Model provider

Inference APIs

Explore models served by Inference APIs.

11models

Pricing & endpoints

11 offers · USD per million tokens
ModelProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredRoute
GLM-5.3Inference APIs
zai-org/GLM-5.3
1,000,000131,072— / ————
View route
Llama-3.3-70B-InstructInference APIs
meta-llama/Llama-3.3-70B-Instruct-Turbo
131,0724,096— / ————
View route
Qwen3.8 FlashInference APIs
Qwen/Qwen3.8-Flash
1,000,000131,072— / ————
View route
GLM-5.3-FlashInference APIs
zai-org/GLM-5.3-Flash
1,000,000131,072— / ————
View route
Kimi K2.7 CodeInference APIs
moonshotai/Kimi-K2.7-Code
262,144262,144— / ————
View route
GPT OSS 120BInference APIs
openai/gpt-oss-120b
131,072131,072— / ————
View route
GPT OSS 20BInference APIs
openai/gpt-oss-20b
131,072131,072— / ————
View route
DeepSeek V4 FlashInference APIs
deepseek-ai/DeepSeek-V4-Flash
1,048,576384,000— / ————
View route
DeepSeek V4 ProInference APIs
deepseek-ai/DeepSeek-V4-Pro
1,048,576384,000— / ————
View route
DeepSeek V4.1 FlashInference APIs
deepseek-ai/DeepSeek-V4.1-Flash
1,048,576384,000— / ————
View route
MiniMax-M3Inference APIs
MiniMaxAI/MiniMax-M3
524,288512,000— / ————
View route
1–11 of 11

Prices, limits and configurations apply to each serving offer. Open a model for its complete specifications and provider comparison.