DeepInfra

68 models available

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by DeepInfra

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	Latency	Throughput
DeepSeek R1-0528 FP4	128k	$0.53/M	$2.26/M	$0.37/M	62.4%	0.8s	20 tps
DeepSeek V3 0324 FP4	128k	$0.25/M	$0.94/M	$0.14/M	11.5%	1.5s	19 tps
DeepSeek V3.1 FP4	128k	$0.26/M	$1.00/M	$0.14/M	47%	0.6s	23 tps
DeepSeek V3.2 FP4	163k	$0.27/M	$0.40/M	$0.14/M	47%	2.7s	20 tps
DeepSeek V3.2 (Thinking) FP4	163k	$0.27/M	$0.40/M	$0.14/M	67.3%	2.7s	20 tps
DeepSeek V4 Flash FP8	1.0M	$0.09/M	$0.19/M	$0.02/M	49.4%	5.1s	14 tps
DeepSeek V4 Flash (Thinking) FP8	1.0M	$0.09/M	$0.19/M	$0.02/M	9.5%	5.1s	14 tps
DeepSeek V4 Flash 0731 FP8	1.0M	$0.06/M	$0.19/M	$0.02/M	87.8%	0.8s	25 tps
DeepSeek V4 Flash 0731 (Thinking) FP8	1.0M	$0.06/M	$0.19/M	$0.02/M	15.8%	0.8s	25 tps
DeepSeek V4 Flash Vision Exp FP8	1.0M	$0.23/M	$0.68/M	$0.0072/M	N/A	1.1s	97 tps
DeepSeek V4 Pro FP8	1.0M	$1.36/M	$2.73/M	$0.10/M	N/A	1.2s	34 tps
DeepSeek V4 Pro (Thinking) FP8	1.0M	$1.36/M	$2.73/M	$0.10/M	N/A	1.2s	34 tps
DeepSeek V4 Pro 0813 FP8	1.0M	$1.36/M	$2.73/M	$0.10/M	0%	0.8s	96 tps
DeepSeek V4 Pro 0813 (Thinking) FP8	1.0M	$1.36/M	$2.73/M	$0.10/M	0%	0.8s	96 tps
DeepSeek V4.1 Flash FP8	1.0M	$0.15/M	$0.44/M	$0.0044/M	85.7%	1.4s	51 tps
DeepSeek V4.1 Flash (Thinking) FP8	1.0M	$0.15/M	$0.44/M	$0.0044/M	84.9%	1.4s	51 tps
Gemma 4 26B A4B FP8	262k	$0.07/M	$0.36/M	$0.01/M	N/A	0.9s	20 tps
Gemma 4 31B FP8	262k	$0.14/M	$0.40/M	$0.02/M	0.4%	3.4s	18 tps
GLM 4.6 FP4	200k	$0.53/M	$2.10/M	$0.10/M	59.7%	0.9s	22 tps
GLM 4.6 (Thinking) FP4	200k	$0.53/M	$2.10/M	$0.10/M	0%	0.9s	22 tps
GLM 4.7 FP4	200k	$0.42/M	$1.84/M	$0.08/M	28.5%	1s	26 tps
GLM 4.7 (Thinking) FP4	200k	$0.42/M	$1.84/M	$0.08/M	24.1%	1s	26 tps
GLM 5.1 FP4	200k	$1.10/M	$3.68/M	$0.22/M	4%	1.1s	32 tps
GLM 5.1 (Thinking) FP4	200k	$1.10/M	$3.68/M	$0.22/M	41.2%	1.1s	32 tps
GLM 5.2 FP4	1.0M	$0.59/M	$1.89/M	$0.11/M	90.2%	1.7s	46 tps
GLM 5.2 (Thinking) FP4	1.0M	$0.59/M	$1.89/M	$0.11/M	57.9%	1.7s	46 tps
GLM 5.3 FP4	1.0M	$0.94/M	$3.15/M	$0.16/M	0.2%	3.6s	30 tps
GLM 5.3 (Thinking) FP4	1.0M	$0.94/M	$3.15/M	$0.16/M	0.6%	3.6s	30 tps
GLM 5.3 Flash FP4	1.0M	$0.08/M	$0.26/M	$0.02/M	2%	1.9s	18 tps
GPT OSS 120B FP8	128k	$0.21/M	$1.00/M	N/A	0%	2.2s	58 tps
GPT OSS 20B BF16	128k	$0.03/M	$0.15/M	N/A	N/A	0.2s	74 tps
Granite 4.2 8B BF16	131k	$0.06/M	$0.26/M	$0.02/M	N/A	0.7s	74 tps
Hermes 3 70B FP8	66k	$0.73/M	$0.73/M	N/A	0%	0.8s	27 tps
Inkling Small FP8	524k	$0.47/M	$1.26/M	$0.10/M	0%	0.6s	53 tps
Inkling Small Thinking FP8	524k	$0.47/M	$1.26/M	$0.10/M	0%	0.6s	53 tps
Kimi K2.6 FP4	256k	$0.79/M	$3.68/M	$0.16/M	N/A	2.1s	21 tps
Kimi K2.7 Code FP4	262k	$0.71/M	$3.57/M	$0.14/M	33.3%	1.1s	44 tps
Kimi K3 BF16	1.0M	$2.99/M	$14.96/M	$0.30/M	20.2%	3s	20 tps
Llama 3.1 8B FP8	131k	$0.02/M	$0.04/M	N/A	0%	0.9s	14 tps
Llama 3.3 70B Instruct FP8	131k	$0.10/M	$0.34/M	N/A	0%	0.8s	5 tps
Llama 4 Maverick FP8	1.0M	$0.21/M	$0.84/M	N/A	0%	0.4s	52 tps
MiMo V2.5 FP8	1.0M	$0.14/M	$0.28/M	$0.0028/M	N/A	0.5s	25 tps
MiMo V2.5 Pro FP8	1.0M	$1.05/M	$3.15/M	$0.21/M	0%	1.4s	34 tps
MiMo V2.5 Pro Thinking FP8	1.0M	$1.05/M	$3.15/M	$0.21/M	5.8%	1.4s	34 tps
MiMo V2.5 Thinking FP8	1.0M	$0.14/M	$0.28/M	$0.0028/M	0%	0.5s	25 tps
MiniMax M2.7 FP8	205k	$0.40/M	$1.79/M	$0.07/M	N/A	2s	91 tps
MiniMax M3 FP8	512k	$0.29/M	$1.16/M	$0.06/M	N/A	1.4s	17 tps
MiniMax M3 Thinking FP8	512k	$0.29/M	$1.16/M	$0.06/M	N/A	1.4s	17 tps
Nvidia Nemotron 3 Super 120B BF16	262k	$0.09/M	$0.42/M	N/A	0%	3s	115 tps
Nvidia Nemotron 3 Super 120B Thinking BF16	262k	$0.09/M	$0.42/M	N/A	0%	3s	115 tps
Nvidia Nemotron 3 Ultra 550B	256k	$0.53/M	$2.31/M	$0.11/M	93.4%	5.5s	35.6 tps
Nvidia Nemotron 3 Ultra 550B Thinking	256k	$0.53/M	$2.31/M	$0.11/M	0%	28.1s	12.7 tps
Nvidia Nemotron 3.5 Lightning	29k	$0.08/M	$0.21/M	$0.04/M	0%	0.6s	424.6 tps
Nvidia Nemotron 3.5 Lightning Thinking	29k	$0.08/M	$0.21/M	$0.04/M	0%	1s	266.8 tps
Qwen 2.5 72B Instruct FP8	131k	$0.38/M	$0.42/M	N/A	0%	0.2s	25 tps
Qwen 3.6 27B FP8	260k	$0.34/M	$3.36/M	N/A	N/A	0.6s	85 tps
Qwen 3.6 27B Thinking FP8	260k	$0.34/M	$3.36/M	N/A	N/A	0.6s	85 tps
Qwen 3.6 35B A3B FP8	262k	$0.10/M	$1.00/M	N/A	N/A	1s	44 tps
Qwen 3.6 35B A3B Thinking FP8	262k	$0.10/M	$1.00/M	N/A	N/A	1s	44 tps
Qwen3 235B A22B FP8	262k	$0.09/M	$0.58/M	N/A	0%	0.3s	12 tps
Qwen3 32B FP8	41k	$0.08/M	$0.29/M	N/A	0%	0.4s	28 tps
Qwen3 Next 80B A3B Instruct FP8	256k	$0.09/M	$1.16/M	N/A	0%	0.6s	41 tps
Qwen3.5 397B FP8	258k	$0.47/M	$3.15/M	$0.23/M	N/A	1.2s	40 tps
Qwen3.5 397B Thinking FP8	258k	$0.47/M	$3.15/M	$0.23/M	N/A	1.2s	40 tps
Qwen3.8 27B BF16	262k	$0.16/M	$1.97/M	$0.04/M	N/A	1.6s	26 tps
Qwen3.8 27B Thinking BF16	262k	$0.16/M	$1.97/M	$0.04/M	N/A	1.6s	26 tps
Qwen3.8 Max FP4	262k	$2.10/M	$6.30/M	$0.21/M	N/A	0.9s	8 tps
Qwen3.8 Max Thinking FP4	262k	$2.10/M	$6.30/M	$0.21/M	N/A	0.9s	8 tps

Prices are per million tokens. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using DeepInfra via the API

For models with provider selection, append :deepinfra to the model ID, set "provider": "deepinfra" in the request body, or send an X-Provider: deepinfra header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-R1-0528:deepinfra",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.

DeepInfra terms of use DeepInfra privacy policy