DeepInfra Models

Serverless inference for machine learning models. Requesty routes to 77 DeepInfra models starting at $0.02 per 1M input tokens with context windows up to 1.0M tokens. One API key and an OpenAI-compatible SDK. Provider rates plus 5% on pay as you go, or 0% with your own keys.

DeepInfra homepage →

Flagship model

deepseek-v4.1-flash-1017

View details →

Intelligence Index

45.1

All DeepInfra models

Model	Context	Max Output	Input/1M	Output/1M	Capabilities	Coding
deepseek-v4.1-flash-1017 51% off	1.0M	—	$0.20$0.10	$0.60$0.29	👁🧠🔧⚡	N/A
deepseek-v4.1-flash-1017:priority 51% off	1.0M	—	$0.30$0.15	$0.90$0.44	👁🧠🔧⚡	N/A
step-5-preview	1.0M	66K	$1.00	$2.70	👁🧠🔧⚡	N/A
mimo-v2.6-flash	1.0M	131K	$0.14	$0.28	👁🧠🔧⚡	N/A
mimo-v2.6-pro	1.0M	131K	$0.43	$0.87	👁🧠🔧⚡	N/A
deepseek-v4.1-flash	1.0M	—	$0.20	$0.60	👁🧠🔧⚡	N/A
deepseek-v4.1-flash:flex	1.0M	—	$0.16	$0.48	👁🧠🔧⚡	N/A
glm-5.3-flash	1.0M	131K	$0.15	$0.50	👁🧠🔧⚡	72
glm-5.3	1.0M	1.0M	$1.20	$4.00	👁🧠🔧⚡	75
qwen3.8-27b	262K	131K	$0.20	$2.50	👁🧠🔧⚡	68
deepseek-v4-pro-0813	1.0M	1.0M	$1.30	$2.60	🧠🔧⚡	69
qwen3.8	262K	262K	$2.00	$6.00	🧠🔧⚡	N/A
deepseek-v4-flash-0731	1.0M	—	$0.09	$0.18	🧠🔧⚡	69
deepseek-v4-flash-0731:flex	1.0M	—	$0.07	$0.14	🧠🔧⚡	69
glm-5.2	262K	128K	$0.75	$2.40	🧠🔧⚡	69
glm-5.2:flex	1M	128K	$0.60	$1.92	🧠🔧⚡	69
ByteDance/Seed-1.8	256K	—	$0.25	$2.00	👁🧠🔧⚡	N/A
deepseek-v4-pro-0424	1.0M	—	$1.30	$2.60	🧠🔧⚡	59
deepseek-v4-pro-0424:flex	1.0M	—	$1.04	$2.08	🧠🔧⚡	59
deepseek-v4-flash-0424	1.0M	—	$0.10	$0.20	🧠🔧⚡	69
deepseek-v4-flash-0424:flex	1.0M	—	$0.07	$0.14	🧠🔧⚡	69
XiaomiMiMo/MiMo-V2.5-Pro	1.0M	—	$1.00	$3.00	🧠🔧⚡	60
XiaomiMiMo/MiMo-V2.5-Pro:flex	1.0M	—	$0.80	$2.40	🧠🔧⚡	60
XiaomiMiMo/MiMo-V2.5	262K	—	$0.40	$2.00	👁🧠🔧⚡	N/A
XiaomiMiMo/MiMo-V2.5:flex	262K	—	$0.32	$1.60	👁🧠🔧⚡	N/A
moonshotai/Kimi-K2.6	262K	—	$0.75	$3.50	👁🧠🔧⚡	62
moonshotai/Kimi-K2.6:flex	262K	—	$0.60	$2.80	👁🧠🔧⚡	62
zai-org/GLM-5.1	203K	—	$1.05	$3.50	🧠🔧⚡	56
zai-org/GLM-5.1:flex	203K	—	$0.84	$2.80	🧠🔧⚡	56
gemma-4-26B-A4B-it	262K	—	$0.07	$0.34	👁🧠🔧	N/A
gemma-4-26B-A4B-it:flex	262K	—	$0.06	$0.27	👁🧠🔧	N/A
gemma-4-31B-it	262K	—	$0.13	$0.38	👁🧠🔧	N/A
gemma-4-31B-it:flex	262K	—	$0.10	$0.30	👁🧠🔧	N/A
moonshotai/Kimi-K2.5	262K	131K	$0.45	$2.25	👁🧠🔧⚡	47
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B	262K	—	$0.10	$0.50	🧠🔧	38
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B:flex	262K	—	$0.07	$0.32	🧠🔧	38
ByteDance/Seed-2.0-code	256K	—	$0.50	$3.00	👁🧠🔧⚡	N/A
ByteDance/Seed-2.0-pro	256K	—	$0.50	$3.00	👁🧠🔧⚡	N/A
Qwen/Qwen3.5-2B	262K	—	$0.02	$0.10	👁🧠🔧	3
ByteDance/Seed-2.0-mini	256K	—	$0.10	$0.40	👁🧠🔧⚡	N/A
Qwen/Qwen3.5-35B-A3B	262K	—	$0.14	$1.00	👁🧠🔧⚡	N/A
Qwen/Qwen3.5-35B-A3B:flex	262K	—	$0.11	$0.80	👁🧠🔧⚡	N/A
Qwen/Qwen3.5-27B	262K	—	$0.26	$2.60	👁🧠🔧	N/A
Qwen/Qwen3.5-27B:flex	262K	—	$0.21	$2.08	👁🧠🔧	N/A
Qwen/Qwen3.5-397B-A17B	262K	—	$0.49	$3.60	👁🧠🔧⚡	N/A
Qwen/Qwen3.5-397B-A17B:flex	262K	—	$0.36	$2.40	👁🧠🔧⚡	N/A
nvidia/Nemotron-3-Nano-30B-A3B	262K	—	$0.05	$0.20	🧠🔧	N/A
nvidia/Nemotron-3-Nano-30B-A3B:flex	262K	—	$0.04	$0.16	🧠🔧	N/A
Qwen/Qwen3-Max	256K	—	$1.20	$6.00	🧠🔧⚡	N/A
deepseek-ai/DeepSeek-V3.1	164K	—	$0.30	$1.00	🧠🔧	N/A
deepseek-ai/DeepSeek-V3.1:flex	164K	—	$0.20	$0.76	🧠🔧	N/A
zai-org/GLM-4.5	131K	4K	$0.60	$2.20	🧠🔧	N/A
zai-org/GLM-4.5-Air	131K	4K	$0.20	$1.10	🧠🔧	N/A
Qwen/Qwen3-235B-A22B-Thinking-2507	262K	—	$0.23	$2.30	🧠🔧⚡	N/A
Qwen/Qwen3-235B-A22B-Thinking-2507:flex	262K	—	$0.18	$1.84	🧠🔧⚡	N/A
Qwen/Qwen3-Coder-480B-A35B-Instruct	262K	—	$0.40	$1.60	🧠🔧	N/A
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo	262K	—	$0.30	$1.00	🧠🔧⚡	N/A
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo:flex	262K	—	$0.24	$0.80	🧠🔧⚡	N/A
Qwen/Qwen3-235B-A22B-Instruct-2507	262K	—	$0.07	$0.10	🧠🔧	22
Qwen/Qwen3-32B	41K	—	$0.10	$0.30	🔧	N/A
Qwen/Qwen3-32B:flex	41K	—	$0.06	$0.22	🔧	N/A
Qwen/Qwen3-235B-A22B	41K	4K	$0.20	$0.60	🧠🔧	N/A
deepseek-ai/DeepSeek-R1-Distill-Llama-70B	64K	8K	$0.23	$0.69	🧠	N/A
deepseek-ai/DeepSeek-R1	64K	8K	$0.85	$2.50	🧠🔧	N/A
phi-4	16K	—	$0.07	$0.14	🧠	N/A
phi-4:flex	16K	—	$0.06	$0.11	🧠	N/A
deepseek-ai/DeepSeek-V3	128K	8K	$0.85	$0.90	🧠🔧	23
deepseek-ai/DeepSeek-V3:flex	128K	8K	$0.26	$0.71	🧠🔧	23
meta-llama/Llama-3.3-70B-Instruct	131K	—	$0.23	$0.40	🧠🔧	N/A
meta-llama/Llama-3.3-70B-Instruct-Turbo	131K	—	$0.12	$0.30	🧠🔧	N/A
meta-llama/Llama-3.3-70B-Instruct-Turbo:flex	131K	—	$0.08	$0.26	🧠🔧	N/A
Qwen/Qwen2.5-Coder-32B-Instruct	16K	41K	$0.07	$0.16	🔧	N/A
meta-llama/Llama-3.2-90B-Vision-Instruct	131K	4K	$0.35	$0.40	🧠	N/A
Qwen/Qwen2.5-72B-Instruct	131K	—	$0.23	$0.40	🧠🔧	N/A
meta-llama/Meta-Llama-3.1-405B-Instruct	131K	—	$0.80	$0.80	🧠	N/A
meta-llama/Meta-Llama-3.1-70B-Instruct	131K	—	$0.23	$0.40	🧠🔧	N/A
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo	131K	—	$0.02	$0.05	🧠🔧	N/A

About DeepInfra on Requesty

How many DeepInfra models are available through Requesty?

Requesty routes to 77 DeepInfra models including regional variants, with pricing synced in real time to the upstream provider.

What is the cheapest DeepInfra model?

The cheapest DeepInfra model starts at $0.02 per million input tokens. See the pricing column in the table below for full per-model rates.

Does Requesty add markup on DeepInfra pricing?

No. Requesty passes through exactly what DeepInfra charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 600+ models.

Is my data used to train DeepInfra models?

DeepInfra's terms state that API data is not used for training. See their privacy policy for the authoritative statement.

Where are DeepInfra models hosted?

DeepInfra models are hosted in 🇺🇸 US. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the DeepInfra rows in the models explorer.

← All models DeepInfra website →