DeepInfra Provider
DeepInfra inference platform with OpenAI-compatible API for hosting open-source models.
Data & Privacy
HQ:US
API Training:No
Consumer Training:No
Prompt Logging:No
Retention:0 days
GDPR:Compliant
SOC2:Type II Certified
ISO 27001:Certified
Available Models
Hy3
tencent
hy3Streaming
Tools
Reasoning
JSON Output
JSON Schema
DeepInfra
Context: 262.1kQuant: fp8
Input
$0.14
/M tokens
Cached
$0.035
/M tokens
Output
$0.58
/M tokens
Qwen3.5 9B
alibaba
qwen3.5-9bStreaming
Tools
Reasoning
JSON Output
DeepInfra
Context: 262.1kQuant: bf16
Input
$0.1
/M tokens
Cached
—
/M tokens
Output
$0.15
/M tokens
Nemotron 3 Ultra 550B
nvidia
nemotron-3-ultra-550bStreaming
Vision
Tools
JSON Output
DeepInfra
Context: 262.1kQuant: fp4
Input
$0.5
/M tokens
Cached
$0.15
/M tokens
Output
$2.5
/M tokens
DeepSeek V4 Pro
deepseek
deepseek-v4-proStreaming
Tools
Reasoning
JSON Output
DeepInfra
Context: 64kQuant: fp4
Input
$1.74
/M tokens
Cached
$0.145
/M tokens
Output
$3.48
/M tokens
DeepSeek V4 Flash
deepseek
deepseek-v4-flashStreaming
Tools
Reasoning
JSON Output
DeepInfra
Context: 1MQuant: fp4
Input
$0.14
/M tokens
Cached
$0.028
/M tokens
Output
$0.28
/M tokens
GLM-5.1
zai
glm-5.1Streaming
Tools
Reasoning
JSON Output
DeepInfra
Context: 198kQuant: fp4
Input
$1.05
/M tokens
Cached
$0.205
/M tokens
Output
$3.5
/M tokens
Gemma 4 31B IT
google
gemma-4-31b-itStreaming
Tools
Reasoning
JSON Output
DeepInfra
Context: 262.1kQuant: fp8
Input
$0.13
/M tokens
Cached
—
/M tokens
Output
$0.38
/M tokens
Gemma 4 26B A4B IT
google
gemma-4-26b-a4b-itStreaming
Tools
Reasoning
JSON Output
DeepInfra
Context: 262.1kQuant: fp8
Input
$0.07
/M tokens
Cached
—
/M tokens
Output
$0.34
/M tokens
Kimi K2.5
moonshot
kimi-k2.5Streaming
Vision
Tools
Reasoning
JSON Output
DeepInfra
Context: 256kQuant: fp4
Input
$0.45
/M tokens
Cached
$0.07
/M tokens
Output
$2.25
/M tokens
Qwen3 VL 30B A3B Instruct
alibaba
qwen3-vl-30b-a3b-instructStreaming
Vision
Tools
JSON Output
DeepInfra
Context: 262.1kQuant: fp8
Input
$0.15
/M tokens
Cached
—
/M tokens
Output
$0.6
/M tokens
DeepSeek V3.2
deepseek
deepseek-v3.2Streaming
Tools
JSON Output
DeepInfra
Context: 160kQuant: fp4
Input
$0.26
/M tokens
Cached
$0.13
/M tokens
Output
$0.38
/M tokens
Qwen3 VL 235B A22B Instruct
alibaba
qwen3-vl-235b-a22b-instructStreaming
Vision
Tools
JSON Output
DeepInfra
Context: 262.1kQuant: fp8
Input
$0.2
/M tokens
Cached
$0.11
/M tokens
Output
$0.88
/M tokens
Qwen3 Reranker 8B
alibaba
qwen3-reranker-8bDeepInfra
Context: 32.8k
Input
$0.05
/M tokens
Cached
—
/M tokens
Output
$0
/M tokens
Qwen3 Reranker 4B
alibaba
qwen3-reranker-4bDeepInfra
Context: 32.8k
Input
$0.03
/M tokens
Cached
—
/M tokens
Output
$0
/M tokens
Qwen3 Reranker 0.6B
alibaba
qwen3-reranker-0.6bDeepInfra
Context: 32.8k
Input
$0.01
/M tokens
Cached
—
/M tokens
Output
$0
/M tokens
Qwen3 Embedding 8B
alibaba
qwen3-embedding-8bDeepInfra
Context: 32.8k
Input
$0.01
/M tokens
Cached
—
/M tokens
Output
$0
/M tokens
BGE-M3
baai
bge-m3DeepInfra
Context: 8.2k
Input
$0.01
/M tokens
Cached
—
/M tokens
Output
$0
/M tokens