💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 22h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.
All providersbedrock_converse 599bedrock_mantle 419fireworks_ai 328bedrock 275azure 211deepinfra 140novita 130gmi 122azure_ai 110openai 104vercel_ai_gateway 93empiriolabs 92kyma 83replicate 83
Cost calculator — what would your workload cost on each model?
| Model | Elo | Input $/M | Output $/M | Cache read | Cache write | Batch in/out | Context | History |
|---|---|---|---|---|---|---|---|---|
| Olmo-3-32B-Think🧮publicai | 1299 | free | free | — | — | — | 33K | |
| Gemma-SEA-LION-v4-27B-ITpublicai | — | free | free | — | — | — | 8K | |
| llama3-8b-instruct-maasvertex_ai-llama_models | — | free | free | — | — | — | 32K | |
| labs-leanstral-1-5-1mistral | — | free | free | — | — | — | 262K | |
| lyria-3-pro-preview🎙️gemini | — | free | free | — | — | — | 131K | |
| codestral-2405codestral | — | free | free | — | — | — | 32K | |
| llama3:8bollama | — | free | free | — | — | — | 8K | |
| llama3-70b-instruct-maasvertex_ai-llama_models | — | free | free | — | — | — | 32K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068017h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023017h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078417h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039917h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4217h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6217h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6017h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2617h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070017h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3617h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090017h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1817h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0017h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3317h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050017h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9617h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3217h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1817h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060017h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2317h
Price cuts are green — they make AI cheaper for everyone.