OpenAI compatible API · Attested · Public status
DeepInfra
Explore DeepInfra models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
DeepInfradeepinfra
No provider claim
These privacy labels describe DeepInfra, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | DeepInfra |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Palo Alto, California, United States Company profile. Source; reviewed 2026-09-27. |
| Routing status | Active |
| Provider website | https://deepinfra.com/ |
| Models | 85 public models |
| Credits routes | 85 |
| Zero data retention | no |
| Verified confidential inference | Not verified |
| Policy note | Tracked as no-store, not strict ZDR. DeepInfra documents memory-only handling and no training for ordinary inference, but reserves the right to log a small portion of requests for debugging or security. Google- and Anthropic-backed routes also inherit those vendors' terms. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- United States; Canada (Toronto, announced capacity)
DeepInfra describes US infrastructure and announced its first international data center in Toronto on July 8, 2026. This is a provider footprint, not an exhaustive or model-specific placement list. DeepSeek V4.1 Flash placement has not been confirmed; do not declare this route US-only. - Can locations change?
- Individual request placement and cross-country failover are not verified.
- Provider region pinning
- No self-service per-request region pin verified for this shared route.
- Pinning through TrustedRouter
- Not supported by the current TrustedRouter integration.
- Infrastructure declaration
- US infrastructure plus announced Canadian capacity; model-specific residency unconfirmed.
- Evidence
- Public provider statement. Reviewed .
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
227 samplesContinuously sampled across DeepInfra's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 4535 ms |
|---|---|
| Effective throughput | 54 tok/s n=8 |
| Uptime | 99.12% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen3.5-397b-a17b | 439 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | 505 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-35b-a3b | 518 ms | — | 100.00% | — | 2 |
| qwen/qwen3-next-80b-a3b-instruct | 544 ms | — | 100.00% | — | 1 |
| xiaomi/mimo-v2.6-pro | 574 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 602 ms | — | 100.00% | — | 1 |
| qwen/qwen3-30b-a3b | 730 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro-0423 | 783 ms | 275 tok/s n=1 | 100.00% | — | 1 |
| tencent/hy4-preview | 842 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-ultra-550b-a55b | 849 ms | — | 100.00% | — | 1 |
| google/gemma-3-12b-it | 885 ms | — | 100.00% | — | 2 |
| google/gemma-4-31b-it-turbo | 1067 ms | — | 100.00% | — | 1 |
| z-ai/glm-4.7 | 1119 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 1149 ms | 120 tok/s n=1 | 100.00% | — | 1 |
| inclusionai/ling-3.1-flash | 1240 ms | — | 100.00% | — | 1 |
| thinkingmachines/inkling | 1437 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | 1554 ms | 53 tok/s n=1 | 100.00% | — | 1 |
| qwen/qwen3-14b | 1821 ms | — | 100.00% | — | 1 |
| google/gemma-3-4b-it | 1950 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3.5-lightning | 2021 ms | — | 100.00% | — | 1 |
| sao10k/l3-8b-lunaris-v1-turbo | 2034 ms | — | 100.00% | — | 1 |
| bytedance/seed-1.8 | 2104 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 2126 ms | — | 100.00% | — | 1 |
| qwen/qwen3.7-max | 2230 ms | — | 100.00% | — | 1 |
| google/gemini-2.5-flash | 2268 ms | — | 100.00% | — | 1 |
| google/gemini-3.1-flash-lite | 2308 ms | — | 100.00% | — | 2 |
| nousresearch/hermes-3-llama-3.1-405b | 2355 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b-instruct-turbo | 2435 ms | — | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 2462 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 3504 ms | 25 tok/s n=1 | 100.00% | — | 1 |
| google/gemini-2.5-pro | 4535 ms | — | 100.00% | — | 186 |
| google/gemini-3.7-flash | 4537 ms | — | 100.00% | — | 1 |
| bytedance/seed-2.0-pro | 5711 ms | — | 100.00% | — | 1 |
| qwen/qwen3.8-27b | 29045 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.1-70b-instruct | — | — | 100.00% | — | 1 |
| qwen/qwen3-vl-30b-a3b-instruct | — | — | 100.00% | — | 1 |
| inclusionai/ling-3.0-flash | — | — | 0.00% | — | 1 |
| minimax/minimax-m3 | — | 44 tok/s n=2 | — | — | 0 |
| moonshotai/kimi-k2.6 | — | 54 tok/s n=2 | — | — | 0 |
| qwen/qwen3.6-35b-a3b | — | — | 0.00% | — | 1 |
DeepInfra performance history · Full provider & model leaderboard.
Provider models
Models served by DeepInfra.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
Qwen/Qwen3-Embedding-8BQwen3 Embedding 8B |
— | 32,000 | $0.01055/1M | Not published | selected route |
bytedance/seed-1.8ByteDance/Seed-1.8 |
— | 256,000 | $0.26375/1M | $0.05275/1M | $2.11/1M |
bytedance/seed-2.0-codeByteDance/Seed-2.0-code |
— | 256,000 | $0.5275/1M | $0.1055/1M | $3.165/1M |
bytedance/seed-2.0-miniByteDance/Seed-2.0-mini |
— | 256,000 | $0.1055/1M | $0.0211/1M | $0.422/1M |
bytedance/seed-2.0-proByteDance/Seed-2.0-pro |
— | 256,000 | $0.5275/1M | $0.1055/1M | $3.165/1M |
deepseek/deepseek-r1-0528DeepSeek: R1 0528 |
— | 163,840 | $0.5275/1M | $0.36925/1M | $2.26825/1M |
deepseek/deepseek-v3deepseek-ai/DeepSeek-V3 |
— | 163,840 | $0.3376/1M | Not published | $0.93895/1M |
deepseek/deepseek-v3.1deepseek-ai/DeepSeek-V3.1 |
IQ 98#125 | 163,840 | $0.26375/1M | $0.13715/1M | $1.00225/1M |
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
IQ 102#105 | 163,840 | $0.2743/1M | $0.13715/1M | $0.4009/1M |
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 122#35 | 1,048,576 | $0.09495/1M | $0.01899/1M | $0.1899/1M |
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,048,576 | $0.0633/1M | $0.015825/1M | $0.1899/1M |
deepseek/deepseek-v4-flash-vision-expDeepSeek: DeepSeek V4 Flash Vision Exp |
IQ 122#36 | 1,048,576 | $0.4642/1M | $0.01477/1M | $1.3926/1M |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro 0423 |
IQ 124#29 | 1,048,576 | $1.3715/1M | $0.1055/1M | $2.743/1M |
deepseek/deepseek-v4-pro-0423DeepSeek V4 Pro 0423 |
— | 1,048,576 | $1.3715/1M | $0.1055/1M | $2.743/1M |
deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash |
IQ 126#21 | 1,048,576 | $0.211/1M | $0.01/1M | $0.633/1M |
google/gemini-2.5-flashGoogle: Gemini 2.5 Flash |
— | 1,048,576 | $0.3165/1M | Not published | $2.6375/1M |
google/gemini-2.5-proGoogle: Gemini 2.5 Pro |
IQ 99#121 | 1,048,576 | $1.31875/1M | Not published | $10.55/1M |
google/gemini-3.1-flash-liteGoogle: Gemini 3.1 Flash Lite |
IQ 104#94 | 1,048,576 | $0.26375/1M | Not published | $1.5825/1M |
google/gemini-3.1-progoogle/gemini-3.1-pro |
IQ 122#37 | 1,000,000 | $2.11/1M | Not published | $12.66/1M |
google/gemini-3.7-flashGoogle: Gemini 3.7 Flash |
IQ 127#19 | 1,048,576 | $0.79125/1M | Not published | $3.95625/1M |
google/gemma-3-12b-itGoogle: Gemma 3 12B |
— | 131,072 | $0.05275/1M | Not published | $0.15825/1M |
google/gemma-3-27b-itGoogle: Gemma 3 27B |
— | 131,072 | $0.0844/1M | Not published | $0.1688/1M |
google/gemma-3-4b-itGoogle: Gemma 3 4B |
— | 131,072 | $0.05275/1M | Not published | $0.1055/1M |
google/gemma-4-26b-a4b-itGoogle: Gemma 4 26B A4B |
IQ 100#113 | 262,144 | $0.07385/1M | Not published | $0.3587/1M |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#110 | 262,144 | $0.211/1M | Not published | $0.422/1M |
google/gemma-4-31b-it-turbogoogle/gemma-4-31B-it-turbo |
— | 262,144 | $0.09495/1M | $0.05275/1M | $0.3587/1M |
google/gemma-4-31b-it-ultragoogle/gemma-4-31B-it-Ultra |
— | 131,072 | $0.28485/1M | Not published | $0.8018/1M |
gryphe/mythomax-l2-13bMythoMax 13B |
— | 4,096 | $0.422/1M | Not published | $0.422/1M |
ibm-granite/granite-4.2-8bIBM: Granite 4.2 8B |
IQ 93#144 | 131,072 | $0.0633/1M | $0.015825/1M | $0.26375/1M |
inclusionai/ling-3.0-flashinclusionAI: Ling 3.0 Flash |
IQ 105#91 | 131,072 | $0.0633/1M | $0.01266/1M | $0.1899/1M |
inclusionai/ling-3.0-flash-vlinclusionAI: Ling 3.0 Flash VL |
— | 131,072 | $0.0633/1M | $0.01266/1M | $0.1899/1M |
inclusionai/ling-3.1-flashinclusionAI: Ling 3.1 Flash |
— | 262,144 | $0.3165/1M | $0.0633/1M | $0.9495/1M |
meta-llama/llama-3.1-70b-instructMeta: Llama 3.1 70B Instruct |
— | 131,072 | $0.422/1M | Not published | $0.422/1M |
meta-llama/llama-3.3-70b-instruct-turbometa-llama/Llama-3.3-70B-Instruct-Turbo |
— | 131,072 | $0.1055/1M | Not published | $0.3376/1M |
meta-llama/llama-4-scout-17b-16e-instructLlama 4 Scout Instruct |
— | 131,072 | $0.1055/1M | Not published | $0.3165/1M |
meta-llama/llama-guard-4-12bMeta: Llama Guard 4 12B |
— | 163,840 | $0.1899/1M | Not published | $0.1899/1M |
meta-llama/meta-llama-3.1-8b-instruct-turbometa-llama/Meta-Llama-3.1-8B-Instruct-Turbo |
— | 131,072 | $0.0211/1M | Not published | $0.0422/1M |
meta-models/muse-glimmer-30bmeta-models/Muse-Glimmer-30B |
— | 131,072 | $0.3165/1M | $0.0422/1M | $1.266/1M |
microsoft/phi-4Microsoft: Phi 4 |
— | 16,384 | $0.07385/1M | Not published | $0.1477/1M |
minimax/minimax-m3MiniMax: MiniMax M3 |
IQ 115#54 | 524,288 | $0.2954/1M | $0.05908/1M | $1.1605/1M |
mistralai/mistral-nemo-instruct-2407mistralai/Mistral-Nemo-Instruct-2407 |
— | 131,072 | $0.030595/1M | Not published | $0.03165/1M |
mistralai/mistral-small-24b-instruct-2501Mistral: Mistral Small 3 |
— | 32,768 | $0.05275/1M | Not published | $0.0844/1M |
mistralai/mistral-small-3.2-24b-instruct-2506mistralai/Mistral-Small-3.2-24B-Instruct-2506 |
— | 128,000 | $0.079125/1M | Not published | $0.211/1M |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 115#52 | 262,144 | $0.79125/1M | $0.15825/1M | $3.6925/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 127#20 | 1,048,576 | $3.00675/1M | $0.300675/1M | $15.03375/1M |
nousresearch/hermes-3-llama-3.1-405bNous: Hermes 3 405B Instruct |
— | 131,072 | $1.055/1M | Not published | $1.055/1M |
nvidia/nemotron-3-super-120b-a12bNVIDIA: Nemotron 3 Super |
— | 262,144 | $0.089675/1M | Not published | $0.422/1M |
nvidia/nemotron-3-ultra-550b-a55bNVIDIA: Nemotron 3 Ultra |
— | 262,144 | $0.5275/1M | $0.1055/1M | $2.321/1M |
nvidia/nemotron-3.5-lightningNVIDIA: Nemotron 3.5 Lightning |
— | 262,144 | $0.0633/1M | $0.03165/1M | $0.1688/1M |
nvidia/nemotron-content-safety-3.5nvidia/Nemotron-Content-Safety-3.5 |
— | 131,072 | $0.211/1M | Not published | $0.211/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 98#126 | 131,072 | $0.039035/1M | Not published | $0.17935/1M |
openai/gpt-oss-120b-turboopenai/gpt-oss-120b-Turbo |
— | 131,072 | $0.15825/1M | Not published | $0.633/1M |
openai/gpt-oss-120b-ultraopenai/gpt-oss-120b-Ultra |
— | 131,072 | $0.211/1M | Not published | $1.00225/1M |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
IQ 94#140 | 131,072 | $0.03165/1M | Not published | $0.1477/1M |
qwen/qwen2.5-72b-instructQwen/Qwen2.5-72B-Instruct |
— | 32,768 | $0.3798/1M | Not published | $0.422/1M |
qwen/qwen3-14bQwen: Qwen3 14B |
— | 40,960 | $0.1266/1M | Not published | $0.2532/1M |
qwen/qwen3-235b-a22b-instruct-2507Qwen/Qwen3-235B-A22B-Instruct-2507 |
— | 262,144 | $0.09495/1M | Not published | $0.58025/1M |
qwen/qwen3-30b-a3bQwen: Qwen3 30B A3B |
— | 40,960 | $0.1266/1M | Not published | $0.5275/1M |
qwen/qwen3-coder-480b-a35b-instruct-turboQwen/Qwen3-Coder-480B-A35B-Instruct-Turbo |
— | 262,144 | $0.3165/1M | $0.1055/1M | $1.055/1M |
qwen/qwen3-next-80b-a3b-instructQwen: Qwen3 Next 80B A3B Instruct |
— | 262,144 | $0.09495/1M | Not published | $1.1605/1M |
qwen/qwen3-vl-235b-a22b-instructQwen: Qwen3 VL 235B A22B Instruct |
— | 262,144 | $0.211/1M | $0.11605/1M | $0.9284/1M |
qwen/qwen3-vl-30b-a3b-instructQwen: Qwen3 VL 30B A3B Instruct |
— | 262,144 | $0.15825/1M | Not published | $0.633/1M |
qwen/qwen3.5-27bQwen: Qwen3.5-27B |
— | 262,144 | $0.2743/1M | Not published | $2.743/1M |
qwen/qwen3.5-35b-a3bQwen: Qwen3.5-35B-A3B |
— | 262,144 | $0.1477/1M | $0.05275/1M | $1.055/1M |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
— | 262,144 | $0.47475/1M | $0.2321/1M | $3.165/1M |
qwen/qwen3.5-9bQwen: Qwen3.5-9B |
IQ 98#131 | 262,144 | $0.1055/1M | Not published | $0.15825/1M |
qwen/qwen3.6-27bQwen: Qwen3.6 27B |
IQ 111#72 | 262,144 | $0.3376/1M | Not published | $3.376/1M |
qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B A3B |
IQ 104#100 | 262,144 | $0.1055/1M | $0.1055/1M | $1.00225/1M |
qwen/qwen3.7-maxQwen3.7 Max |
IQ 119#46 | 1,000,000 | $2.6375/1M | $0.5275/1M | $7.9125/1M |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 116#50 | 65,536 | $0.211/1M | $0.05275/1M | $2.6375/1M |
qwen/qwen3.8-flashQwen3.8 Flash |
IQ 116#51 | 1,000,000 | $0.119215/1M | $0.014876/1M | $0.40301/1M |
qwen/qwen3.8-maxQwen3.8 Max |
IQ 124#32 | 1,000,000 | $1.74075/1M | $0.21733/1M | $5.223305/1M |
sao10k/l3-8b-lunaris-v1-turboSao10K/L3-8B-Lunaris-v1-Turbo |
— | 8,192 | $0.0422/1M | Not published | $0.05275/1M |
sao10k/l3.1-70b-euryale-v2.2Sao10K/L3.1-70B-Euryale-v2.2 |
— | 131,072 | $0.89675/1M | Not published | $0.89675/1M |
stepfun-ai/step-5-previewstepfun-ai/Step-5-Preview |
— | 1,048,576 | $1.055/1M | $0.05275/1M | $2.8485/1M |
tencent/hy4-previewTencent: Hy4 preview |
IQ 113#60 | 1,048,576 | $0.87987/1M | $0.04431/1M | $2.638555/1M |
thinkingmachines/inklingThinking Machines: Inkling |
IQ 108#81 | 524,288 | $1.00225/1M | $0.1688/1M | $4.27275/1M |
thinkingmachines/inkling-smallThinking Machines: Inkling Small |
IQ 111#71 | 524,288 | $0.47475/1M | $0.1055/1M | $1.266/1M |
xiaomi/mimo-v2.6-flashXiaomi: MiMo-V2.6-Flash |
IQ 122#38 | 1,050,000 | $0.1477/1M | $0.01/1M | $0.2954/1M |
xiaomi/mimo-v2.6-proXiaomi: MiMo-V2.6-Pro |
IQ 125#27 | 1,050,000 | $0.45365/1M | $0.01/1M | $0.91785/1M |
z-ai/glm-4.6Z.ai: GLM 4.6 |
— | 202,752 | $0.5275/1M | $0.1055/1M | $2.11/1M |
z-ai/glm-4.7Z.ai: GLM 4.7 |
IQ 105#90 | 202,752 | $0.422/1M | $0.0844/1M | $1.84625/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 119#45 | 1,048,576 | $0.79125/1M | $0.1477/1M | $2.532/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 125#24 | 1,048,576 | $0.9495/1M | $0.211/1M | $4.22/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 120#42 | 1,048,576 | $0.15825/1M | $0.03165/1M | $0.5275/1M |
Questions
Does DeepInfra have zero data retention?
TrustedRouter does not currently mark DeepInfra as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is DeepInfra end-to-end encrypted?
TrustedRouter does not currently mark DeepInfra as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which DeepInfra models are available through TrustedRouter?
This page currently lists 85 public DeepInfra models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.