Launch offer: 30% off all Runware models until August 26
Runware Provider
Runware provides fast, cost-efficient inference for open and frontier LLMs through an OpenAI-compatible API.
Data & Privacy
HQ:GB
API Training:No
Consumer Training:No
Prompt Logging:Yes
Retention:30 days
Available Models
GLM-5.2
zai30% off
glm-5.2Streaming
Tools
Reasoning
JSON Output
30% Discount
Runware
Context: 1.0MQuant: fp430% off
Input
$0.8$0.56
/M tokens
Cached
$0.16$0.112
/M tokens
Output
$2.55$1.785
/M tokens
DeepSeek V4 Pro
deepseek30% off
deepseek-v4-proStreaming
Tools
Reasoning
JSON Schema
30% Discount
Runware
Context: 1.0MQuant: fp830% off
Input
$0.961$0.6727
/M tokens
Cached
$0.079$0.0553
/M tokens
Output
$1.922$1.3454
/M tokens
DeepSeek V4 Flash
deepseek30% off
deepseek-v4-flashStreaming
Tools
Reasoning
JSON Schema
30% Discount
Runware
Context: 1.0MQuant: fp830% off
Input
$0.076$0.0532
/M tokens
Cached
$0.014$0.0098
/M tokens
Output
$0.153$0.1071
/M tokens
Kimi K2.6
moonshot30% off
kimi-k2.6Streaming
Vision
Tools
Reasoning
JSON Output
30% Discount
Runware
Context: 262.1kQuant: fp430% off
Input
$0.6$0.42
/M tokens
Cached
$0.13$0.091
/M tokens
Output
$3.05$2.135
/M tokens
Gemma 4 31B IT
google30% off
gemma-4-31b-itStreaming
Vision
Tools
Reasoning
30% Discount
Runware
Context: 262.1kQuant: bf1630% off
Input
$0.102$0.0714
/M tokens
Cached
$0.012$0.0084
/M tokens
Output
$0.297$0.2079
/M tokens
GPT OSS 120B
openai30% off
gpt-oss-120bStreaming
Tools
Reasoning
JSON Output
30% Discount
Runware
Context: 131.1kQuant: bf1630% off
Input
$0.032$0.0224
/M tokens
Cached
$0.032$0.0224
/M tokens
Output
$0.14$0.098
/M tokens