💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 9h. 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 |
|---|---|---|---|---|---|---|---|---|
| command-r-plusazure | — | $3.00 | $15.0 | — | — | — | 128K | |
| computer-use-previewazure | — | $3.00 | $12.0 | — | — | — | 8K | |
| gpt-35-turbo-16kazure | — | $3.00 | $4.00 | — | — | — | 16K | |
| gpt-35-turbo-16k-0613azure | — | $3.00 | $4.00 | — | — | — | 16K | |
| gpt-4o-2024-11-20💬azure | — | $2.75 | $11.0 | $1.38 | $1.38 | $1.38 / $5.50 | 128K | |
| gpt-4o💬azure | — | $2.75 | $11.0 | $1.38 | $1.38 | $1.38 / $5.50 | 128K | — |
| gpt-4o-2024-11-20💬azure | — | $2.75 | $11.0 | $1.38 | $1.38 | $1.38 / $5.50 | 128K | |
| gpt-5.4-2026-03-05azure | — | $2.75 | $16.5 | $0.28 | — | $1.38 / $8.25 | 922K | |
| gpt-4o-2024-08-06💬azure | 1283 | $2.75 | $11.0 | $1.38 | — | $1.38 / $5.50 | 128K | |
| gpt-4o-2024-08-06💬azure | 1283 | $2.75 | $11.0 | $1.38 | — | $1.38 / $5.50 | 128K | |
| gpt-5.4💬azure | 1452 | $2.75 | $16.5 | $0.28 | — | $1.38 / $8.25 | 922K | |
| gpt-4o💬azure | — | $2.75 | $11.0 | $1.38 | $1.38 | $1.38 / $5.50 | 128K | — |
| gpt-5.4-2026-03-05azure | — | $2.75 | $16.5 | $0.28 | — | $1.38 / $8.25 | 922K | |
| gpt-5.4💬azure | 1452 | $2.75 | $16.5 | $0.28 | — | $1.38 / $8.25 | 922K | |
| gpt-4o-2024-08-06💬azure | 1283 | $2.50 | $10.0 | $1.25 | — | $1.25 / $5.00 | 128K | |
| gpt-4o-audio-preview-2024-12-17azure | — | $2.50 | $10.0 | — | — | — | 128K | |
| gpt-audio-1.5-2026-02-23azure | — | $2.50 | $10.0 | — | — | — | 128K | |
| gpt-5.4-2026-03-05azure | — | $2.50 | $15.0 | $0.25 | — | $1.25 / $7.50 | 922K | |
| gpt-4o-2024-11-20💬azure | — | $2.50 | $10.0 | $1.25 | — | $1.25 / $5.00 | 128K | |
| gpt-4o💬azure | — | $2.50 | $10.0 | $1.25 | — | — | 128K | |
| gpt-4o-2024-11-20💬azure | — | $2.50 | $10.0 | $1.25 | — | $1.25 / $5.00 | 128K | |
| gpt-4o-2024-08-06💬azure | 1283 | $2.50 | $10.0 | $1.25 | — | $1.25 / $5.00 | 128K | |
| gpt-4o-2024-08-06💬azure | 1283 | $2.50 | $10.0 | $1.25 | — | $1.25 / $5.00 | 128K | |
| gpt-4o-2024-11-20💬azure | — | $2.50 | $10.0 | $1.25 | — | $1.25 / $5.00 | 128K | |
| gpt-audio🎙️azure | — | $2.50 | $10.0 | — | — | — | 128K | |
| gpt-audio-2025-08-28azure | — | $2.50 | $10.0 | — | — | — | 128K | |
| gpt-audio-1.5azure | — | $2.50 | $10.0 | — | — | — | 128K | |
| gpt-5.4💬azure | 1452 | $2.50 | $15.0 | $0.25 | — | $1.25 / $7.50 | 922K | |
| gpt-6-sol💬azure | — | $2.40 | $12.0 | $0.24 | $3.00 | — | 922K | |
| gpt-6.1-sol💬azure | — | $2.40 | $12.0 | $0.12 | $3.00 | — | 922K | |
| gpt-6.1-sol💬azure | — | $2.40 | $12.0 | $0.12 | $3.00 | — | 922K | |
| o3-2025-04-16azure | — | $2.20 | $8.80 | $0.55 | — | $1.10 / $4.40 | 200K | |
| gpt-4.1💬azure | — | $2.20 | $8.80 | $0.55 | — | $1.10 / $4.40 | — | |
| gpt-4.1-2025-04-14azure | — | $2.20 | $8.80 | $0.55 | — | $1.10 / $4.40 | 1.0M | |
| gpt-4.1💬azure | — | $2.20 | $8.80 | $0.55 | — | $1.10 / $4.40 | — | |
| o3-2025-04-16azure | — | $2.20 | $8.80 | $0.55 | — | $1.10 / $4.40 | 200K | |
| o3🧮azure | — | $2.20 | $8.80 | $0.55 | — | $1.10 / $4.40 | 200K | — |
| gpt-6.1-sol💬azure | — | $2.20 | $11.0 | $0.11 | $2.75 | — | 922K | |
| gpt-5.6-terra💬azure | — | $2.20 | $13.2 | $0.22 | $2.75 | — | 922K | |
| gpt-6-sol💬azure | — | $2.20 | $11.0 | $0.22 | $2.75 | — | 922K | |
| o3🧮azure | — | $2.20 | $8.80 | $0.55 | — | $1.10 / $4.40 | 200K | — |
| gpt-5.6-terra💬azure | — | $2.20 | $13.2 | $0.22 | $2.75 | — | 922K | |
| o3🧮azure | — | $2.00 | $8.00 | $0.50 | — | — | 200K | |
| gpt-5.6-terra-2026-07-09azure | — | $2.00 | $12.0 | $0.20 | $2.50 | — | 922K | |
| gpt-4.1💬azure | — | $2.00 | $8.00 | $0.50 | — | $1.00 / $4.00 | 1.0M | |
| gpt-6-sol💬azure | — | $2.00 | $10.0 | $0.20 | $2.50 | — | 922K | |
| gpt-6-sol-2026-09-22azure | — | $2.00 | $10.0 | $0.20 | $2.50 | — | 922K | |
| gpt-6.1-sol💬azure | — | $2.00 | $10.0 | $0.10 | $2.50 | — | 922K | |
| gpt-6.1-sol-2026-09-29azure | — | $2.00 | $10.0 | $0.10 | $2.50 | — | 922K | |
| gpt-4.1-2025-04-14azure | — | $2.00 | $8.00 | $0.50 | — | $1.00 / $4.00 | 1.0M |
Recent price changes
- ▲ 66.7%Z.ai: GLM 5z-ai · output $1.92 → $3.204h
- ▲ 66.7%Z.ai: GLM 5z-ai · input $0.60 → $1.004h
- ▼ 6.7%Qwen: Qwen3.5-35B-A3Bqwen · input $0.15 → $0.144h
- ▼ 13.3%Qwen: Qwen3.5-9Bqwen · output $0.15 → $0.134h
- ▼ 20.0%Qwen: Qwen3.5-9Bqwen · input $0.10 → $0.08004h
- ▲ 433.3%NVIDIA: Nemotron 3 Supernvidia · output $0.45 → $2.404h
- ▲ 275.0%NVIDIA: Nemotron 3 Supernvidia · input $0.0800 → $0.304h
- ▲ 44.9%Z.ai: GLM 5.1z-ai · output $3.04 → $4.404h
- ▲ 44.9%Z.ai: GLM 5.1z-ai · input $0.97 → $1.404h
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · output $0.28 → $0.244h
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · input $0.14 → $0.124h
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · output $0.87 → $0.614h
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · input $0.43 → $0.304h
- ▲ 189.3%Z.ai: GLM 5.2z-ai · output $2.42 → $7.004h
- ▼ 94.5%Z.ai: GLM 5.2z-ai · input $0.62 → $0.03414h
- ▲ 17.3%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.45 → $0.534h
- ▲ 84.2%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0114 → $0.02104h
- ▼ 38.6%Qwen: Qwen3.8 27Bqwen · output $2.20 → $1.354h
- ▼ 83.3%Qwen: Qwen3.8 27Bqwen · input $0.24 → $0.04004h
- ▲ 212.5%Z.ai: GLM 5.3 Flashz-ai · output $0.16 → $0.504h
Price cuts are green — they make AI cheaper for everyone.