💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 8h. 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 |
|---|---|---|---|---|---|---|---|---|
| daybreak-red-latestopenai | — | $12.5 | $75.0 | $1.25 | $15.6 | — | 400K | |
| gpt-5.5-cyber-previewopenai | — | $12.5 | $75.0 | $1.25 | — | — | — | |
| ai21.j2-mid-v1bedrock | — | $12.5 | $12.5 | — | — | — | 8K | |
| us-gov.anthropic.claude-fable-5-1bedrock_converse | — | $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-fable-5-1bedrock | — | $12.0 | $60.0 | $0.30 | $15.0 | — | 1.0M | |
| gpt-6-astra💬azure | — | $12.0 | $60.0 | $1.20 | $15.0 | — | 922K | |
| o3-deep-research🔍azure | — | $11.0 | $44.0 | $2.75 | — | — | — | |
| eu.anthropic.claude-fable-5-1bedrock_converse | — | $11.0 | $55.0 | $0.28 | $13.8 | — | 1.0M | |
| eu.anthropic.claude-fable-5bedrock_converse | — | $11.0 | $55.0 | $1.10 | $13.8 | — | 1.0M | |
| us.anthropic.claude-fable-5-1bedrock_converse | — | $11.0 | $55.0 | $0.28 | $13.8 | — | 1.0M | |
| claude-fable-5💬aihubmix | 1493 | $11.0 | $55.0 | $1.10 | $13.8 | — | 1.0M | |
| us.anthropic.claude-fable-5bedrock_converse | — | $11.0 | $55.0 | $1.10 | $13.8 | — | 1.0M | |
| o3-deep-research🔍azure | — | $11.0 | $44.0 | $2.75 | — | — | — | |
| gpt-4-turbo💬azure | — | $11.0 | $33.0 | — | — | — | 128K | |
| gpt-6-astra💬azure | — | $11.0 | $55.0 | $1.10 | $13.8 | — | 922K | |
| us.openai.gpt-6-astrabedrock_converse | — | $11.0 | $55.0 | $1.10 | $13.8 | — | 1.1M | |
| gpt-4-turbo-2024-04-09azure | — | $11.0 | $33.0 | — | — | — | 128K | |
| gpt-4-turbo-vision-previewazure | — | $11.0 | $33.0 | — | — | — | 128K | |
| us.anthropic.claude-mythos-5bedrock_converse | — | $11.0 | $55.0 | $1.10 | $13.8 | — | 1.0M | |
| apac.anthropic.claude-fable-5bedrock_converse | — | $11.0 | $55.0 | $1.10 | $13.8 | — | 1.0M | |
| us.anthropic.claude-mythos-5-1bedrock_converse | — | $11.0 | $55.0 | $0.28 | $13.8 | — | 1.0M | |
| au.anthropic.claude-fable-5bedrock_converse | — | $11.0 | $55.0 | $1.10 | $13.8 | — | 1.0M | |
| meta.llama-3.1-405b-instructoci | — | $10.7 | $10.7 | — | — | — | 128K | |
| databricks-claude-fable-5databricks | — | $10.0 | $50.0 | $1.00 | $12.5 | — | 1.0M | |
| databricks-claude-fable-5-1databricks | — | $10.0 | $50.0 | $0.25 | $12.5 | — | 1.0M | |
| gpt-6-astra💬azure | — | $10.0 | $50.0 | $1.00 | $12.5 | — | 922K | |
| gpt-4-turbo💬openai | — | $10.0 | $30.0 | — | — | — | 128K | |
| gpt-4-1106-previewopenai | — | $10.0 | $30.0 | — | — | — | 128K | |
| gpt-4-turbo-2024-04-09openai | — | $10.0 | $30.0 | — | — | $5.00 / $15.0 | 128K | |
| claude-fable-5-1@defaultvertex_ai-anthropic_models | — | $10.0 | $50.0 | $0.25 | $12.5 | $5.00 / $25.0 | 1.0M | |
| global.anthropic.claude-fable-5-1bedrock_converse | — | $10.0 | $50.0 | $0.25 | $12.5 | — | 1.0M | |
| claude-fable-5-1💬azure_ai | — | $10.0 | $50.0 | $0.25 | $12.5 | — | 1.0M | |
| global.anthropic.claude-fable-5bedrock_converse | — | $10.0 | $50.0 | $1.00 | $12.5 | — | 1.0M | |
| anthropic.claude-fable-5-1bedrock_converse | — | $10.0 | $50.0 | $0.25 | $12.5 | — | 1.0M | |
| gpt-6-astra-2026-09-03azure | — | $10.0 | $50.0 | $1.00 | $12.5 | — | 922K | |
| gpt-6-astra💬azure_ai | — | $10.0 | $50.0 | $1.00 | $12.5 | — | 922K | |
| claude-fable-5💬vertex_ai-anthropic_models | 1493 | $10.0 | $50.0 | $1.00 | $12.5 | $5.00 / $25.0 | 1.0M | |
| gpt-6-astra💬openai | — | $10.0 | $50.0 | $1.00 | $12.5 | $5.00 / $25.0 | 922K | |
| claude-fable-5-1💬vertex_ai-anthropic_models | — | $10.0 | $50.0 | $0.25 | $12.5 | $5.00 / $25.0 | 1.0M | |
| claude-fable-5@defaultvertex_ai-anthropic_models | — | $10.0 | $50.0 | $1.00 | $12.5 | $5.00 / $25.0 | 1.0M | |
| claude-fable-5.1💬github_copilot | — | $10.0 | $50.0 | $0.25 | $12.5 | — | 200K | |
| claude-fable-5💬github_copilot | 1493 | $10.0 | $50.0 | $1.00 | $12.5 | — | 200K | |
| claude-fable-5💬deepinfra | 1493 | $10.0 | $50.0 | — | — | — | 1.0M | |
| gpt-4-turbo💬vercel_ai_gateway | — | $10.0 | $30.0 | — | — | — | 128K | |
| claude-opus-4.8-fast💬github_copilot | — | $10.0 | $50.0 | $1.00 | $12.5 | — | 200K | |
| claude-mythos-previewanthropic | — | $10.0 | $50.0 | $1.00 | $12.5 | — | 1.0M | |
| gpt-4-1106-previewazure | — | $10.0 | $30.0 | — | — | — | 128K | |
| anthropic.claude-fable-5bedrock_converse | — | $10.0 | $50.0 | $1.00 | $12.5 | — | 1.0M | |
| gpt-4-0125-previewazure | — | $10.0 | $30.0 | — | — | — | 128K |
Recent price changes
- ▲ 53.9%Qwen: Qwen3.5 397B A17Bqwen · output $2.34 → $3.603h
- ▲ 28.2%Qwen: Qwen3.5 397B A17Bqwen · input $0.39 → $0.503h
- ▲ 53.9%Qwen: Qwen3.5-122B-A10Bqwen · output $2.08 → $3.203h
- ▲ 53.9%Qwen: Qwen3.5-122B-A10Bqwen · input $0.26 → $0.403h
- ▲ 50.0%MoonshotAI: Kimi Latestmoonshotai · output $16.0 → $24.03h
- ▼ 70.3%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.53 → $0.163h
- ▲ 126.2%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0210 → $0.04753h
- ▼ 71.1%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.143h
- ▼ 90.3%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.01463h
- ▼ 61.5%Z.ai: GLM Flash Latestz-ai · output $0.38 → $0.143h
- ▼ 71.8%Z.ai: GLM Flash Latestz-ai · input $0.0517 → $0.01463h
- ▲ 220.0%DeepSeek: DeepSeek V4.1 Flashdeepseek · output $0.38 → $1.203h
- ▲ 512.2%DeepSeek: DeepSeek V4.1 Flashdeepseek · input $0.0490 → $0.303h
- ▼ 0.7%DeepSeek: DeepSeek Pro Latestdeepseek · input $0.23 → $0.223h
- ▲ 66.7%Z.ai: GLM 5z-ai · output $1.92 → $3.201d
- ▲ 66.7%Z.ai: GLM 5z-ai · input $0.60 → $1.001d
- ▼ 6.7%Qwen: Qwen3.5-35B-A3Bqwen · input $0.15 → $0.141d
- ▼ 13.3%Qwen: Qwen3.5-9Bqwen · output $0.15 → $0.131d
- ▼ 20.0%Qwen: Qwen3.5-9Bqwen · input $0.10 → $0.08001d
- ▲ 433.3%NVIDIA: Nemotron 3 Supernvidia · output $0.45 → $2.401d
Price cuts are green — they make AI cheaper for everyone.