💲 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 |
|---|---|---|---|---|---|---|---|---|
| communitynovita | — | $4.00 | $4.00 | — | — | — | 64K | |
| deepseek-r1🧮novita | 1373 | $4.00 | $4.00 | — | — | — | 64K | |
| kimi-k3💬novita | 1473 | $3.00 | $15.0 | $0.30 | — | — | 1.0M | |
| qwen3-max💬novita | — | $2.11 | $8.45 | — | — | — | 262K | |
| qwen3.8-max💬novita | 1483 | $2.00 | $6.00 | $0.25 | — | — | 1.0M | |
| deepseek-v4-pro💬novita | 1451 | $1.60 | $3.20 | $0.14 | — | — | 1.0M | |
| macaron-v1-ventinovita | — | $1.50 | $4.50 | $0.30 | — | — | 1.0M | |
| l3-70b-euryale-v2.1novita | — | $1.48 | $1.48 | — | — | — | 8K | |
| l31-70b-euryale-v2.2novita | — | $1.48 | $1.48 | — | — | — | 8K | |
| glm-5.3💬novita | — | $1.40 | $4.40 | $0.26 | — | — | 1.0M | |
| glm-5.2💬novita | — | $1.40 | $4.40 | $0.26 | — | — | 1.0M | |
| glm-5.1💬novita | 1462 | $1.38 | $4.40 | $0.26 | — | — | 205K | |
| deepseek-v4-pro-0813💬novita | — | $1.32 | $3.96 | $0.13 | — | — | 1.0M | |
| qwen3.7-max💬novita | — | $1.25 | $3.75 | $0.25 | — | — | 1.0M | |
| glm-5-turbo💬novita | — | $1.20 | $4.00 | $0.24 | — | — | 203K | |
| glm-5v-turbo💬novita | 1438 | $1.20 | $4.00 | $0.24 | — | — | 205K | |
| glm-5💬novita | 1446 | $1.00 | $3.20 | $0.20 | — | — | 203K | |
| qwen3-vl-235b-a22b-thinking🧮novita | 1401 | $0.98 | $3.95 | — | — | — | 131K | |
| kimi-k2.7-code💻novita | — | $0.95 | $4.00 | $0.19 | — | — | 262K | |
| deepseek_v3novita | — | $0.89 | $0.89 | — | — | — | 64K | |
| communitynovita | — | $0.89 | $0.89 | — | — | — | 64K | |
| qwen2.5-vl-72b-instruct👁️novita | — | $0.80 | $0.80 | — | — | — | 33K | |
| deepseek-r1-distill-llama-70b🧮novita | — | $0.80 | $0.80 | — | — | — | 8K | |
| kimi-k2.6💬novita | 1455 | $0.80 | $3.40 | $0.16 | — | — | 262K | |
| deepseek-prover-v2-671bnovita | — | $0.70 | $2.50 | — | — | — | 160K | |
| deepseek-r1-turbonovita | — | $0.70 | $2.50 | — | — | — | 64K | |
| deepseek-r1-0528🧮novita | 1428 | $0.70 | $2.50 | $0.35 | — | — | 164K | |
| wizardlm-2-8x22b💬novita | — | $0.62 | $0.62 | — | — | — | 66K | |
| glm-4.7💬novita | 1435 | $0.60 | $2.20 | $0.11 | — | — | 205K | |
| glm-4.5💬novita | 1430 | $0.60 | $2.20 | $0.11 | — | — | 131K | |
| kimi-k2.5💬novita | — | $0.60 | $3.00 | $0.10 | — | — | 262K | |
| qwen3.6-27b💬novita | — | $0.60 | $3.60 | — | — | — | 262K | |
| kimi-k2-thinking🧮novita | — | $0.60 | $2.50 | $0.15 | — | — | 262K | |
| glm-4.7-hnovita | — | $0.60 | $2.20 | $0.11 | — | — | 205K | |
| minimax-m2.5-highspeednovita | — | $0.60 | $2.40 | $0.0300 | — | — | 205K | |
| kimi-k2-0905💬novita | — | $0.60 | $2.50 | — | — | — | 262K | |
| minimax-m2.7-highspeednovita | — | $0.60 | $2.40 | $0.0600 | — | — | 205K | |
| qwen3.5-397b-a17b💬novita | 1438 | $0.60 | $3.60 | — | — | — | 262K | |
| glm-4.5v💬novita | 1333 | $0.60 | $1.80 | $0.11 | — | — | 66K | |
| kimi-k2-instructnovita | — | $0.57 | $2.30 | — | — | — | 131K | |
| glm-4.6💬novita | 1440 | $0.55 | $2.20 | $0.11 | — | — | 205K | |
| minimax-m1-80knovita | — | $0.55 | $2.20 | — | — | — | 1.0M | |
| glm-4-32b-0414novita | — | $0.55 | $1.66 | — | — | — | 32K | |
| mimo-v2.5-pro💬novita | 1465 | $0.52 | $1.04 | $0.0043 | — | — | 1.0M | |
| llama-3-70b-instructnovita | — | $0.51 | $0.74 | — | — | — | 8K | |
| macaron-v1-tallnovita | — | $0.45 | $2.60 | $0.0800 | — | — | 262K | |
| deepseek-v4-flash-0731💬novita | — | $0.44 | $1.32 | $0.0280 | — | — | 1.0M | |
| deepseek-v4-flash-vision-exp👁️novita | — | $0.44 | $1.32 | $0.0280 | — | — | 1.0M | |
| ernie-4.5-vl-424b-a47b👁️novita | — | $0.42 | $1.25 | — | — | — | 123K | |
| qwen3.5-122b-a10b💬novita | 1417 | $0.40 | $3.20 | — | — | — | 262K |
Recent price changes
- ▲ 66.7%Z.ai: GLM 5z-ai · output $1.92 → $3.203h
- ▲ 66.7%Z.ai: GLM 5z-ai · input $0.60 → $1.003h
- ▼ 6.7%Qwen: Qwen3.5-35B-A3Bqwen · input $0.15 → $0.143h
- ▼ 13.3%Qwen: Qwen3.5-9Bqwen · output $0.15 → $0.133h
- ▼ 20.0%Qwen: Qwen3.5-9Bqwen · input $0.10 → $0.08003h
- ▲ 433.3%NVIDIA: Nemotron 3 Supernvidia · output $0.45 → $2.403h
- ▲ 275.0%NVIDIA: Nemotron 3 Supernvidia · input $0.0800 → $0.303h
- ▲ 44.9%Z.ai: GLM 5.1z-ai · output $3.04 → $4.403h
- ▲ 44.9%Z.ai: GLM 5.1z-ai · input $0.97 → $1.403h
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · output $0.28 → $0.243h
- ▼ 15.0%Xiaomi: MiMo-V2.5xiaomi · input $0.14 → $0.123h
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · output $0.87 → $0.613h
- ▼ 30.0%Xiaomi: MiMo-V2.5-Proxiaomi · input $0.43 → $0.303h
- ▲ 189.3%Z.ai: GLM 5.2z-ai · output $2.42 → $7.003h
- ▼ 94.5%Z.ai: GLM 5.2z-ai · input $0.62 → $0.03413h
- ▲ 17.3%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.45 → $0.533h
- ▲ 84.2%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0114 → $0.02103h
- ▼ 38.6%Qwen: Qwen3.8 27Bqwen · output $2.20 → $1.353h
- ▼ 83.3%Qwen: Qwen3.8 27Bqwen · input $0.24 → $0.04003h
- ▲ 212.5%Z.ai: GLM 5.3 Flashz-ai · output $0.16 → $0.503h
Price cuts are green — they make AI cheaper for everyone.