💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 16h. 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 |
|---|---|---|---|---|---|---|---|---|
| mythomax-l2-13b💬novita | — | $0.0900 | $0.0900 | — | — | — | 4K | |
| qwen3-235b-a22b-instruct-2507novita | — | $0.0900 | $0.58 | — | — | — | 131K | |
| qwen3-30b-a3b-fp8novita | — | $0.0900 | $0.45 | — | — | — | 41K | |
| qwen3-vl-8b-instruct👁️novita | — | $0.0800 | $0.50 | — | — | — | 131K | |
| baichuan-m2-32bnovita | — | $0.0700 | $0.0700 | — | — | — | 131K | |
| glm-4.7-flash💬novita | 1351 | $0.0700 | $0.40 | $0.0100 | — | — | 200K | |
| ernie-4.5-21B-a3b-thinkingnovita | — | $0.0700 | $0.28 | — | — | — | 131K | |
| qwen2.5-7b-instructnovita | — | $0.0700 | $0.0700 | — | — | — | 32K | |
| ernie-4.5-21B-a3bnovita | — | $0.0700 | $0.28 | — | — | — | 120K | |
| qwen3-coder-30b-a3b-instruct💻novita | — | $0.0700 | $0.27 | — | — | — | 160K | |
| deepseek-r1-0528-qwen3-8bnovita | — | $0.0600 | $0.0900 | — | — | — | 128K | |
| ling-3.0-flash💬novita | — | $0.0600 | $0.18 | $0.0120 | — | — | 262K | |
| ling-3.0-flash-fastnovita | — | $0.0600 | $0.18 | $0.0120 | — | — | 262K | |
| gpt-oss-120b💬novita | 1366 | $0.0500 | $0.25 | — | — | — | 131K | |
| l3-8b-lunarisnovita | — | $0.0500 | $0.0500 | — | — | — | 8K | |
| nemotron-3-nano-30b-a3b💬novita | — | $0.0500 | $0.20 | — | — | — | 262K | |
| gemma-3-12b-it💬novita | 1334 | $0.0500 | $0.10 | — | — | — | 131K | |
| L3-8B-Stheno-v3.2novita | — | $0.0500 | $0.0500 | — | — | — | 8K | |
| llama-3-8b-instruct💬novita | 1166 | $0.0400 | $0.0400 | — | — | — | 8K | |
| mistral-nemo💬novita | — | $0.0400 | $0.17 | — | — | — | 60K | |
| gpt-oss-20b💬novita | 1288 | $0.0400 | $0.15 | — | — | — | 131K | |
| qwen3-8b-fp8novita | — | $0.0350 | $0.14 | — | — | — | 128K | |
| autoglm-phone-9b-multilingualnovita | — | $0.0350 | $0.14 | — | — | — | 66K | |
| deepseek-ocrnovita | — | $0.0300 | $0.0300 | — | — | — | 8K | |
| llama-3.2-3b-instruct💬novita | 1110 | $0.0300 | $0.0500 | — | — | — | 33K | |
| qwen3-4b-fp8novita | — | $0.0300 | $0.0300 | — | — | — | 128K | |
| deepseek-ocr-2novita | — | $0.0300 | $0.0300 | — | — | — | 8K | |
| llama-3.1-8b-instruct💬novita | 1187 | $0.0200 | $0.0500 | — | — | — | 16K | |
| llama-3.2-1b-instruct💬novita | 1055 | $0.0200 | $0.0200 | — | — | — | 131K | |
| paddleocr-vlnovita | — | $0.0200 | $0.0200 | — | — | — | 16K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068011h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023011h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078411h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039911h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4211h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6211h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6011h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2611h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070011h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3611h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090011h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1811h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0011h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3311h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050011h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9611h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3211h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1811h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060011h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2311h
Price cuts are green — they make AI cheaper for everyone.