💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 21h. 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 |
|---|---|---|---|---|---|---|---|---|
| gpt-oss-120b💬sail | 1366 | $0.0600 | $0.40 | $0.0300 | — | — | 131K | |
| qwen3-5-35b-a3b💬empiriolabs | 1395 | $0.0570 | $0.46 | — | — | — | 258K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0560 | $0.22 | $0.0140 | — | — | 128K | |
| eu.amazon.nova-micro-v1:0bedrock_converse | — | $0.0560 | $0.22 | $0.0140 | — | — | 128K | |
| Llama-Guard-3-8Bdeepinfra | — | $0.0550 | $0.0550 | — | — | — | 131K | |
| gpt-5-nano💬azure | — | $0.0550 | $0.44 | $0.0055 | — | $0.0275 / $0.22 | — | |
| gpt-5-nano-2025-08-07azure | — | $0.0550 | $0.44 | $0.0055 | — | $0.0275 / $0.22 | 272K | |
| gpt-5-nano-2025-08-07azure | — | $0.0550 | $0.44 | $0.0055 | — | $0.0275 / $0.22 | 272K | |
| gpt-5-nano💬azure | — | $0.0550 | $0.44 | $0.0055 | — | $0.0275 / $0.22 | — | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0520 | $0.21 | $0.0130 | — | — | 128K | |
| eu.amazon.nova-micro-v1:0bedrock_converse | — | $0.0520 | $0.21 | $0.0130 | — | — | 128K | |
| llama-3.2-3b-instruct💬cloudflare | 1110 | $0.0509 | $0.34 | — | — | — | 80K | |
| qwen3-30b-a3b-fp8cloudflare | — | $0.0509 | $0.34 | — | — | — | 33K | |
| llama-3.2-3b-instruct-fastzerogpu | — | $0.0500 | $0.30 | $0.0250 | — | — | 131K | |
| mistral.voxtral-mini-3b-2507bedrock_converse | — | $0.0500 | $0.0500 | — | — | — | 33K | |
| gpt-oss-20b💬together_ai | 1288 | $0.0500 | $0.20 | — | — | — | 131K | |
| nemotron-3-nano-30b-a3b💬novita | — | $0.0500 | $0.20 | — | — | — | 262K | |
| llama-2-7b-chatreplicate | — | $0.0500 | $0.25 | — | — | — | 4K | |
| llama-3-8breplicate | — | $0.0500 | $0.25 | — | — | — | 8K | |
| llama-3-8b-instruct💬replicate | 1166 | $0.0500 | $0.25 | — | — | — | 8K | |
| openai.gpt-5-nanooci | — | $0.0500 | $0.40 | — | — | — | 272K | |
| mistral-7b-instruct-v0.2replicate | — | $0.0500 | $0.25 | — | — | — | 4K | |
| mistral-7b-v0.1replicate | — | $0.0500 | $0.25 | — | — | — | 4K | |
| google.gemma-3-4b-itbedrock_mantle | — | $0.0500 | $0.10 | — | — | — | 128K | |
| gpt-5-nano💬replicate | — | $0.0500 | $0.40 | — | — | — | — | |
| mistral.voxtral-mini-3b-2507bedrock_mantle | — | $0.0500 | $0.0500 | — | — | — | 33K | |
| L3-8B-Stheno-v3.2novita | — | $0.0500 | $0.0500 | — | — | — | 8K | |
| mistral.voxtral-mini-3b-2507bedrock_converse | — | $0.0500 | $0.0500 | — | — | — | 33K | |
| google.gemma-3-4b-itbedrock_mantle | — | $0.0500 | $0.0900 | — | — | — | 128K | |
| mistral.voxtral-mini-3b-2507bedrock | — | $0.0500 | $0.0500 | — | — | $0.0300 / $0.0300 | 33K | |
| mistral.voxtral-mini-3b-2507bedrock_mantle | — | $0.0500 | $0.0500 | — | — | — | 33K | |
| qwen3-32b-fp8lambda_ai | — | $0.0500 | $0.10 | — | — | — | 131K | |
| qwen25-coder-32b-instructlambda_ai | — | $0.0500 | $0.10 | — | — | — | 131K | |
| meta-llama-3-8b-instructreplicate | — | $0.0500 | $0.25 | — | — | — | — | |
| llama-4-scout-17b-16e-instructlambda_ai | — | $0.0500 | $0.10 | — | — | — | 16K | |
| llama-4-maverick-17b-128e-instruct-fp8lambda_ai | — | $0.0500 | $0.10 | — | — | — | 131K | |
| google.gemma-3-4b-itbedrock_converse | — | $0.0500 | $0.0900 | — | — | — | 128K | |
| meta-llama-3-8breplicate | — | $0.0500 | $0.25 | — | — | — | — | |
| granite-8b-code-instruct-128kreplicate | — | $0.0500 | $0.25 | — | — | — | — | |
| l3-8b-lunarisnovita | — | $0.0500 | $0.0500 | — | — | — | 8K | |
| gpt-5-nano-2025-08-07openai | — | $0.0500 | $0.40 | $0.0050 | — | $0.0250 / $0.20 | 272K | |
| gpt-5-nano💬openai | — | $0.0500 | $0.40 | $0.0050 | — | $0.0250 / $0.20 | 272K | |
| llama-3-8bvercel_ai_gateway | — | $0.0500 | $0.0800 | — | — | — | 8K | |
| llama-3.1-8bvercel_ai_gateway | — | $0.0500 | $0.0800 | — | — | — | 131K | |
| granite-3.0-8b-instructreplicate | — | $0.0500 | $0.25 | — | — | — | — | |
| qwen-turbodashscope | — | $0.0500 | $0.20 | — | — | — | 129K | |
| extract💬scaledown | — | $0.0500 | free | — | — | — | — | |
| qwen-turbo-2025-04-28dashscope | — | $0.0500 | $0.20 | — | — | — | 1.0M | |
| summarize💬scaledown | — | $0.0500 | free | — | — | — | — | |
| compressscaledown | — | $0.0500 | free | — | — | — | — |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068016h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023016h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078416h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039916h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4216h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6216h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6016h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2616h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070016h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3616h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090016h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1816h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0016h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3316h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050016h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9616h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3216h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1816h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060016h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2316h
Price cuts are green — they make AI cheaper for everyone.