GLM 5.3 Flash Inference / Multimodal · 1M context Frontier Provider Input Cache Output
Qwen3.8 Flash-Next Multimodal · 256K context Frontier Provider Input Cache Output
DeepSeek V4.1 Flash Multimodal · 1M / , context Frontier Provider Input Cache Output
DeepSeek V4 Flash Inference · 1M / , context Frontier Provider Input Cache Output
Qwen3.6 35B A3B Multimodal · 262K / , context Frontier Provider Input Cache Output
Qwen3.8 27B Multimodal · 256K / 262K context Frontier Provider Input Cache Output
Qwen3.5 397B Multimodal · , context Frontier Provider Input Cache Output
GLM 5.3 Inference · 1M / , context Frontier Provider Input Cache Output
Kimi K2.7 Code Multimodal · 256K context Frontier Provider Input Cache Output
GLM-5.2 Inference · 1M / 524K context Frontier Provider Input Cache Output
Kimi K2.6 Multimodal · 262K context Frontier Provider Input Cache Output
DeepSeek V4 Pro Inference · 1M context Frontier Provider Input Cache Output
Qwen3.8 2.4T A95B Inference · 256K context Frontier Provider Input Cache Output
Kimi K3 Multimodal · 1M context Frontier Provider Input Cache Output
Mistral Moderation 2 Moderation · 128K context Legacy Provider Input Cache Output
KB-Whisper Large Speech · , / 448 context Legacy Provider Input Cache Output
Voxtral Small 24B Speech · 32K context Legacy Provider Input Cache Output
Whisper Large v3 Speech · 448 / , context Legacy Provider Input Cache Output
Whisper Large v3 Turbo Speech · 448 context Legacy Provider Input Cache Output
Voxtral Mini Transcribe 3 Speech · 32K context Legacy Provider Input Cache Output
Voxtral Small Transcribe 3 Speech · 32K context Legacy Provider Input Cache Output
Voxtral Mini Transcribe Realtime 3 Speech · , context Legacy Provider Input Cache Output
Qwen3 Embedding 8B Embedding · , / 40K context Legacy Provider Input Cache Output
MU multilingual-e5-large Embedding · , context
Legacy Provider Input Cache Output
MU multilingual-e5-large-instruct Embedding · , context
Legacy Provider Input Cache Output
Qwen3 Reranker 4B Rerank · 32K context Legacy Provider Input Cache Output
Ministral 3 3B Multimodal · 256K context Legacy Provider Input Cache Output
Mistral Embed Embedding · 8K context Legacy Provider Input Cache Output
Voxtral Small Audio · 32K context Legacy Provider Input Cache Output
EM E5 Multilingual Large Instruct Embedding · 512 context
Legacy Provider Input Cache Output
BGE Multilingual Gemma2 Embedding · , context Legacy Provider Input Cache Output
BG bge-reranker-v2-m3 Rerank · , context
Legacy Provider Input Cache Output
Green Rerank Rerank · 32K context Legacy Provider Input Cache Output
Gemma 4 26B A4B Multimodal · 262K / , context Legacy Provider Input Cache Output
Codestral Embed Embedding · 8K context Legacy Provider Input Cache Output
Ministral 3 8B Multimodal · 256K context Legacy Provider Input Cache Output
Mistral Small Inference / Multimodal · 256K / , context Legacy Provider Input Cache Output
GPT OSS 120B Inference · , / 66K context Legacy Provider Input Cache Output
Ministral 3 14B Multimodal · 256K context Legacy Provider Input Cache Output
Green Embedding Embedding · , context Legacy Provider Input Cache Output
Llama 3.1 8B Instruct Inference · , context Legacy Provider Input Cache Output
GreenS Speech · , context Legacy Provider Input Cache Output
GreenS Pro Speech · , context Legacy Provider Input Cache Output
Gemma 4 31B Multimodal · , context Legacy Provider Input Cache Output
Codestral 25.08 Inference · 128K context Legacy Provider Input Cache Output
MiniMax M3.1 Multimodal · 1M context Legacy Provider Input Cache Output
MiniMax M3 Multimodal · 1M context Legacy Provider Input Cache Output
Mistral Large Multimodal · 1M context Legacy Provider Input Cache Output
GLM-4.7 FP8 Inference · , context Legacy Provider Input Cache Output
Qwen3 235B Inference · , context Legacy Provider Input Cache Output
Llama 3.3 70B Instruct Inference · , context Legacy Provider Input Cache Output
Llama 3.3 70B Instruct FP8 Inference · 128K context Legacy Provider Input Cache Output
Mistral Medium 3.5 Inference / Multimodal · , / 262K context Legacy Provider Input Cache Output
O3 OCR 3 OCR · , context
Legacy Provider Input Cache Output
LO LightOn OCR 3 0.8B OCR · , context
Legacy Provider Input Cache Output
roc Multimodal · 262K context Legacy Provider Input Cache Output
Faster-Whisper Large v3 Speech · , context Legacy Provider Input Cache Output
NB-Whisper Large Speech · , context Legacy Provider Input Cache Output
O4 OCR 4.1 OCR · , context
Legacy Provider Input Cache Output
Voxtral TTS 3 Speech · , context Legacy Provider Input Cache Output
Pharia-1-Embedding-4608-control Embedding · , context Legacy Provider Input Cache Output
Pharia-1-LLM-7B-control Inference · 8K context Legacy Provider Input Cache Output
Shieldstral 1.0 Moderation · 32K context Legacy Provider Input Cache Output
Timestral 1.0 123M Time series · 32K context Legacy Provider Input Cache Output
Timestral 1.0 209M Time series · 32K context Legacy Provider Input Cache Output
Timestral 1.0 28M Time series · 32K context Legacy Provider Input Cache Output
Timestral 1.0 5M Time series · 32K context Legacy Provider Input Cache Output
No models match. Clear a filter or search another term.
Provider rows show input, cached input, and output prices in the provider's currency. Compare opens only for model families with more than one provider.