💲 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 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 |
|---|---|---|---|---|---|---|---|---|
| isaac-0.1replicate | — | $0.26 | $2.17 | — | — | — | — | |
| llama-4-maverick-instructreplicate | — | $0.25 | $0.95 | — | — | — | — | |
| gpt-5-mini💬replicate | — | $0.25 | $2.00 | — | — | — | — | |
| llama-guard-4-12b🛡️replicate | — | $0.20 | $0.20 | — | — | — | — | |
| gpt-oss-120b💬replicate | 1366 | $0.18 | $0.72 | — | — | — | — | |
| llama-4-scout-instructreplicate | — | $0.17 | $0.65 | — | — | — | — | |
| gpt-4o-mini💬replicate | — | $0.15 | $0.60 | — | — | — | — | |
| llama-2-13b-chatreplicate | — | $0.10 | $0.50 | — | — | — | 4K | |
| llama-2-13breplicate | — | $0.10 | $0.50 | — | — | — | 4K | |
| gpt-4.1-nano💬replicate | — | $0.10 | $0.40 | — | — | — | — | |
| granite-20b-code-instruct-8kreplicate | — | $0.10 | $0.50 | — | — | — | — | |
| gpt-oss-20b💬replicate | 1288 | $0.0900 | $0.36 | — | — | — | — | |
| granite-vision-4.1-4breplicate | — | $0.0600 | $0.25 | — | — | — | — | |
| granite-4.1-8b💬replicate | 1291 | $0.0600 | $0.25 | — | — | — | — | |
| granite-4.0-h-smallreplicate | — | $0.0600 | $0.25 | — | — | — | — | |
| granite-4.2-8b💬replicate | 1319 | $0.0600 | $0.25 | — | — | — | — | |
| mistral-7b-instruct-v0.2replicate | — | $0.0500 | $0.25 | — | — | — | 4K | |
| llama-3-8b-instruct💬replicate | 1166 | $0.0500 | $0.25 | — | — | — | 8K | |
| granite-3.0-8b-instructreplicate | — | $0.0500 | $0.25 | — | — | — | — | |
| granite-8b-code-instruct-128kreplicate | — | $0.0500 | $0.25 | — | — | — | — | |
| llama-3-8breplicate | — | $0.0500 | $0.25 | — | — | — | 8K | |
| mistral-7b-v0.1replicate | — | $0.0500 | $0.25 | — | — | — | 4K | |
| meta-llama-3-8breplicate | — | $0.0500 | $0.25 | — | — | — | — | |
| meta-llama-3-8b-instructreplicate | — | $0.0500 | $0.25 | — | — | — | — | |
| llama-2-7b-chatreplicate | — | $0.0500 | $0.25 | — | — | — | 4K | |
| llama-2-7breplicate | — | $0.0500 | $0.25 | — | — | — | 4K | |
| gpt-5-nano💬replicate | — | $0.0500 | $0.40 | — | — | — | — | |
| granite-3.0-2b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| granite-3.2-8b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| granite-3.1-8b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| granite-3.1-2b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| granite-3.3-8b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| granite-vision-3.3-2breplicate | — | free | $0.25 | — | — | — | — |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.06805h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.02305h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.07845h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.03995h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.425h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.625h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.605h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.265h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.07005h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.365h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.09005h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.185h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.005h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.335h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.05005h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.965h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.325h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.185h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.06005h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.235h
Price cuts are green — they make AI cheaper for everyone.