💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 17h. 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 |
|---|---|---|---|---|---|---|---|---|
| devstral-medium-latestmistral | — | $0.40 | $2.00 | $0.0400 | — | — | 256K | |
| devstral-latestmistral | — | $0.40 | $2.00 | $0.0400 | — | — | 256K | |
| qwen3-coder💻vercel_ai_gateway | — | $0.40 | $1.60 | — | — | — | 262K | |
| gpt-4.1-mini-2025-04-14openai | — | $0.40 | $1.60 | $0.10 | — | $0.20 / $0.80 | 1.0M | |
| Beam-1.0-501B-A23B💬together_ai | 1424 | $0.40 | $1.20 | $0.0400 | — | — | 1.0M | |
| deepseek-v3-turbonovita | — | $0.40 | $1.30 | — | — | — | 64K | |
| Beam-1.0baseten | — | $0.40 | $1.20 | $0.0400 | — | — | 1.0M | |
| mistral.devstral-2-123bbedrock_converse | — | $0.40 | $2.00 | — | — | $0.20 / $1.00 | 256K | |
| GLM-4.7-FP8gmi | — | $0.40 | $2.00 | — | — | — | 203K | |
| qwen3-vl-235b-a22b-instruct👁️qwen_ai_platform | 1420 | $0.40 | $1.60 | — | — | — | 131K | |
| GLM-4.5💬deepinfra | 1430 | $0.40 | $1.60 | — | — | — | 131K | |
| qwen3.5-122b-a10b💬novita | 1418 | $0.40 | $3.20 | — | — | — | 262K | |
| deepseek-v4-flash-0731💬scaleway | — | $0.40 | $0.80 | $0.0800 | — | — | 256K | |
| seed-2-0-code💻empiriolabs | — | $0.40 | $2.40 | — | — | — | 229K | |
| qwen-3-32bcerebras | — | $0.40 | $0.80 | — | — | — | 128K | |
| gpt-4.1-mini💬zerogpu | — | $0.40 | $1.60 | $0.10 | — | — | 1.0M | |
| qwen3.8-27b💬aiand | 1437 | $0.40 | $3.00 | $0.20 | — | — | 262K | |
| qwen3-vl-235b-a22b-instruct👁️qwencloud | 1420 | $0.40 | $1.60 | — | — | — | 131K | |
| qwen-plus-2025-07-14qwencloud | — | $0.40 | $1.20 | — | — | — | 129K | |
| amazon.nova-2-lite-v1:0bedrock_converse | — | $0.40 | $3.31 | $0.0990 | free | — | 1.0M | |
| apac.amazon.nova-2-lite-v1:0bedrock_converse | — | $0.40 | $3.31 | $0.0990 | — | — | 1.0M | |
| jp.amazon.nova-2-lite-v1:0bedrock_converse | — | $0.40 | $3.31 | $0.0990 | — | $0.20 / $1.66 | 1.0M | |
| minimax-m3💬kyma | 1427 | $0.40 | $1.58 | $0.0756 | — | — | 1.0M | |
| minimax-m3💬inferenceapis | 1427 | $0.39 | $1.56 | $0.0800 | — | — | 524K | |
| MiniMax-M3💬inferenceapis | 1427 | $0.39 | $1.56 | $0.0800 | — | — | 524K | |
| global.amazon.nova-2-lite-v1:0bedrock_converse | — | $0.39 | $3.27 | — | — | — | 1.0M | |
| gemma-4-31B-it💬together_ai | — | $0.39 | $0.97 | — | — | — | 262K | |
| global.amazon.nova-2-lite-v1:0bedrock_converse | — | $0.39 | $3.21 | — | — | — | 1.0M | |
| meta.llama3-8b-instruct-v1:0bedrock | — | $0.39 | $0.78 | — | — | — | 8K | |
| ernie-4.5-vl-28b-a3b-thinkingnovita | — | $0.39 | $0.39 | — | — | — | 131K | |
| deepseek-v4-flash-vision-exp👁️kyma | — | $0.39 | $1.17 | — | — | — | 1.0M | |
| qwen3.8-27b💬kyma | 1437 | $0.38 | $2.73 | — | — | — | 1.0M | |
| granite-ttm-512-96-r2watsonx | — | $0.38 | $0.38 | — | — | — | 512 | |
| gemma-4-31B-it💬sambanova | — | $0.38 | $1.15 | — | — | — | 131K | |
| granite-ttm-1536-96-r2watsonx | — | $0.38 | $0.38 | — | — | — | 512 | |
| granite-ttm-1024-96-r2watsonx | — | $0.38 | $0.38 | — | — | — | 512 | |
| qwen3-coder-480b-a35b-instructnovita | — | $0.38 | $1.55 | — | — | — | 262K | |
| qwen-2.5-72b-instruct💬novita | 1269 | $0.38 | $0.40 | — | — | — | 32K | |
| MiniMax-M2.7-Turbodeepinfra | — | $0.38 | $1.70 | $0.0700 | — | — | 197K | |
| kimi-k2.7-code💻clf_ai_gateway | — | $0.38 | $1.60 | $0.0760 | — | — | 262K | |
| kimi-k2.6💬clf_ai_gateway | 1456 | $0.38 | $1.60 | $0.0640 | — | — | 262K | |
| nova-lite-2empiriolabs | — | $0.38 | $3.16 | $0.21 | — | — | 1.0M | |
| global.amazon.nova-2-lite-v1:0bedrock_converse | — | $0.38 | $3.13 | — | — | — | 1.0M | |
| qwen3.6-35b-a3b💬streamlake | — | $0.38 | $2.25 | — | — | — | 229K | |
| FW-DeepSeek-V4.1-Flashazure_ai | — | $0.38 | $1.50 | $0.0080 | — | — | 1.0M | |
| deepseek-v4.1-flash-1017💬wally | — | $0.38 | $1.50 | $0.0080 | — | — | 1.0M | |
| DeepSeek-R1-Distill-Llama-70B🧮nscale | — | $0.38 | $0.38 | — | — | — | — | |
| databricks-gemini-3-5-flash-litedatabricks | — | $0.37 | $3.13 | $0.0375 | $0.37 | — | 1.0M | |
| eu.amazon.nova-2-lite-v1:0bedrock_converse | — | $0.37 | $3.16 | $0.0935 | free | — | 1.0M | |
| amazon.nova-2-lite-v1:0bedrock_converse | — | $0.37 | $3.16 | $0.0935 | free | — | 1.0M |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068012h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023012h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078412h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039912h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4212h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6212h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6012h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2612h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070012h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3612h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090012h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1812h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0012h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3312h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050012h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9612h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3212h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1812h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060012h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2312h
Price cuts are green — they make AI cheaper for everyone.