💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 14h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.
All providersbedrock_converse 599bedrock_mantle 419fireworks_ai 328bedrock 275azure 211deepinfra 140novita 130gmi 122azure_ai 110openai 104vercel_ai_gateway 93empiriolabs 92kyma 83replicate 83
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 |
|---|---|---|---|---|---|---|---|---|
| Hy3💬deepinfra | 1439 | $0.14 | $0.58 | $0.0350 | — | — | 262K | |
| Qwen3-30B-A3B💬deepinfra | 1317 | $0.12 | $0.50 | — | — | — | 41K | |
| Qwen3-14B💬deepinfra | — | $0.12 | $0.24 | — | — | — | 41K | |
| Llama-3.3-70B-Instruct-Turbodeepinfra | — | $0.10 | $0.32 | — | — | — | 131K | |
| Llama-4-Scout-17B-16E-Instructdeepinfra | — | $0.10 | $0.30 | — | — | — | 328K | |
| Qwen3.6-35B-A3B💬deepinfra | — | $0.10 | $0.95 | — | — | — | 262K | |
| Seed-2.0-mini💬deepinfra | — | $0.10 | $0.40 | $0.0200 | — | — | 256K | |
| Qwen3.5-9B💬deepinfra | — | $0.10 | $0.15 | — | — | — | 262K | |
| Llama-3.3-Nemotron-Super-49B-v1.5💬deepinfra | 1338 | $0.10 | $0.40 | — | — | — | 131K | |
| Qwen3-Next-80B-A3B-Instruct💬deepinfra | 1417 | $0.0900 | $1.10 | — | — | — | 262K | |
| gemma-4-31B-it-turbodeepinfra | — | $0.0900 | $0.34 | $0.0500 | — | — | 262K | |
| Qwen3-235B-A22B-Instruct-2507deepinfra | — | $0.0900 | $0.55 | — | — | — | 262K | |
| DeepSeek-V4-Flash💬deepinfra | 1432 | $0.0900 | $0.18 | $0.0180 | — | — | 1.0M | |
| gemma-3-27b-it💬deepinfra | 1358 | $0.0800 | $0.16 | — | — | — | 131K | |
| Qwen3-32B💬deepinfra | 1340 | $0.0800 | $0.28 | — | — | — | 41K | |
| Mistral-Small-3.2-24B-Instruct-2506deepinfra | — | $0.0750 | $0.20 | — | — | — | 128K | |
| NVIDIA-Nemotron-3-Super-120B-A12Bdeepinfra | — | $0.0750 | $0.40 | — | — | — | 262K | |
| gemma-4-26B-A4B-it💬deepinfra | — | $0.0700 | $0.34 | — | — | — | 262K | |
| phi-4💬deepinfra | 1217 | $0.0700 | $0.14 | — | — | — | 16K | |
| GLM-4.7-Flash💬deepinfra | 1351 | $0.0600 | $0.40 | $0.0100 | — | — | 203K | |
| DeepSeek-V4-Flash-0731💬deepinfra | — | $0.0600 | $0.18 | $0.0150 | — | — | 1.0M | |
| Ling-3.0-flash💬deepinfra | — | $0.0600 | $0.18 | $0.0120 | — | — | 131K | |
| NVIDIA-Nemotron-3.5-Lightningdeepinfra | — | $0.0600 | $0.16 | $0.0400 | — | — | 262K | |
| Llama-Guard-3-8Bdeepinfra | — | $0.0550 | $0.0550 | — | — | — | 131K | |
| Nemotron-3-Nano-30B-A3B💬deepinfra | — | $0.0500 | $0.20 | $0.0250 | — | — | 262K | |
| Mistral-Small-24B-Instruct-2501💬deepinfra | 1234 | $0.0500 | $0.0800 | — | — | — | 33K | |
| gemma-3-12b-it💬deepinfra | 1334 | $0.0500 | $0.15 | — | — | — | 131K | |
| gemma-3-4b-it💬deepinfra | 1291 | $0.0500 | $0.10 | — | — | — | 131K | |
| Llama-3.2-11B-Vision-Instruct👁️deepinfra | — | $0.0490 | $0.0490 | — | — | — | 131K | |
| NVIDIA-Nemotron-Nano-9B-v2deepinfra | — | $0.0400 | $0.16 | — | — | — | 131K | |
| Qwen2.5-7B-Instructdeepinfra | — | $0.0400 | $0.10 | — | — | — | 33K | |
| L3-8B-Lunaris-v1-Turbodeepinfra | — | $0.0400 | $0.0500 | — | — | — | 8K | |
| gpt-oss-120b💬deepinfra | 1366 | $0.0370 | $0.17 | — | — | — | 131K | |
| Meta-Llama-3-8B-Instructdeepinfra | — | $0.0300 | $0.0600 | — | — | — | 8K | |
| gpt-oss-20b💬deepinfra | 1288 | $0.0300 | $0.14 | — | — | — | 131K | |
| Meta-Llama-3.1-8B-Instructdeepinfra | — | $0.0300 | $0.0500 | — | — | — | 131K | |
| Mistral-Nemo-Instruct-2407deepinfra | — | $0.0290 | $0.0300 | — | — | — | 131K | |
| Llama-3.2-3B-Instruct💬deepinfra | 1110 | $0.0200 | $0.0200 | — | — | — | 131K | |
| gemma-4-E4B-itdeepinfra | — | $0.0200 | $0.10 | — | — | — | 131K | |
| Meta-Llama-3.1-8B-Instruct-Turbodeepinfra | — | $0.0200 | $0.0400 | — | — | — | 131K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.06809h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.02309h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.07849h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.03999h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.429h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.629h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.609h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.269h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.07009h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.369h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.09009h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.189h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.009h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.339h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.05009h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.969h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.329h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.189h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.06009h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.239h
Price cuts are green — they make AI cheaper for everyone.