DeepInfra Provider
DeepInfra provides OpenAI-compatible inference for a wide catalog of open-weight models (Llama, DeepSeek, GLM, Qwen, etc.).
Available Models
TCS Cheap
tcs
tcs-cheapStreaming
Vision
Tools
JSON Output
DeepInfra
Context: 1.0M
Input
$0.2
/M tokens
Cached
$0.04
/M tokens
Output
$0.6
/M tokens
TCS Balanced
tcs
tcs-balancedStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
DeepInfra
Context: 262.1k
Input
$0.75
/M tokens
Cached
$0.15
/M tokens
Output
$3.5
/M tokens
TCS Reasoning
tcs
tcs-reasoningStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
DeepInfra
Context: 262.1k
Input
$0.75
/M tokens
Cached
$0.15
/M tokens
Output
$3.5
/M tokens
TCS Premium
tcs
tcs-premiumStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
DeepInfra
Context: 262.1k
Input
$0.75
/M tokens
Cached
$0.15
/M tokens
Output
$3.5
/M tokens
TCS Vision
tcs
tcs-visionStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
DeepInfra
Context: 262.1k
Input
$0.75
/M tokens
Cached
$0.15
/M tokens
Output
$3.5
/M tokens
Kimi K2.6 (DeepInfra)
moonshot
deepinfra-kimi-k2.6Streaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
DeepInfra
Context: 262.1k
Input
$0.75
/M tokens
Cached
$0.15
/M tokens
Output
$3.5
/M tokens
Llama 4 Maverick 17B (DeepInfra)
llama
deepinfra-llama-4-maverickStreaming
Vision
Tools
JSON Output
DeepInfra
Context: 1.0M
Input
$0.2
/M tokens
Cached
$0.04
/M tokens
Output
$0.6
/M tokens
Llama 3.3 70B Instruct (DeepInfra)
llama
deepinfra-llama-3.3-70b-instructStreaming
Tools
JSON Output
DeepInfra
Context: 131.1k
Input
$0.23
/M tokens
Cached
$0.04
/M tokens
Output
$0.4
/M tokens