💲 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 |
|---|---|---|---|---|---|---|---|---|
| llama-v3-8b-instruct-hffireworks_ai | — | $0.20 | $0.20 | — | — | — | 8K | |
| pixtral-12b-2409scaleway | — | $0.20 | $0.20 | — | — | — | 128K | |
| GLM-4.5-Air-FP8gmi | — | $0.20 | $1.10 | — | — | — | 131K | |
| mistral.mistral-7b-instruct-v0:2bedrock | — | $0.20 | $0.26 | — | — | — | 32K | |
| qwen3-coder-30b-a3b-instruct💻scaleway | — | $0.20 | $0.80 | — | — | — | 128K | |
| gemma-2-9bvercel_ai_gateway | — | $0.20 | $0.20 | — | — | — | 8K | |
| zephyr-7b-betafireworks_ai | — | $0.20 | $0.20 | — | — | — | 33K | |
| MAI-Code-1.1-Flashazure_ai | — | $0.20 | $1.20 | $0.0200 | — | — | 256K | |
| qwen3-vl-30b-a3b-thinking🧮novita | — | $0.20 | $1.00 | — | — | — | 131K | |
| qwen3-vl-30b-a3b-instruct👁️novita | — | $0.20 | $0.70 | — | — | — | 131K | |
| llama-v2-13b-chatfireworks_ai | — | $0.20 | $0.20 | — | — | — | 4K | |
| pythia-12bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 2K | |
| llama-v2-7bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 4K | |
| gpt-oss-120b💬inferenceapis | 1366 | $0.20 | $0.80 | — | — | — | 131K | |
| qwen-v2p5-14b-instructfireworks_ai | — | $0.20 | $0.20 | — | — | — | 33K | |
| qwen-v2p5-7bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 131K | |
| qwen2-7b-instructfireworks_ai | — | $0.20 | $0.20 | — | — | — | 33K | |
| qwen2-vl-7b-instructfireworks_ai | — | $0.20 | $0.20 | — | — | — | 33K | |
| qwen2p5-14bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 131K | |
| Nemotron-Content-Safety-3.5deepinfra | — | $0.20 | $0.20 | — | — | — | 131K | |
| databricks-gpt-5-6-lunadatabricks | — | $0.20 | $1.20 | $0.0200 | $0.25 | — | 922K | |
| databricks-gpt-5-4-nanodatabricks | — | $0.20 | $1.25 | $0.0200 | $0.20 | — | 272K | |
| GLM-5.3-Flash💬openinfer | 1471 | $0.20 | $1.56 | — | — | — | 393K | |
| Qwen3.5-27B💬openinfer | 1409 | $0.20 | $1.56 | — | — | — | 33K | |
| deepseek-v3inferenceapis | — | $0.19 | $0.38 | $0.0400 | — | — | 1.0M | |
| deepseek-reasonerinferenceapis | — | $0.19 | $0.38 | $0.0400 | — | — | 1.0M | |
| mamba-codestral-7B-v0.1ovhcloud | — | $0.19 | $0.19 | — | — | — | 256K | |
| deepseek-chat💬inferenceapis | 1333 | $0.19 | $0.38 | $0.0400 | — | — | 1.0M | |
| DeepSeek-V4-Flash💬inferenceapis | 1432 | $0.19 | $0.38 | $0.0400 | — | — | 1.0M | |
| eu.meta.llama3-2-3b-instruct-v1:0bedrock | — | $0.19 | $0.19 | — | — | — | 128K | |
| deepseek-v4-flash💬azure_ai | 1432 | $0.19 | $0.51 | $0.0280 | — | — | 1.0M | |
| meta.llama3-2-3b-instruct-v1:0bedrock | — | $0.19 | $0.19 | — | — | — | 128K | |
| DeepSeek-V4-Flash-0731💬inferenceapis | — | $0.19 | $0.38 | $0.0400 | — | — | 1.0M | |
| DeepSeek-V3inferenceapis | — | $0.19 | $0.38 | $0.0400 | — | — | 1.0M | |
| deepseek-v4-flash💬inferenceapis | 1432 | $0.19 | $0.38 | $0.0400 | — | — | 1.0M | |
| mimo-v2.6-flash💬kyma | 1450 | $0.19 | $0.38 | — | — | — | 1.1M | |
| FW-GLM-5.3-Flashazure_ai | — | $0.19 | $0.63 | $0.0380 | — | — | 1.0M | |
| mimo-v2.5💬kyma | 1428 | $0.19 | $0.37 | — | — | — | 1.1M | |
| writer.palmyra-vision-7bbedrock_converse | — | $0.18 | $0.72 | — | — | — | 4K | |
| mistral.ministral-3-8b-instructbedrock_mantle | — | $0.18 | $0.18 | — | — | — | 128K | |
| nvidia.nemotron-super-3-120bbedrock | — | $0.18 | $0.78 | — | — | $0.0900 / $0.39 | 256K | |
| openai.gpt-oss-120b-1:0bedrock | — | $0.18 | $0.72 | — | — | $0.0900 / $0.36 | 128K | |
| nvidia.nemotron-super-3-120bbedrock_mantle | — | $0.18 | $0.78 | — | — | — | 256K | |
| openai.gpt-oss-safeguard-120bbedrock_mantle | — | $0.18 | $0.72 | — | — | — | 131K | |
| nvidia.nemotron-super-3-120bbedrock | — | $0.18 | $0.78 | — | — | $0.0900 / $0.39 | 256K | |
| openai.gpt-oss-120b-1:0bedrock | — | $0.18 | $0.72 | — | — | $0.0900 / $0.36 | 128K | |
| QwQ-32Bnscale | — | $0.18 | $0.20 | — | — | — | — | |
| openai.gpt-oss-120bbedrock_mantle | — | $0.18 | $0.72 | — | — | $0.0900 / $0.36 | 131K | |
| openai.gpt-oss-120bbedrock_mantle | — | $0.18 | $0.72 | — | — | $0.0900 / $0.36 | 131K | |
| writer.palmyra-vision-7bbedrock_mantle | — | $0.18 | $0.72 | — | — | — | 4K |
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.