💲 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 |
|---|---|---|---|---|---|---|---|---|
| command-r7b-12-2024💬cohere_chat | — | $0.0375 | $0.15 | — | — | — | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0370 | $0.15 | $0.0092 | — | — | 128K | |
| apac.amazon.nova-micro-v1:0bedrock_converse | — | $0.0370 | $0.15 | $0.0092 | — | — | 128K | |
| gpt-oss-120b💬deepinfra | 1366 | $0.0370 | $0.17 | — | — | — | 131K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0350 | $0.14 | $0.0088 | free | — | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0350 | $0.14 | $0.0088 | free | — | 128K | |
| us.amazon.nova-micro-v1:0bedrock_converse | — | $0.0350 | $0.14 | $0.0088 | — | $0.0175 / $0.0700 | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0350 | $0.14 | $0.0088 | free | — | 128K | |
| qwen3-8b-fp8novita | — | $0.0350 | $0.14 | — | — | — | 128K | |
| nova-microvercel_ai_gateway | — | $0.0350 | $0.14 | — | — | — | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0350 | $0.14 | $0.0088 | — | $0.0175 / $0.0700 | 128K | |
| autoglm-phone-9b-multilingualnovita | — | $0.0350 | $0.14 | — | — | — | 66K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0350 | $0.14 | $0.0088 | free | — | 128K | |
| nova-micro-v1💬amazon_nova | — | $0.0350 | $0.14 | — | — | — | 128K | |
| doubao-seed-2-0-miniaihubmix | — | $0.0301 | $0.30 | $0.0060 | — | — | 256K | |
| agnes-2.5-flashaihubmix | — | $0.0300 | $0.15 | — | — | — | 512K | |
| granite-3.1-8b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| Llama-3.1-8B-Instruct💬nscale | 1187 | $0.0300 | $0.0300 | — | — | — | — | |
| granite-3.0-2b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| granite-3.1-2b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| gpt-oss-120b💬wandb | 1366 | $0.0300 | $0.17 | — | — | — | 131K | |
| gpt-oss-20b💬wandb | 1288 | $0.0300 | $0.13 | — | — | — | 131K | |
| Meta-Llama-3.1-8B-Instructdeepinfra | — | $0.0300 | $0.0500 | — | — | — | 131K | |
| deepseek-ocr-2novita | — | $0.0300 | $0.0300 | — | — | — | 8K | |
| granite-3.2-8b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| Meta-Llama-3-8B-Instructdeepinfra | — | $0.0300 | $0.0600 | — | — | — | 8K | |
| granite-3.3-8b-instructreplicate | — | $0.0300 | $0.25 | — | — | — | — | |
| llama-3.2-3b-instruct💬novita | 1110 | $0.0300 | $0.0500 | — | — | — | 33K | |
| llama-prompt-guard-2-22mgroq | — | $0.0300 | $0.0300 | — | — | — | 512 | |
| llama-3.1-8bllamagate | — | $0.0300 | $0.0500 | — | — | — | 131K | |
| gemma3-4bllamagate | — | $0.0300 | $0.0800 | — | — | — | 128K | |
| gemma-4-26bdarkbloom | — | $0.0300 | $0.17 | — | — | — | 131K | |
| qwen3-7-flash💬empiriolabs | — | $0.0300 | $0.13 | $0.0060 | — | — | 984K | |
| qwen3-4b-fp8novita | — | $0.0300 | $0.0300 | — | — | — | 128K | |
| gpt-oss-20b💬deepinfra | 1288 | $0.0300 | $0.14 | — | — | — | 131K | |
| deepseek-ocrnovita | — | $0.0300 | $0.0300 | — | — | — | 8K | |
| Mistral-Nemo-Instruct-2407deepinfra | — | $0.0290 | $0.0300 | — | — | — | 131K | |
| qwen3-5-flash:variant1empiriolabs | — | $0.0290 | $0.29 | — | — | — | 996K | |
| qwen3-7-flash:variant1empiriolabs | — | $0.0280 | $0.11 | $0.0060 | — | — | 984K | |
| llama-3.2-1b-instruct💬cloudflare | 1055 | $0.0270 | $0.20 | — | — | — | 60K | |
| llama3.1-8b-instructlambda_ai | — | $0.0250 | $0.0400 | — | — | — | 131K | |
| lfm-7blambda_ai | — | $0.0250 | $0.0400 | — | — | — | 131K | |
| DeepSeek-R1-Distill-Llama-8Bnscale | — | $0.0250 | $0.0250 | — | — | — | — | |
| hermes3-8blambda_ai | — | $0.0250 | $0.0400 | — | — | — | 131K | |
| glm-4.7-flash💬clf_ai_gateway | 1351 | $0.0240 | $0.16 | — | — | — | 131K | |
| Llama-3.2-3B-Instruct💬deepinfra | 1110 | $0.0200 | $0.0200 | — | — | — | 131K | |
| Meta-Llama-3.1-8B-Instructnebius | — | $0.0200 | $0.0600 | — | — | — | 128K | |
| LFM2.5-1.2B-Instructzerogpu | — | $0.0200 | $0.0500 | — | — | — | 33K | |
| LFM2.5-1.2B-Thinkingzerogpu | — | $0.0200 | $0.0500 | — | — | — | 33K | |
| paddleocr-vlnovita | — | $0.0200 | $0.0200 | — | — | — | 16K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068017h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023017h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078417h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039917h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4217h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6217h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6017h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2617h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070017h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3617h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090017h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1817h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0017h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3317h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050017h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9617h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3217h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1817h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060017h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2317h
Price cuts are green — they make AI cheaper for everyone.