💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 10h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.
All providersvertex_ai 10openai 7gemini 5azure 5aws_polly 4minimax 4elevenlabs 3mistral 2groq 2cartesia 1runwayml 1
| Model | $ / 1K characters | Output $/M |
|---|---|---|
| gpt-4o-mini-ttsazure | — | $10.0 |
| gpt-4o-mini-ttsopenai | — | $10.0 |
| gpt-4o-mini-tts-2025-03-20openai | — | $10.0 |
| gpt-4o-mini-tts-2025-12-15openai | — | $10.0 |
| eleven_multilingual_v2runwayml | $0.0003 | — |
| standardaws_polly | $0.0040 | — |
| tts-1openai | $0.0150 | — |
| azure-ttsazure | $0.0150 | — |
| tts-1azure | $0.0150 | — |
| tts-1-1106openai | $0.0150 | — |
| neuralaws_polly | $0.0160 | — |
| voxtral-mini-tts-2603mistral | $0.0160 | — |
| voxtral-mini-tts-latestmistral | $0.0160 | — |
| orpheus-v1-englishgroq | $0.0220 | — |
| chirpvertex_ai | $0.0300 | — |
| azure-tts-hdazure | $0.0300 | — |
| tts-1-hd-1106openai | $0.0300 | — |
| tts-1-hdopenai | $0.0300 | — |
| generativeaws_polly | $0.0300 | — |
| tts-1-hdazure | $0.0330 | — |
| orpheus-arabic-saudigroq | $0.0400 | — |
| lyria-3-clip-preview🎙️vertex_ai | — | free |
| Cartesia Sonic 2cartesia | $0.0500 | — |
| speech-02-turbominimax | $0.0600 | — |
| speech-2.6-turbominimax | $0.0600 | — |
| lyria-002vertex_ai | — | — |
| lyria-3-pro-preview🎙️vertex_ai | — | free |
| long-formaws_polly | $0.10 | — |
| speech-02-hdminimax | $0.10 | — |
| speech-2.6-hdminimax | $0.10 | — |
| ElevenLabs Multilingual v2 (Business tier)elevenlabs | $0.12 | — |
| eleven_multilingual_v2elevenlabs | $0.18 | — |
| eleven_v3elevenlabs | $0.18 | — |
| gemini-3.8-flash-ttsgemini | — | $9.00 |
| gemini-2.5-flash-preview-ttsgemini | — | $10.0 |
| gemini-2.5-flash-preview-ttsgemini | — | $10.0 |
| gemini-2.5-flash-preview-ttsvertex_ai | — | $10.0 |
| gemini-3.8-flash-ttsvertex_ai | — | $9.00 |
| gemini-3.8-flash-lite-ttsvertex_ai | — | $6.00 |
| gemini-3.8-flash-lite-ttsgemini | — | $6.00 |
| gemini-2.5-flash-ttsvertex_ai | — | $10.0 |
| gemini-3.1-flash-tts-previewvertex_ai | — | $20.0 |
| gemini-3.1-flash-tts-previewgemini | — | $20.0 |
| gemini-2.5-pro-ttsvertex_ai | — | $20.0 |
Recent price changes
- ▲ 66.7%Z.ai: GLM 5z-ai · output $1.92 → $3.205h
- ▲ 66.7%Z.ai: GLM 5z-ai · input $0.60 → $1.005h
- ▼ 6.7%Qwen: Qwen3.5-35B-A3Bqwen · input $0.15 → $0.145h
- ▼ 13.3%Qwen: Qwen3.5-9Bqwen · output $0.15 → $0.135h
- ▼ 20.0%Qwen: Qwen3.5-9Bqwen · input $0.10 → $0.08005h
- ▲ 433.3%NVIDIA: Nemotron 3 Supernvidia · output $0.45 → $2.405h
- ▲ 275.0%NVIDIA: Nemotron 3 Supernvidia · input $0.0800 → $0.305h
- ▲ 44.9%Z.ai: GLM 5.1z-ai · output $3.04 → $4.405h
- ▲ 44.9%Z.ai: GLM 5.1z-ai · input $0.97 → $1.405h
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · output $0.28 → $0.245h
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · input $0.14 → $0.125h
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · output $0.87 → $0.615h
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · input $0.43 → $0.305h
- ▲ 189.3%Z.ai: GLM 5.2z-ai · output $2.42 → $7.005h
- ▼ 94.5%Z.ai: GLM 5.2z-ai · input $0.62 → $0.03415h
- ▲ 17.3%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.45 → $0.535h
- ▲ 84.2%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0114 → $0.02105h
- ▼ 38.6%Qwen: Qwen3.8 27Bqwen · output $2.20 → $1.355h
- ▼ 83.3%Qwen: Qwen3.8 27Bqwen · input $0.24 → $0.04005h
- ▲ 212.5%Z.ai: GLM 5.3 Flashz-ai · output $0.16 → $0.505h
Price cuts are green — they make AI cheaper for everyone.