💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 7h. 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 |
|---|---|---|---|---|---|---|---|---|
| anthropic.claude-mythos-previewbedrock | — | $27.5 | $137.5 | $2.75 | $34.4 | — | 1.0M | |
| ai21.j2-ultra-v1bedrock | — | $18.8 | $18.8 | — | — | — | 8K | |
| eu.anthropic.claude-3-opus-20240229-v1:0bedrock | — | $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 | |
| us.anthropic.claude-3-opus-20240229-v1:0bedrock | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| ai21.j2-mid-v1bedrock | — | $12.5 | $12.5 | — | — | — | 8K | |
| anthropic.claude-fable-5-1bedrock | — | $12.0 | $60.0 | $0.30 | $15.0 | — | 1.0M | |
| anthropic.claude-fable-5-1bedrock | — | $12.0 | $60.0 | $0.30 | $15.0 | — | 1.0M | |
| anthropic.claude-v1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-v2:1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-v1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-v2:1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-v2:1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-v2:1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-v1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-v1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-v2:1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-v1bedrock | — | $8.00 | $24.0 | — | — | — | 100K | |
| anthropic.claude-opus-4-8bedrock | — | $6.00 | $30.0 | $0.60 | $7.50 | — | 1.0M | |
| anthropic.claude-opus-4-8bedrock | — | $6.00 | $30.0 | $0.60 | $7.50 | — | 1.0M | |
| anthropic.claude-opus-5bedrock | — | $6.00 | $30.0 | $0.60 | $7.50 | — | 1.0M | |
| anthropic.claude-opus-5bedrock | — | $6.00 | $30.0 | $0.60 | $7.50 | — | 1.0M | |
| mistral.mistral-large-2402-v1:0bedrock | — | $5.20 | $15.6 | — | — | — | 32K | |
| anthropic.claude-opus-5-5bedrock | — | $4.80 | $24.0 | $0.24 | $6.00 | — | 1.0M | |
| anthropic.claude-opus-5-5bedrock | — | $4.80 | $24.0 | $0.24 | $6.00 | — | 1.0M | |
| meta.llama3-70b-instruct-v1:0bedrock | — | $4.45 | $5.88 | — | — | — | 8K | |
| mistral.mistral-large-2402-v1:0bedrock | — | $4.00 | $12.0 | — | — | — | 32K | |
| mistral.mistral-large-2402-v1:0bedrock | — | $4.00 | $12.0 | — | — | — | 32K | |
| mistral.mistral-large-2402-v1:0bedrock | — | $4.00 | $12.0 | — | — | — | 32K | |
| anthropic.claude-3-7-sonnet-20240620-v1:0bedrock | — | $3.60 | $18.0 | $0.36 | $4.50 | — | 200K | |
| anthropic.claude-sonnet-4-5-20250929-v1:0bedrock | — | $3.60 | $18.0 | $0.36 | $4.50 | — | 200K | |
| anthropic.claude-sonnet-4-5-20250929-v1:0bedrock | — | $3.60 | $18.0 | $0.36 | $4.50 | — | 200K | |
| claude-sonnet-4-5-20250929-v1:0bedrock | — | $3.60 | $18.0 | $0.36 | $4.50 | — | 200K | |
| claude-sonnet-4-5-20250929-v1:0bedrock | — | $3.60 | $18.0 | $0.36 | $4.50 | — | 200K | |
| meta.llama3-70b-instruct-v1:0bedrock | — | $3.45 | $4.55 | — | — | — | 8K | |
| meta.llama3-70b-instruct-v1:0bedrock | — | $3.18 | $4.20 | — | — | — | 8K | |
| meta.llama3-70b-instruct-v1:0bedrock | — | $3.05 | $4.03 | — | — | — | 8K | |
| us.anthropic.claude-3-5-sonnet-20240620-v1:0bedrock | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| us.anthropic.claude-3-5-sonnet-20241022-v2:0bedrock | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| anthropic.claude-3-5-sonnet-20240620-v1:0bedrock | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| claude-sonnet-4-5-20250929-v1:0bedrock | — | $3.00 | $15.0 | $0.30 | $3.75 | $1.50 / $7.50 | 200K | |
| anthropic.claude-3-5-sonnet-20241022-v2:0bedrock | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| anthropic.claude-3-5-sonnet-20240620-v1:0bedrock | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| eu.anthropic.claude-3-5-sonnet-20240620-v1:0bedrock | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| eu.anthropic.claude-3-5-sonnet-20241022-v2:0bedrock | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| eu.anthropic.claude-3-7-sonnet-20250219-v1:0bedrock | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| meta.llama3-70b-instruct-v1:0bedrock | — | $2.86 | $3.78 | — | — | — | 8K | |
| meta.llama3-70b-instruct-v1:0bedrock | — | $2.65 | $3.50 | — | — | — | 8K | |
| meta.llama3-70b-instruct-v1:0bedrock | — | $2.65 | $3.50 | — | — | — | 8K | |
| meta.llama3-70b-instruct-v1:0bedrock | — | $2.65 | $3.50 | — | — | — | 8K |
Recent price changes
- ▲ 66.7%Z.ai: GLM 5z-ai · output $1.92 → $3.202h
- ▲ 66.7%Z.ai: GLM 5z-ai · input $0.60 → $1.002h
- ▼ 6.7%Qwen: Qwen3.5-35B-A3Bqwen · input $0.15 → $0.142h
- ▼ 13.3%Qwen: Qwen3.5-9Bqwen · output $0.15 → $0.132h
- ▼ 20.0%Qwen: Qwen3.5-9Bqwen · input $0.10 → $0.08002h
- ▲ 433.3%NVIDIA: Nemotron 3 Supernvidia · output $0.45 → $2.402h
- ▲ 275.0%NVIDIA: Nemotron 3 Supernvidia · input $0.0800 → $0.302h
- ▲ 44.9%Z.ai: GLM 5.1z-ai · output $3.04 → $4.402h
- ▲ 44.9%Z.ai: GLM 5.1z-ai · input $0.97 → $1.402h
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · output $0.28 → $0.242h
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · input $0.14 → $0.122h
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · output $0.87 → $0.612h
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · input $0.43 → $0.302h
- ▲ 189.3%Z.ai: GLM 5.2z-ai · output $2.42 → $7.002h
- ▼ 94.5%Z.ai: GLM 5.2z-ai · input $0.62 → $0.03412h
- ▲ 17.3%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.45 → $0.532h
- ▲ 84.2%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0114 → $0.02102h
- ▼ 38.6%Qwen: Qwen3.8 27Bqwen · output $2.20 → $1.352h
- ▼ 83.3%Qwen: Qwen3.8 27Bqwen · input $0.24 → $0.04002h
- ▲ 212.5%Z.ai: GLM 5.3 Flashz-ai · output $0.16 → $0.502h
Price cuts are green — they make AI cheaper for everyone.