💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 19h. 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-4o-mini💬gmi | — | $0.15 | $0.60 | — | — | — | 131K | |
| gpt-4o-mini💬openai | — | $0.15 | $0.60 | $0.0750 | — | $0.0750 / $0.30 | 128K | |
| gpt-4o-mini-2024-07-18💬openai | 1286 | $0.15 | $0.60 | $0.0750 | — | $0.0750 / $0.30 | 128K | |
| gpt-4o-mini-audio-preview-2024-12-17openai | — | $0.15 | $0.60 | — | — | — | 128K | |
| gpt-4o-mini-search-preview🔍openai | — | $0.15 | $0.60 | $0.0750 | — | $0.0750 / $0.30 | 128K | |
| gpt-4o-mini-search-preview-2025-03-11openai | — | $0.15 | $0.60 | $0.0750 | — | $0.0750 / $0.30 | 128K | |
| gpt-oss-120b💬groq | 1366 | $0.15 | $0.60 | $0.0750 | — | — | 131K | |
| Qwen3.8-Flash💬inferenceapis | — | $0.15 | $0.50 | $0.0200 | — | — | 1.0M | |
| qwen3.8-flash💬inferenceapis | — | $0.15 | $0.50 | $0.0200 | — | — | 1.0M | |
| meta.llama3-2-3b-instruct-v1:0bedrock | — | $0.15 | $0.15 | — | — | — | 128K | |
| MiniMax-M3.1-Flash💬minimax | — | $0.15 | $0.60 | $0.0150 | — | — | 1.0M | |
| mistral.ministral-3-8b-instructbedrock_converse | — | $0.15 | $0.15 | — | — | $0.0700 / $0.0700 | 128K | |
| mistral.mistral-7b-instruct-v0:2bedrock | — | $0.15 | $0.20 | — | — | — | 32K | |
| zai-glm-5-3-flashmistral | — | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| magistral-small-latestmistral | — | $0.15 | $0.60 | $0.0150 | — | — | 262K | |
| mistral-small-latestmistral | — | $0.15 | $0.60 | $0.0150 | — | — | 262K | |
| ministral-3-8b-2512mistral | — | $0.15 | $0.15 | $0.0150 | — | — | 262K | |
| ministral-8b-2512💬mistral | — | $0.15 | $0.15 | $0.0150 | — | — | 262K | |
| ministral-8b-latestmistral | — | $0.15 | $0.15 | $0.0150 | — | — | 262K | |
| us.meta.llama3-2-3b-instruct-v1:0bedrock | — | $0.15 | $0.15 | — | — | — | 128K | |
| QwQ-32Bnebius | — | $0.15 | $0.45 | — | — | — | 33K | |
| gpt-oss-120b💬nebius | 1366 | $0.15 | $0.60 | $0.10 | — | — | 131K | |
| Qwen3-Next-80B-A3B-Thinking🧮nebius | 1368 | $0.15 | $1.20 | — | — | — | 128K | |
| GLM-5.3-Flash💬nebius | 1471 | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| nvidia.nemotron-super-3-120bbedrock_converse | — | $0.15 | $0.65 | — | — | $0.0750 / $0.33 | 256K | |
| google.gemini-2.5-flashoci | — | $0.15 | $0.60 | — | — | — | 1.0M | |
| cohere.command-r-08-2024oci | — | $0.15 | $0.15 | — | — | — | 128K | |
| openai.gpt-oss-120boci | — | $0.15 | $0.60 | — | — | — | 128K | |
| openai.gpt-oss-120b-1:0bedrock_converse | — | $0.15 | $0.60 | — | — | $0.0750 / $0.30 | 128K | |
| openai.gpt-oss-safeguard-120bbedrock_converse | — | $0.15 | $0.60 | — | — | $0.0700 / $0.30 | 128K | |
| qwen.qwen3-coder-30b-a3b-v1:0bedrock_converse | — | $0.15 | $0.60 | — | — | $0.0750 / $0.30 | 262K | |
| qwen.qwen3-32b-v1:0bedrock_converse | — | $0.15 | $0.60 | — | — | $0.0750 / $0.30 | 33K | |
| qwen.qwen3-next-80b-a3bbedrock_converse | — | $0.15 | $1.20 | — | — | — | 256K | |
| gpt-4o-mini💬replicate | — | $0.15 | $0.60 | — | — | — | — | |
| DeepSeek-V4.1-flash💬scx-ai | — | $0.15 | $0.60 | $0.0100 | — | — | 1.0M | |
| llama3.2-3bsnowflake | — | $0.15 | $0.15 | — | — | — | 128K | |
| mistral-7bsnowflake | — | $0.15 | $0.20 | — | — | — | 32K | |
| gpt-oss-120b💬together_ai | 1366 | $0.15 | $0.60 | — | — | — | 131K | |
| MiniMax-M3.1-Flash💬together_ai | — | $0.15 | $0.60 | $0.0150 | — | — | 1.0M | |
| GLM-5.3-Flash💬together_ai | 1471 | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| command-rvercel_ai_gateway | — | $0.15 | $0.60 | — | — | — | 128K | |
| llama-3.2-3bvercel_ai_gateway | — | $0.15 | $0.15 | — | — | — | 128K | |
| codestral-embedvercel_ai_gateway | — | $0.15 | free | — | — | — | 0 | |
| pixtral-12bvercel_ai_gateway | — | $0.15 | $0.15 | — | — | — | 128K | |
| gpt-4o-mini💬vercel_ai_gateway | — | $0.15 | $0.60 | $0.0750 | free | — | 128K | |
| mistral-nemo@latestvertex_ai-mistral_models | — | $0.15 | $0.15 | — | — | — | 128K | |
| gemma-4-26b-a4b-it-maasvertex_ai-openai_models | — | $0.15 | $0.60 | $0.0150 | — | — | 262K | |
| qwen3-next-80b-a3b-instruct-maasvertex_ai-qwen_models | — | $0.15 | $1.20 | — | — | — | 262K | |
| qwen3-next-80b-a3b-thinking-maasvertex_ai-qwen_models | — | $0.15 | $1.20 | — | — | — | 262K | |
| llama-3-2-3b-instruct💬watsonx | 1110 | $0.15 | $0.15 | — | — | — | 128K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068014h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023014h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078414h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039914h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4214h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6214h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6014h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2614h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070014h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3614h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090014h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1814h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0014h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3314h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050014h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9614h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3214h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1814h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060014h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2314h
Price cuts are green — they make AI cheaper for everyone.