💲 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 |
|---|---|---|---|---|---|---|---|---|
| Qwen3.6-27B-FP8tensormesh | — | $0.32 | $3.20 | free | — | — | 262K | |
| qwen3.6-27b💬aiand | — | $0.32 | $3.20 | $0.20 | — | — | 262K | |
| Qwen3.7-Plus💬together_ai | 1454 | $0.32 | $1.28 | — | — | — | 1.0M | |
| global.amazon.nova-2-lite-v1:0bedrock_converse | — | $0.32 | $2.63 | — | — | — | 1.0M | |
| global.amazon.nova-2-lite-v1:0bedrock_converse | — | $0.32 | $2.64 | — | — | — | 1.0M | |
| global.amazon.nova-2-lite-v1:0bedrock_converse | — | $0.32 | $2.63 | — | — | — | 1.0M | |
| DeepSeek-V3deepinfra | — | $0.32 | $0.89 | — | — | — | 164K | |
| meta.llama3-8b-instruct-v1:0bedrock | — | $0.32 | $0.65 | — | — | — | 8K | |
| Qwen3.6-27B💬deepinfra | — | $0.32 | $3.20 | — | — | — | 262K | |
| databricks-gemini-3-1-flash-lite-imagedatabricks | — | $0.31 | $1.88 | $0.31 | $0.31 | — | 66K | |
| databricks-gemini-3-1-flash-litedatabricks | — | $0.31 | $1.88 | $0.0312 | $0.31 | — | 1.0M | |
| minimax.minimax-m2.1bedrock_converse | — | $0.31 | $1.24 | — | — | — | 196K | |
| seed-2-0-lite💬empiriolabs | — | $0.31 | $2.50 | — | — | — | 229K | |
| nvidia.nemotron-nano-12b-v2bedrock_mantle | — | $0.31 | $0.93 | — | — | — | 128K | |
| nvidia.nemotron-nano-12b-v2bedrock_converse | — | $0.31 | $0.93 | — | — | — | 128K | |
| mistral.ministral-3-14b-instructbedrock_mantle | — | $0.31 | $0.31 | — | — | — | 128K | |
| mistral.ministral-3-14b-instructbedrock_converse | — | $0.31 | $0.31 | — | — | — | 128K | |
| minimax.minimax-m2.5bedrock_mantle | — | $0.31 | $1.24 | — | — | — | 196K | |
| minimax.minimax-m2.1bedrock_mantle | — | $0.31 | $1.24 | — | — | — | 196K | |
| minimax.minimax-m2.5bedrock | — | $0.31 | $1.24 | — | — | $0.15 / $0.62 | 196K | |
| minimax.minimax-m2bedrock_mantle | — | $0.31 | $1.24 | — | — | — | 1.0M | |
| MiMo-V2.5-Pro💬gmi | 1464 | $0.30 | $0.61 | $0.0025 | — | — | 1.1M | |
| databricks-deepseek-v4-1-flashdatabricks | — | $0.30 | $1.20 | $0.0300 | $0.30 | — | 1.0M | |
| databricks-gemini-2-5-flashdatabricks | — | $0.30 | $2.50 | $0.0300 | $0.30 | — | 1.0M | |
| databricks-deepseek-v4-1-flash-1017databricks | — | $0.30 | $1.20 | $0.0070 | $0.30 | — | 1.0M | |
| deepseek-v4p1-flashfireworks_ai | — | $0.30 | $1.20 | $0.0060 | — | — | 1.0M | |
| minimax.minimax-m2.5bedrock | — | $0.30 | $1.20 | — | — | $0.15 / $0.60 | 196K | |
| deepseek-v4-1-flash-1017💬mistral | — | $0.30 | $1.20 | $0.0070 | — | — | 1.0M | |
| Qwen3-235B-A22B-Thinking-2507🧮deepinfra | 1416 | $0.30 | $2.90 | — | — | — | 262K | |
| qwen3-vl-235b-a22b-instruct👁️novita | 1420 | $0.30 | $1.50 | — | — | — | 131K | |
| gemini-3.5-flash-lite💬aihubmix | 1435 | $0.30 | $2.50 | $0.0300 | — | — | 1.0M | |
| deepseek-v4.1-flash-maasvertex_ai-deepseek_models | — | $0.30 | $1.20 | $0.0300 | — | — | 1.0M | |
| kat-coder-pronovita | — | $0.30 | $1.20 | $0.0600 | — | — | 256K | |
| glm-4.6v💬novita | 1376 | $0.30 | $0.90 | $0.0550 | — | — | 131K | |
| DeepSeek-V4.1-Flash💬nebius | — | $0.30 | $1.20 | $0.0100 | — | — | 1.0M | |
| codestral-latestmistral | — | $0.30 | $0.90 | $0.0300 | — | — | 128K | |
| codestral-2508💻mistral | — | $0.30 | $0.90 | $0.0300 | — | — | 128K | |
| qwen3-coder-30b-a3bpinstripes | — | $0.30 | $0.60 | — | — | — | 131K | |
| MiniMax-M2.5💬nebius | 1359 | $0.30 | $1.20 | — | — | — | 197K | |
| MiniMax-M3💬nebius | 1427 | $0.30 | $1.20 | $0.0600 | — | — | 1.0M | |
| minimax-m2-7-highspeedempiriolabs | — | $0.30 | $1.20 | $0.0300 | — | — | 205K | |
| minimax-m2💬novita | 1340 | $0.30 | $1.20 | $0.0300 | — | — | 205K | |
| minimax-m2.1💬novita | — | $0.30 | $1.20 | $0.0300 | — | — | 205K | |
| DeepSeek-V4.1-Flash-1017💬baseten | — | $0.30 | $1.20 | $0.0070 | — | — | 1.0M | |
| deepseek-v4p1-flash-1017fireworks_ai | — | $0.30 | $1.20 | $0.0060 | — | — | 1.0M | |
| deepseek-flash-latest💬fireworks_ai | — | $0.30 | $1.20 | $0.0060 | — | — | 1.0M | |
| DeepSeek-V4.1-Flash-1017💬together_ai | — | $0.30 | $1.20 | $0.0060 | — | — | 1.0M | |
| gemini-2.5-flash💬vercel_ai_gateway | 1417 | $0.30 | $2.50 | $0.0300 | — | — | 1.0M | |
| MiniMax-M3💬minimax | 1427 | $0.30 | $1.20 | $0.0600 | — | — | 1.0M | |
| MiniMax-M2💬minimax | 1340 | $0.30 | $1.20 | $0.0300 | $0.38 | — | 200K |
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.