💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 15h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.
All providersreplicate 23vertex_ai 10elevenlabs 10openai 7dashscope 5azure 5gemini 5together_ai 5minimax 4aws_polly 4mistral 4runwayml 3groq 2cartesia 1
| Model | $ / 1K characters | Output $/M |
|---|---|---|
| voxtral-mini-tts-latestmistral | $0.0130 | — |
| voxtral-mini-tts-3mistral | $0.0130 | — |
| voxtral-mini-tts-3-0mistral | $0.0130 | — |
| voxtral-mini-tts-2603mistral | $0.0160 | — |
Recent price changes
- ▼ 53.3%Qwen: Qwen3 Coder 30B A3B Instructqwen · output $0.60 → $0.2810h
- ▼ 53.3%Qwen: Qwen3 Coder 30B A3B Instructqwen · input $0.15 → $0.070010h
- ▼ 40.0%Qwen: Qwen3.5-27Bqwen · output $2.60 → $1.5610h
- ▼ 25.0%Qwen: Qwen3.5-27Bqwen · input $0.26 → $0.2010h
- ▼ 5.6%OpenAI: gpt-oss-20bopenai · output $0.0900 → $0.085010h
- ▼ 5.6%OpenAI: gpt-oss-20bopenai · input $0.0180 → $0.017010h
- ▼ 6.0%NVIDIA: Nemotron 3.5 Super VLnvidia · output $0.50 → $0.4710h
- ▲ 114.3%MiniMax: MiniMax M2.7minimax · output $0.84 → $1.8010h
- ▲ 185.7%MiniMax: MiniMax M2.7minimax · input $0.21 → $0.6010h
- ▼ 20.8%MiniMax: MiniMax M2.5minimax · output $1.20 → $0.9510h
- ▼ 8.5%MiniMax: MiniMax M2.5minimax · input $0.29 → $0.2710h
- ▲ 33.3%inclusionAI: Ling 3.1 Flashinclusionai · output $0.14 → $0.1810h
- ▲ 33.3%inclusionAI: Ling 3.1 Flashinclusionai · input $0.0450 → $0.060010h
- ▼ 11.8%Google: Gemma 4 26B A4B google · output $0.26 → $0.2310h
- ▼ 11.8%Google: Gemma 4 26B A4B google · input $0.0765 → $0.067510h
- ▲ 181.3%Google: Gemma 3 27Bgoogle · output $0.16 → $0.4510h
- ▼ 51.0%DeepSeek: DeepSeek V4 Flash Vision Expdeepseek · output $1.32 → $0.6510h
- ▼ 51.0%DeepSeek: DeepSeek V4 Flash Vision Expdeepseek · input $0.44 → $0.2210h
- ▼ 26.7%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.18 → $0.1310h
- ▼ 26.7%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0600 → $0.044010h
Price cuts are green — they make AI cheaper for everyone.