💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 5h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.
All providersfireworks_ai 311bedrock_converse 231bedrock 206azure 198deepinfra 136novita 130azure_ai 116openai 97vercel_ai_gateway 93together_ai 87aihubmix 72nebius 58databricks 52mistral 49
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 |
|---|---|---|---|---|---|---|---|---|
| jais-13b-chatwatsonx | — | $500.0 | $2000.0 | — | — | — | 8K | |
| gpt-4.5-previewazure | — | $75.0 | $150.0 | $37.5 | — | $37.5 / $75.0 | 128K | |
| gpt-4-32kazure | — | $60.0 | $120.0 | — | — | — | 33K | |
| gpt-4-32k-0613azure | — | $60.0 | $120.0 | — | — | — | 33K | |
| gpt-4💬azure | — | $30.0 | $60.0 | — | — | — | 8K | |
| gpt-4-0613azure | — | $30.0 | $60.0 | — | — | — | 8K | |
| gpt-4💬openai | — | $30.0 | $60.0 | — | — | — | 8K | |
| ft:gpt-4-0613openai | — | $30.0 | $60.0 | — | — | — | 8K | |
| gpt-4-0613openai | — | $30.0 | $60.0 | — | — | $15.0 / $30.0 | 8K | |
| gpt-5.5-pro💬aihubmix | — | $30.0 | $180.0 | — | — | — | 1.1M | |
| au.anthropic.claude-mythos-previewbedrock_converse | — | $27.5 | $137.5 | $2.75 | $34.4 | — | 1.0M | |
| apac.anthropic.claude-mythos-previewbedrock_converse | — | $27.5 | $137.5 | $2.75 | $34.4 | — | 1.0M | |
| anthropic.claude-mythos-previewbedrock | — | $27.5 | $137.5 | $2.75 | $34.4 | — | 1.0M | |
| us.anthropic.claude-mythos-previewbedrock_converse | — | $27.5 | $137.5 | $2.75 | $34.4 | — | 1.0M | |
| ai21.j2-ultra-v1bedrock | — | $18.8 | $18.8 | — | — | — | 8K | |
| o1-previewazure | — | $16.5 | $66.0 | $8.25 | — | — | 128K | |
| o1-2024-12-17azure | — | $16.5 | $66.0 | $8.25 | — | $8.25 / $33.0 | 200K | |
| claude-4-opusdeepinfra | — | $16.5 | $82.5 | — | — | — | 200K | |
| o1-2024-12-17azure | — | $16.5 | $66.0 | $8.25 | — | $8.25 / $33.0 | 200K | |
| o1-previewazure | — | $16.5 | $66.0 | $8.25 | — | — | 128K | |
| o1🧮azure | — | $16.5 | $66.0 | $8.25 | — | $8.25 / $33.0 | 200K | — |
| o1🧮azure | — | $16.5 | $66.0 | $8.25 | — | $8.25 / $33.0 | 200K | — |
| databricks-claude-opus-4-1databricks | — | $15.0 | $75.0 | $1.50 | $18.7 | — | 200K | |
| databricks-claude-opus-4databricks | — | $15.0 | $75.0 | $1.50 | $18.7 | — | 200K | |
| us.anthropic.claude-opus-4-1-20250805-v1:0bedrock_converse | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| o1-2024-12-17openai | — | $15.0 | $60.0 | $7.50 | — | $7.50 / $30.0 | 200K | |
| o1🧮openai | — | $15.0 | $60.0 | $7.50 | — | $7.50 / $30.0 | 200K | |
| claude-3-opusvercel_ai_gateway | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| us.anthropic.claude-3-opus-20240229-v1:0bedrock | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| o1🧮replicate | — | $15.0 | $60.0 | — | — | — | — | |
| claude-opus-4💬gmi | — | $15.0 | $75.0 | — | — | — | 410K | |
| anthropic-claude-3-opusgradient_ai | — | $15.0 | $75.0 | — | — | — | 200K | |
| claude-3-opus@20240229vertex_ai-anthropic_models | — | $15.0 | $75.0 | — | — | — | 200K | |
| o1-2024-12-17azure | — | $15.0 | $60.0 | $7.50 | — | $7.50 / $30.0 | 200K | |
| o1🧮azure | — | $15.0 | $60.0 | $7.50 | — | — | 200K | |
| us.anthropic.claude-opus-4-20250514-v1:0bedrock_converse | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| o1🧮vercel_ai_gateway | — | $15.0 | $60.0 | $7.50 | free | — | 200K | |
| eu.anthropic.claude-3-opus-20240229-v1:0bedrock | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| eu.anthropic.claude-opus-4-1-20250805-v1:0bedrock_converse | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| anthropic.claude-opus-4-20250514-v1:0bedrock_converse | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| anthropic.claude-opus-4-1-20250805-v1:0bedrock_converse | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| claude-opus-4💬vercel_ai_gateway | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| eu.anthropic.claude-opus-4-20250514-v1:0bedrock_converse | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| anthropic.claude-3-opus-20240229-v1:0bedrock | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| v0-1.5-lgv0 | — | $15.0 | $75.0 | — | — | — | 512K | |
| claude-4-opusvercel_ai_gateway | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| claude-opus-4.1💬vercel_ai_gateway | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| claude-3-opusvertex_ai-anthropic_models | — | $15.0 | $75.0 | — | — | — | 200K | |
| gpt-5.5-cyberopenai | — | $12.5 | $75.0 | $1.25 | — | — | — | |
| daybreak-red-latestopenai | — | $12.5 | $75.0 | $1.25 | $15.6 | — | 400K |
Recent price changes
- ▲ 66.7%Z.ai: GLM 5z-ai · output $1.92 → $3.2038m
- ▲ 66.7%Z.ai: GLM 5z-ai · input $0.60 → $1.0038m
- ▼ 6.7%Qwen: Qwen3.5-35B-A3Bqwen · input $0.15 → $0.1438m
- ▼ 13.3%Qwen: Qwen3.5-9Bqwen · output $0.15 → $0.1338m
- ▼ 20.0%Qwen: Qwen3.5-9Bqwen · input $0.10 → $0.080038m
- ▲ 433.3%NVIDIA: Nemotron 3 Supernvidia · output $0.45 → $2.4038m
- ▲ 275.0%NVIDIA: Nemotron 3 Supernvidia · input $0.0800 → $0.3038m
- ▲ 44.9%Z.ai: GLM 5.1z-ai · output $3.04 → $4.4038m
- ▲ 44.9%Z.ai: GLM 5.1z-ai · input $0.97 → $1.4038m
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · output $0.28 → $0.2438m
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · input $0.14 → $0.1238m
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · output $0.87 → $0.6138m
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · input $0.43 → $0.3038m
- ▲ 189.3%Z.ai: GLM 5.2z-ai · output $2.42 → $7.0038m
- ▼ 94.5%Z.ai: GLM 5.2z-ai · input $0.62 → $0.034138m
- ▲ 17.3%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.45 → $0.5338m
- ▲ 84.2%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0114 → $0.021038m
- ▼ 38.6%Qwen: Qwen3.8 27Bqwen · output $2.20 → $1.3538m
- ▼ 83.3%Qwen: Qwen3.8 27Bqwen · input $0.24 → $0.040038m
- ▲ 212.5%Z.ai: GLM 5.3 Flashz-ai · output $0.16 → $0.5038m
Price cuts are green — they make AI cheaper for everyone.