💲 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 providersfireworks_ai 290bedrock 188bedrock_converse 152azure 133openrouter 100vercel_ai_gateway 95openai 93azure_ai 90novita 80deepinfra 68mistral 55gemini 51xai 44databricks 40
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 |
|---|---|---|---|---|---|---|---|---|
| claude-opus-4.1💬vercel_ai_gateway | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| claude-opus-4💬vercel_ai_gateway | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| o1🧮vercel_ai_gateway | — | $15.0 | $60.0 | $7.50 | free | — | 200K | |
| claude-4-opusvercel_ai_gateway | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| claude-3-opusvercel_ai_gateway | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| gpt-4-turbo💬vercel_ai_gateway | — | $10.0 | $30.0 | — | — | — | 128K | |
| grok-3-fastvercel_ai_gateway | — | $5.00 | $25.0 | — | — | — | 131K | |
| claude-opus-4.6💬vercel_ai_gateway | 1497 | $5.00 | $25.0 | $0.50 | $6.25 | — | 200K | |
| claude-opus-4.5💬vercel_ai_gateway | — | $5.00 | $25.0 | $0.50 | $6.25 | — | 200K | |
| claude-3-5-sonnetvercel_ai_gateway | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| claude-3-5-sonnet-20241022vercel_ai_gateway | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| claude-3-7-sonnetvercel_ai_gateway | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| claude-sonnet-4.5💬vercel_ai_gateway | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 1.0M | |
| sonar-pro🔍vercel_ai_gateway | — | $3.00 | $15.0 | — | — | — | 200K | |
| grok-3vercel_ai_gateway | — | $3.00 | $15.0 | — | — | — | 131K | |
| v0-1.5-mdvercel_ai_gateway | — | $3.00 | $15.0 | — | — | — | 128K | |
| grok-4vercel_ai_gateway | — | $3.00 | $15.0 | — | — | — | 256K | |
| v0-1.0-mdvercel_ai_gateway | — | $3.00 | $15.0 | — | — | — | 128K | |
| claude-3.5-sonnetvercel_ai_gateway | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| claude-3.7-sonnetvercel_ai_gateway | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| claude-4-sonnetvercel_ai_gateway | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| claude-sonnet-4💬vercel_ai_gateway | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| gpt-4o💬vercel_ai_gateway | — | $2.50 | $10.0 | $1.25 | free | — | 128K | |
| command-r-plusvercel_ai_gateway | — | $2.50 | $10.0 | — | — | — | 128K | |
| command-a💬vercel_ai_gateway | — | $2.50 | $10.0 | — | — | — | 256K | |
| gemini-2.5-pro💬vercel_ai_gateway | 1457 | $2.50 | $10.0 | — | — | — | 1.0M | |
| grok-2vercel_ai_gateway | — | $2.00 | $10.0 | — | — | — | 131K | |
| magistral-mediumvercel_ai_gateway | — | $2.00 | $5.00 | — | — | — | 128K | |
| grok-2-visionvercel_ai_gateway | — | $2.00 | $10.0 | — | — | — | 33K | |
| mistral-large💬vercel_ai_gateway | — | $2.00 | $6.00 | — | — | — | 32K | |
| sonar-reasoning-pro🔍vercel_ai_gateway | — | $2.00 | $8.00 | — | — | — | 127K | |
| o3🧮vercel_ai_gateway | — | $2.00 | $8.00 | $0.50 | free | — | 200K | |
| gpt-4.1💬vercel_ai_gateway | — | $2.00 | $8.00 | $0.50 | free | — | 1.0M | |
| pixtral-largevercel_ai_gateway | — | $2.00 | $6.00 | — | — | — | 128K | |
| gpt-3.5-turbo-instruct💬vercel_ai_gateway | — | $1.50 | $2.00 | — | — | — | 8K | |
| mixtral-8x22b-instruct💬vercel_ai_gateway | — | $1.20 | $1.20 | — | — | — | 66K | |
| o4-mini💬vercel_ai_gateway | — | $1.10 | $4.40 | $0.28 | free | — | 200K | |
| o3-mini💬vercel_ai_gateway | 1319 | $1.10 | $4.40 | $0.55 | free | — | 200K | |
| sonar-reasoningvercel_ai_gateway | — | $1.00 | $5.00 | — | — | — | 127K | |
| sonar🔍vercel_ai_gateway | — | $1.00 | $1.00 | — | — | — | 127K | |
| claude-haiku-4.5💬vercel_ai_gateway | — | $1.00 | $5.00 | $0.10 | $1.25 | — | 200K | |
| deepseek-v3vercel_ai_gateway | — | $0.90 | $0.90 | — | — | — | 128K | |
| morph-v3-large🖼️vercel_ai_gateway | — | $0.90 | $1.90 | — | — | — | 33K | |
| claude-3.5-haikuvercel_ai_gateway | — | $0.80 | $4.00 | $0.0800 | $1.00 | — | 200K | |
| nova-provercel_ai_gateway | — | $0.80 | $3.20 | — | — | — | 300K | |
| morph-v3-fast🖼️vercel_ai_gateway | — | $0.80 | $1.20 | — | — | — | 33K | |
| mistral-saba-24bvercel_ai_gateway | — | $0.79 | $0.79 | — | — | — | 33K | |
| deepseek-r1-distill-llama-70b🧮vercel_ai_gateway | — | $0.75 | $0.99 | — | — | — | 131K | |
| llama-3.3-70bvercel_ai_gateway | — | $0.72 | $0.72 | — | — | — | 128K | |
| llama-3.1-70bvercel_ai_gateway | — | $0.72 | $0.72 | — | — | — | 128K |
Recent price changes
- ▲ 10.0%Mistral: Devstral 2 2512mistralai · output $2.00 → $2.2011h
- ▲ 10.0%Mistral: Devstral 2 2512mistralai · input $0.40 → $0.4411h
- ▲ 33.3%MoonshotAI: Kimi K2.5moonshotai · output $2.25 → $3.0011h
- ▲ 33.3%MoonshotAI: Kimi K2.5moonshotai · input $0.45 → $0.6011h
- ▲ 25.0%MiniMax: MiniMax M2.7minimax · output $0.96 → $1.2011h
- ▲ 25.0%MiniMax: MiniMax M2.7minimax · input $0.24 → $0.3011h
- ▲ 30.4%Z.ai: GLM 5.1z-ai · output $3.04 → $3.9611h
- ▲ 30.4%Z.ai: GLM 5.1z-ai · input $0.97 → $1.2611h
- ▲ 54.4%DeepSeek: DeepSeek V4 Flash 0423deepseek · output $0.11 → $0.1811h
- ▲ 54.4%DeepSeek: DeepSeek V4 Flash 0423deepseek · input $0.0574 → $0.088611h
- ▲ 50.2%DeepSeek: DeepSeek V4 Pro 0423deepseek · output $1.05 → $1.5811h
- ▲ 50.2%DeepSeek: DeepSeek V4 Pro 0423deepseek · input $0.53 → $0.7911h
- ▲ 7.7%MoonshotAI Kimi Latestmoonshotai · output $13.0 → $14.011h
- ▲ 7.7%MoonshotAI Kimi Latestmoonshotai · input $2.60 → $2.8011h
- ▲ 23.2%Z.ai: GLM 5.2z-ai · output $3.04 → $3.7411h
- ▼ 12.5%DeepSeek V4 Flash Latestdeepseek · input $0.0400 → $0.035011h
- ▼ 6.3%DeepSeek V4 Flash Latestdeepseek · output $0.0800 → $0.075011h
- ▼ 5.0%Thinking Machines: Inklingthinkingmachines · input $1.00 → $0.9511h
- ▲ 23.2%Z.ai: GLM 5.2z-ai · input $0.97 → $1.1911h
- ▼ 27.3%DeepSeek V4 Flash Latestdeepseek · input $0.0550 → $0.04001d
Price cuts are green — they make AI cheaper for everyone.