💲 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 |
|---|---|---|---|---|---|---|---|---|
| qwen.qwen3-32bbedrock_mantle | — | $0.20 | $0.79 | — | — | — | 32K | |
| qwen.qwen3-coder-30b-a3b-instructbedrock_mantle | — | $0.20 | $0.79 | — | — | — | 256K | |
| gpt-5.6-luna💬openai | — | $0.20 | $1.20 | $0.0200 | $0.25 | $0.10 / $0.60 | 922K | |
| QwQ-32Bhyperbolic | — | $0.20 | $0.20 | — | — | — | 131K | |
| llama-guard-4-12b🛡️replicate | — | $0.20 | $0.20 | — | — | — | — | |
| glm-4.5-air💬zai | 1384 | $0.20 | $1.10 | — | — | — | 128K | |
| gpt-5.6-luna💬zerogpu | — | $0.20 | $1.20 | $0.20 | — | — | 272K | |
| chronos-hermes-13b-v2fireworks_ai | — | $0.20 | $0.20 | — | — | — | 4K | |
| gemma-4-31b-it💬aiand | — | $0.20 | $0.50 | $0.0500 | — | — | 262K | |
| code-llama-13b-pythonfireworks_ai | — | $0.20 | $0.20 | — | — | — | 16K | |
| code-llama-13b-instructfireworks_ai | — | $0.20 | $0.20 | — | — | — | 16K | |
| code-llama-13bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 16K | |
| hermes-2-pro-mistral-7bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 33K | |
| meta.llama3-2-3b-instruct-v1:0bedrock | — | $0.20 | $0.20 | — | — | — | 128K | |
| eu.meta.llama3-2-3b-instruct-v1:0bedrock | — | $0.20 | $0.20 | — | — | — | 128K | |
| llama-3.1-8b-instruct💬perplexity | 1187 | $0.20 | $0.20 | — | — | — | 131K | |
| grok-4.1-fast-reasoningvertex_ai | — | $0.20 | $0.50 | $0.0500 | — | — | 128K | |
| deepseek-v4-flash-0731💬qwen_ai_platform | — | $0.20 | $0.40 | $0.0400 | — | — | 1.0M | |
| deepseek-v4-flash💬qwen_ai_platform | 1432 | $0.20 | $0.40 | $0.0400 | — | — | 1.0M | |
| glm-5.3-flash💬inferenceapis | 1471 | $0.20 | $0.66 | $0.0400 | — | — | 1.0M | |
| global.openai.gpt-5.6-lunabedrock_converse | — | $0.20 | $1.20 | $0.0200 | $0.25 | — | 922K | |
| mistral.mistral-7b-instruct-v0:2bedrock | — | $0.20 | $0.26 | — | — | — | 32K | |
| internvl3-8bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 16K | |
| gpt-oss-120b💬inferenceapis | 1366 | $0.20 | $0.80 | — | — | — | 131K | |
| llama-3.1-8b-instantinferenceapis | — | $0.20 | $0.50 | — | — | — | 131K | |
| llama-3.3-70binferenceapis | — | $0.20 | $0.50 | — | — | — | 131K | |
| deepseek-v4-flash-0731💬qwencloud | — | $0.20 | $0.40 | $0.0400 | — | — | 1.0M | |
| deepseek-v4-flash💬qwencloud | 1432 | $0.20 | $0.40 | $0.0400 | — | — | 1.0M | |
| grok-4.1-fast-non-reasoningvertex_ai | — | $0.20 | $0.50 | $0.0500 | — | — | 128K | |
| deepseek-r1-distill-qwen-7bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 131K | |
| mistral.ministral-3-14b-instructbedrock_mantle | — | $0.20 | $0.20 | — | — | $0.10 / $0.10 | 128K | |
| llama-3.3-70b-instruct💬inferenceapis | 1274 | $0.20 | $0.50 | — | — | — | 131K | |
| together-ai-4.1b-8btogether_ai | — | $0.20 | $0.20 | — | — | — | — | |
| deepseek-v4-flash-0731💬dashscope | — | $0.20 | $0.40 | $0.0400 | — | — | 1.0M | |
| deepseek-v4-flash💬dashscope | 1432 | $0.20 | $0.40 | $0.0400 | — | — | 1.0M | |
| llama-3.3-70b-versatileinferenceapis | — | $0.20 | $0.50 | — | — | — | 131K | |
| Step-3.7-Flash💬deepinfra | — | $0.20 | $1.15 | $0.0400 | — | — | 262K | |
| nvidia.nemotron-nano-12b-v2bedrock_mantle | — | $0.20 | $0.60 | — | — | $0.10 / $0.30 | 128K | |
| llama-guard-2-8bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 8K | |
| Llama-3.3-70B-Instruct💬inferenceapis | 1274 | $0.20 | $0.50 | — | — | — | 131K | |
| qwen3-235b-a22b-fp8novita | — | $0.20 | $0.80 | — | — | — | 41K | |
| qwen2p5-7b-instructfireworks_ai | — | $0.20 | $0.20 | — | — | — | 33K | |
| llama-v2-7b-chatfireworks_ai | — | $0.20 | $0.20 | — | — | — | 4K | |
| qwen2p5-coder-14bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 33K | |
| r1v4-litenovita | — | $0.20 | $0.60 | — | — | — | 262K | |
| qwen2p5-coder-14b-instructfireworks_ai | — | $0.20 | $0.20 | — | — | — | 33K | |
| qwen-3-235bvercel_ai_gateway | — | $0.20 | $0.60 | — | — | — | 41K | |
| llama-v3-8bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 8K | |
| Step-3.7-Flash💬gmi | — | $0.20 | $1.15 | $0.0400 | — | — | 256K | |
| NVIDIA-Nemotron-3.5-Super-VL-120B-A12Bbaseten | — | $0.20 | $0.50 | $0.0400 | — | — | 1.0M |
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.