💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 17h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.
All providersdeepgram 36openai 9azure 6groq 2mistral 2soniox 2assemblyai 2elevenlabs 2fireworks_ai 2vertex_ai 1watsonx 1
| Model | $ / minute | $ / hour |
|---|---|---|
| whisper-1azure | $0.0060 | $0.36 |
| azure-sttazure | $0.0167 | $1.00 |
| gpt-realtime-whisperazure | $0.0170 | $1.02 |
| gpt-4o-mini-transcribeazure | — | — |
| gpt-4o-transcribeazure | — | — |
| gpt-4o-transcribe-diarizeazure | — | — |
Recent price changes
- ▲ 10.0%Mistral: Devstral 2 2512mistralai · output $2.00 → $2.2012h
- ▲ 10.0%Mistral: Devstral 2 2512mistralai · input $0.40 → $0.4412h
- ▲ 33.3%MoonshotAI: Kimi K2.5moonshotai · output $2.25 → $3.0012h
- ▲ 33.3%MoonshotAI: Kimi K2.5moonshotai · input $0.45 → $0.6012h
- ▲ 25.0%MiniMax: MiniMax M2.7minimax · output $0.96 → $1.2012h
- ▲ 25.0%MiniMax: MiniMax M2.7minimax · input $0.24 → $0.3012h
- ▲ 30.4%Z.ai: GLM 5.1z-ai · output $3.04 → $3.9612h
- ▲ 30.4%Z.ai: GLM 5.1z-ai · input $0.97 → $1.2612h
- ▲ 54.4%DeepSeek: DeepSeek V4 Flash 0423deepseek · output $0.11 → $0.1812h
- ▲ 54.4%DeepSeek: DeepSeek V4 Flash 0423deepseek · input $0.0574 → $0.088612h
- ▲ 50.2%DeepSeek: DeepSeek V4 Pro 0423deepseek · output $1.05 → $1.5812h
- ▲ 50.2%DeepSeek: DeepSeek V4 Pro 0423deepseek · input $0.53 → $0.7912h
- ▲ 7.7%MoonshotAI Kimi Latestmoonshotai · output $13.0 → $14.012h
- ▲ 7.7%MoonshotAI Kimi Latestmoonshotai · input $2.60 → $2.8012h
- ▲ 23.2%Z.ai: GLM 5.2z-ai · output $3.04 → $3.7412h
- ▼ 12.5%DeepSeek V4 Flash Latestdeepseek · input $0.0400 → $0.035012h
- ▼ 6.3%DeepSeek V4 Flash Latestdeepseek · output $0.0800 → $0.075012h
- ▼ 5.0%Thinking Machines: Inklingthinkingmachines · input $1.00 → $0.9512h
- ▲ 23.2%Z.ai: GLM 5.2z-ai · input $0.97 → $1.1912h
- ▼ 27.3%DeepSeek V4 Flash Latestdeepseek · input $0.0550 → $0.04001d
Price cuts are green — they make AI cheaper for everyone.