💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 20h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.
All providersopenai 7azure 5aws_polly 4minimax 4groq 3elevenlabs 3gemini 3cartesia 1runwayml 1vertex_ai 1
| Model | $ / 1K characters | Output $/M |
|---|---|---|
| gemini-2.5-flash-preview-ttsgemini | — | $2.50 |
| gemini-2.5-flash-preview-ttsgemini | — | $2.50 |
| gemini-3.1-flash-tts-previewgemini | — | $20.0 |
Recent price changes
- ▲ 121.9%Meta: Llama 3.3 70B Instructmeta-llama · output $0.32 → $0.7115h
- ▲ 610.0%Meta: Llama 3.3 70B Instructmeta-llama · input $0.10 → $0.7115h
- ▼ 25.0%Qwen: Qwen2.5 VL 72B Instructqwen · output $1.00 → $0.7515h
- ▼ 68.8%Qwen: Qwen2.5 VL 72B Instructqwen · input $0.80 → $0.2515h
- ▲ 13.3%Meta: Llama 4 Scoutmeta-llama · output $0.30 → $0.3415h
- ▲ 10.0%Meta: Llama 4 Scoutmeta-llama · input $0.10 → $0.1115h
- ▼ 35.0%Qwen: Qwen3.5 397B A17Bqwen · output $3.60 → $2.3415h
- ▼ 22.0%Qwen: Qwen3.5 397B A17Bqwen · input $0.50 → $0.3915h
- ▼ 10.0%Google: Gemma 4 31Bgoogle · input $0.10 → $0.090015h
- ▲ 10.1%DeepSeek: DeepSeek V4 Pro 0423deepseek · output $1.58 → $1.7415h
- ▲ 10.1%DeepSeek: DeepSeek V4 Pro 0423deepseek · input $0.79 → $0.8715h
- ▼ 8.9%MoonshotAI Kimi Latestmoonshotai · output $14.0 → $12.815h
- ▼ 8.9%MoonshotAI Kimi Latestmoonshotai · input $2.80 → $2.5515h
- ▼ 57.1%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.28 → $0.1215h
- ▼ 57.1%DeepSeek: DeepSeek V4 Flash 0731deepseek · input $0.14 → $0.060015h
- ▼ 14.3%DeepSeek V4 Flash Latestdeepseek · input $0.0350 → $0.030015h
- ▼ 15.0%Qwen: Qwen3.8 27Bqwen · output $3.00 → $2.5515h
- ▲ 6.3%Qwen: Qwen3.8 27Bqwen · input $0.40 → $0.4215h
- ▲ 18.2%Llama-3.3-70B-Instruct-Turbotogether_ai · output $0.88 → $1.0415h
- ▲ 18.2%Llama-3.3-70B-Instruct-Turbotogether_ai · input $0.88 → $1.0415h
Price cuts are green — they make AI cheaper for everyone.