Skip to main content
Gateway

Deep Infra

Deep Infra is a Gateway provider with 11 models across 11 offerings.

Access

SDK
@ai-sdk/deepinfra
Environment variables
DEEPINFRA_API_KEY

Models

List view / Table view

11 of 11 model versions

ModelOrganizationFamilyProvider model IDProtocolStreamingContextMax outputInputOutputReasoningTool callStructuredTemperatureWeightsPricingReleasedUpdated
Kimi K3
moonshotai/kimi-k3
Moonshot AIKimi
moonshotai/Kimi-K3
Openai chat
Yes
1M131K
TextImageVideo
Text
YesYesYes-NoOpen weight
input $2.7/M · cache read $0.27/M
output $13.5/M
2026-07-162026-07-30
Kimi K2.7 Code
moonshotai/kimi-k2.7-code
Moonshot AIKimi
moonshotai/Kimi-K2.7-Code
Openai chat
Yes
262K262K
TextImageVideo
Text
YesYesYes-NoOpen weight
input $0.74/M · cache read $0.15/M
output $3.5/M
2026-06-122026-07-22
Nemotron 3 Nano Omni 30B A3B Reasoning
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
NVIDIANemotron
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Openai chat
Yes
256K66K
TextImageVideoAudio
Text
YesYes-NoYesOpen weight
input $0.2/M
output $0.8/M
2026-04-282026-04-28
Kimi K2.6
moonshotai/kimi-k2.6
Moonshot AIKimi
moonshotai/Kimi-K2.6
Openai chat
Yes
262K262K
TextImageVideo
Text
YesYesYesYesOpen weight
input $0.75/M · cache read $0.15/M
output $3.5/M
2026-04-212026-07-22
Gemma 4 26B A4B IT
google/gemma-4-26b-a4b-it
GoogleGemma
google/gemma-4-26B-A4B-it
Openai chat
Yes
262K33K
TextImage
Text
YesYesYesYesOpen weight
input $0.07/M
output $0.34/M
2026-04-022026-07-22
Gemma 4 31B IT
google/gemma-4-31b-it
GoogleGemma
google/gemma-4-31B-it
Openai chat
Yes
262K33K
TextImage
Text
YesYesYesYesOpen weight
input $0.13/M
output $0.38/M
2026-04-022026-04-30
Kimi K2.5
moonshotai/kimi-k2.5
Moonshot AIKimi
moonshotai/Kimi-K2.5
Openai chat
Yes
262K262K
TextImageVideo
Text
YesYesYes-NoOpen weight
input $0.45/M · cache read $0.07/M
output $2.25/M
2026-012026-07-22
Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b
NVIDIANemotron
nvidia/Nemotron-3-Nano-30B-A3B
Openai chat
Yes
262K262K
Text
Text
YesYes-NoYesOpen weight
input $0.05/M · cache read $0.025/M
output $0.2/M
2025-12-152025-12-15
GPT OSS 120B
openai/gpt-oss-120b
OpenAIGPT
openai/gpt-oss-120b
Openai chat
Yes
131K33K
Text
Text
YesYesYesYesOpen weight
input $0.037/M
output $0.17/M
2025-08-052026-07-22
GPT OSS 20B
openai/gpt-oss-20b
OpenAIGPT
openai/gpt-oss-20b
Openai chat
Yes
131K33K
Text
Text
YesYesYesYesOpen weight
input $0.03/M
output $0.14/M
2025-08-052026-03-01
Llama 3.3 Nemotron Super 49B v1.5
nvidia/llama-3.3-nemotron-super-49b-v1.5
NVIDIANemotron
nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
Openai chat
Yes
131K131K
Text
Text
YesYes-NoYesOpen weight
input $0.4/M
output $0.4/M
2025-07-252025-07-25

FAQ