💲 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 116openai 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 |
|---|---|---|---|---|---|---|---|---|
| llama-3.2-90bvercel_ai_gateway | — | $0.72 | $0.72 | — | — | — | 128K | |
| glm-4.5💬vercel_ai_gateway | 1430 | $0.60 | $2.20 | — | — | — | 131K | |
| grok-3-mini-fastvercel_ai_gateway | — | $0.60 | $4.00 | — | — | — | 131K | |
| llama-3-70bvercel_ai_gateway | — | $0.59 | $0.79 | — | — | — | 8K | |
| kimi-k2💬vercel_ai_gateway | — | $0.55 | $2.20 | — | — | — | 131K | |
| deepseek-r1🧮vercel_ai_gateway | 1373 | $0.55 | $2.19 | — | — | — | 128K | |
| magistral-smallvercel_ai_gateway | — | $0.50 | $1.50 | — | — | — | 128K | |
| gpt-3.5-turbo💬vercel_ai_gateway | — | $0.50 | $1.50 | — | — | — | 16K | |
| glm-4.6💬vercel_ai_gateway | 1440 | $0.45 | $1.80 | $0.11 | — | — | 200K | |
| gpt-4.1-mini💬vercel_ai_gateway | — | $0.40 | $1.60 | $0.10 | free | — | 1.0M | |
| qwen3-coder💻vercel_ai_gateway | — | $0.40 | $1.60 | — | — | — | 262K | |
| grok-3-minivercel_ai_gateway | — | $0.30 | $0.50 | — | — | — | 131K | |
| codestralvercel_ai_gateway | — | $0.30 | $0.90 | — | — | — | 256K | |
| gemini-2.5-flash💬vercel_ai_gateway | 1417 | $0.30 | $2.50 | $0.0300 | — | — | 1.0M | |
| claude-3-haiku💬vercel_ai_gateway | — | $0.25 | $1.25 | $0.0300 | $0.30 | — | 200K | |
| mercury-coder-smallvercel_ai_gateway | — | $0.25 | $1.00 | — | — | — | 32K | |
| glm-4.5-air💬vercel_ai_gateway | 1384 | $0.20 | $1.10 | — | — | — | 128K | |
| gemma-2-9bvercel_ai_gateway | — | $0.20 | $0.20 | — | — | — | 8K | |
| llama-4-maverick💬vercel_ai_gateway | — | $0.20 | $0.60 | — | — | — | 131K | |
| qwen-3-235bvercel_ai_gateway | — | $0.20 | $0.60 | — | — | — | 41K | |
| llama-3.2-11bvercel_ai_gateway | — | $0.16 | $0.16 | — | — | — | 128K | |
| pixtral-12bvercel_ai_gateway | — | $0.15 | $0.15 | — | — | — | 128K | |
| command-rvercel_ai_gateway | — | $0.15 | $0.60 | — | — | — | 128K | |
| codestral-embedvercel_ai_gateway | — | $0.15 | free | — | — | — | 0 | |
| gpt-4o-mini💬vercel_ai_gateway | — | $0.15 | $0.60 | $0.0750 | free | — | 128K | |
| llama-3.2-3bvercel_ai_gateway | — | $0.15 | $0.15 | — | — | — | 128K | |
| embed-v4.0vercel_ai_gateway | — | $0.12 | free | — | — | — | 0 | |
| qwen-3-32bvercel_ai_gateway | — | $0.10 | $0.30 | — | — | — | 41K | |
| ministral-8b💬vercel_ai_gateway | — | $0.10 | $0.10 | — | — | — | 128K | |
| mistral-smallvercel_ai_gateway | — | $0.10 | $0.30 | — | — | — | 32K | |
| llama-3.2-1bvercel_ai_gateway | — | $0.10 | $0.10 | — | — | — | 128K | |
| gpt-4.1-nano💬vercel_ai_gateway | — | $0.10 | $0.40 | $0.0250 | free | — | 1.0M | |
| mistral-embedvercel_ai_gateway | — | $0.10 | free | — | — | — | 0 | |
| qwen-3-30bvercel_ai_gateway | — | $0.10 | $0.30 | — | — | — | 41K | |
| llama-4-scout💬vercel_ai_gateway | — | $0.10 | $0.30 | — | — | — | 131K | |
| qwen-3-14bvercel_ai_gateway | — | $0.0800 | $0.24 | — | — | — | 41K | |
| devstral-smallvercel_ai_gateway | — | $0.0700 | $0.28 | — | — | — | 128K | |
| nova-litevercel_ai_gateway | — | $0.0600 | $0.24 | — | — | — | 300K | |
| llama-3-8bvercel_ai_gateway | — | $0.0500 | $0.0800 | — | — | — | 8K | |
| llama-3.1-8bvercel_ai_gateway | — | $0.0500 | $0.0800 | — | — | — | 131K | |
| ministral-3bvercel_ai_gateway | — | $0.0400 | $0.0400 | — | — | — | 128K | |
| nova-microvercel_ai_gateway | — | $0.0350 | $0.14 | — | — | — | 128K | |
| titan-embed-text-v2vercel_ai_gateway | — | $0.0200 | free | — | — | — | 0 |
Recent price changes
- ▼ 53.3%Qwen: Qwen3 Coder 30B A3B Instructqwen · output $0.60 → $0.2811h
- ▼ 53.3%Qwen: Qwen3 Coder 30B A3B Instructqwen · input $0.15 → $0.070011h
- ▼ 40.0%Qwen: Qwen3.5-27Bqwen · output $2.60 → $1.5611h
- ▼ 25.0%Qwen: Qwen3.5-27Bqwen · input $0.26 → $0.2011h
- ▼ 5.6%OpenAI: gpt-oss-20bopenai · output $0.0900 → $0.085011h
- ▼ 5.6%OpenAI: gpt-oss-20bopenai · input $0.0180 → $0.017011h
- ▼ 6.0%NVIDIA: Nemotron 3.5 Super VLnvidia · output $0.50 → $0.4711h
- ▲ 114.3%MiniMax: MiniMax M2.7minimax · output $0.84 → $1.8011h
- ▲ 185.7%MiniMax: MiniMax M2.7minimax · input $0.21 → $0.6011h
- ▼ 20.8%MiniMax: MiniMax M2.5minimax · output $1.20 → $0.9511h
- ▼ 8.5%MiniMax: MiniMax M2.5minimax · input $0.29 → $0.2711h
- ▲ 33.3%inclusionAI: Ling 3.1 Flashinclusionai · output $0.14 → $0.1811h
- ▲ 33.3%inclusionAI: Ling 3.1 Flashinclusionai · input $0.0450 → $0.060011h
- ▼ 11.8%Google: Gemma 4 26B A4B google · output $0.26 → $0.2311h
- ▼ 11.8%Google: Gemma 4 26B A4B google · input $0.0765 → $0.067511h
- ▲ 181.3%Google: Gemma 3 27Bgoogle · output $0.16 → $0.4511h
- ▼ 51.0%DeepSeek: DeepSeek V4 Flash Vision Expdeepseek · output $1.32 → $0.6511h
- ▼ 51.0%DeepSeek: DeepSeek V4 Flash Vision Expdeepseek · input $0.44 → $0.2211h
- ▼ 26.7%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.18 → $0.1311h
- ▼ 26.7%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0600 → $0.044011h
Price cuts are green — they make AI cheaper for everyone.