /1M41K5h agoQwen3.5-122B-A10B125B$0.29 / $2.40 /1M262K5h agoQwen3.5-122B-A10B125B$0.29 / $2.40 /1M262K5h agoQwen3.5-27B27.8B$0.26 / $2.60 /1M262K5h agoQwen3.5-27B27.8B$0.26 / $2.60 /1M262K5h agoQwen3.5-35B-A3B36B$0.14 / $1.00 /1M262K5h agoQwen3.5-35B-A3B36B$0.14 / $1.00 /1M262K7h agoQwen3.5 397B A17B403B$0.45 / $3.00 /1M262K5h agoQwen3.5 397B A17B403B$0.45 / $3.00 /1M262K7h agoQwen3.5-9B9.7B$0.10 / $0.15 /1M262K5h agoQwen3.5-9B9.7B$0.10 / $0.15 /1M262K5h agoQwen3.6 27B27.8B$0.32 / $3.20 /1M262K5h agoQwen3.6 27B27.8B$0.32 / $3.20 /1M262K5h agoQwen3.6 35B A3B36B$0.10 / $0.95 /1M262K5h agoQwen3.6 35B A3B36B$0.10 / $0.95 /1M262K5h agoQwen3.7 Max—$2.50 / $7.50 /1M256K5h agoQwen3 Coder 480B A35B480B$0.30 / $1.00 /1M262K6d agoQwen3 Coder 480B A35B480B$0.30 / $1.00 /1M262K5h agoQwen3 Max—$1.20 / $6.00 /1M256K5h agoQwen3 Max Thinking—$1.20 / $6.00 /1M256K5h agoQwen3 Next 80B A3B Instruct81.3B$0.090 / $1.10 /1M262K5h agoQwen3 Next 80B A3B Instruct81.3B$0.090 / $1.10 /1M262K5h agoQwen3 VL 235B A22B Instruct236B$0.20 / $0.88 /1M262K13h agoQwen3 VL 235B A22B Instruct236B$0.20 / $0.88 /1M262K5h agoQwen3 VL 30B A3B Instruct31.1B$0.15 / $0.60 /1M262K5h agoQwen3 VL 30B A3B Instruct31.1B$0.15 / $0.60 /1M262K5h agoR1 0528685B$0.50 / $2.15 /1M164K5h agoR1 0528685B$0.50 / $2.15 /1M164K5h agoSeed-2.0-Mini—$0.10 / $0.40 /1M256K5h agoStep 3.7 Flash201B$0.20 / $1.15 /1M262K5h agoStep 3.7 Flash201B$0.20 / $1.15 /1M262K5h ago