💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 18h. 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 |
|---|---|---|---|---|---|---|---|---|
| google.gemma-3-27b-itbedrock_converse | — | $0.23 | $0.38 | — | — | $0.12 / $0.19 | 128K | |
| qwen.qwen3-32bbedrock_mantle | — | $0.23 | $0.93 | — | — | — | 32K | |
| qwen.qwen3-235b-a22b-2507bedrock_mantle | — | $0.23 | $0.91 | — | — | — | 256K | |
| nvidia.nemotron-nano-12b-v2bedrock_mantle | — | $0.23 | $0.70 | — | — | — | 128K | |
| mistral.ministral-3-14b-instructbedrock_mantle | — | $0.23 | $0.23 | — | — | — | 128K | |
| nvidia.nemotron-nano-12b-v2bedrock_mantle | — | $0.23 | $0.70 | — | — | — | 128K | |
| Llama-3.3-70B-Instruct💬deepinfra | 1274 | $0.23 | $0.40 | — | — | — | 131K | |
| mistral.ministral-3-14b-instructbedrock_converse | — | $0.23 | $0.23 | — | — | — | 128K | |
| openai.gpt-oss-120bbedrock_mantle | — | $0.23 | $0.93 | — | — | — | 131K | |
| mistral.ministral-3-8b-instructbedrock_mantle | — | $0.23 | $0.23 | — | — | — | 128K | |
| nvidia.nemotron-nano-12b-v2bedrock_converse | — | $0.23 | $0.70 | — | — | — | 128K | |
| openai.gpt-oss-safeguard-120bbedrock_mantle | — | $0.23 | $0.93 | — | — | — | 131K | |
| qwen.qwen3-coder-30b-a3b-instructbedrock_mantle | — | $0.23 | $0.93 | — | — | — | 256K | |
| mistral.ministral-3-14b-instructbedrock_converse | — | $0.23 | $0.23 | — | — | — | 128K | |
| qwen.qwen3-235b-a22b-2507bedrock_mantle | — | $0.23 | $0.91 | — | — | — | 256K | |
| glm-5p3-flash-usfireworks_ai | — | $0.23 | $0.75 | $0.0450 | — | — | 1.0M | |
| minimax-m3💬empiriolabs | 1427 | $0.23 | $0.90 | $0.0450 | — | — | 1.0M | |
| glm-5p3-flash-usfireworks_ai | — | $0.23 | $0.75 | $0.0450 | — | — | 1.0M | |
| step-3.7-flash💬kyma | — | $0.22 | $1.28 | $0.0540 | — | — | 256K | |
| databricks-qwen35-122b-a10bdatabricks | — | $0.22 | $2.20 | $0.22 | $0.22 | — | 262K | |
| qwen3-vl-235b-a22b-instruct👁️fireworks_ai | 1420 | $0.22 | $0.88 | — | — | — | 262K | |
| glm-4p5-airfireworks_ai | — | $0.22 | $0.88 | — | — | — | 131K | |
| meta.llama3-1-8b-instruct-v1:0bedrock | — | $0.22 | $0.22 | — | — | $0.11 / $0.11 | 128K | |
| qwen3-235b-a22b-instruct-2507fireworks_ai | — | $0.22 | $0.88 | — | — | — | 262K | |
| qwen3-vl-235b-a22b-thinking🧮fireworks_ai | 1401 | $0.22 | $0.88 | — | — | — | 262K | |
| llama4-maverick-instruct-basicfireworks_ai | — | $0.22 | $0.88 | — | — | — | 131K | |
| us.meta.llama3-1-8b-instruct-v1:0bedrock | — | $0.22 | $0.22 | — | — | $0.11 / $0.11 | 128K | |
| llama3.1-8bsnowflake | — | $0.22 | $0.22 | — | — | — | 128K | |
| deepseek-v4-flash-0731💬fireworks_ai | — | $0.22 | $0.66 | $0.0070 | — | — | 1.0M | |
| gpt-5.4-nano💬azure | — | $0.22 | $1.38 | $0.0220 | — | $0.11 / $0.69 | — | |
| deepseek-v4-flash-vision-exp👁️fireworks_ai | — | $0.22 | $0.66 | $0.0070 | — | — | 1.0M | |
| deepseek-v4-flash-vision-exp👁️fireworks_ai | — | $0.22 | $0.66 | $0.0070 | — | — | 1.0M | |
| us.openai.gpt-5.6-lunabedrock_converse | — | $0.22 | $1.32 | $0.0220 | $0.28 | — | 922K | |
| gpt-5.6-luna💬azure | — | $0.22 | $1.32 | $0.0220 | $0.28 | — | 922K | |
| gpt-oss-120b💬sambanova | 1366 | $0.22 | $0.59 | — | — | — | 131K | |
| gpt-5.4-nano💬azure | — | $0.22 | $1.38 | $0.0220 | — | $0.11 / $0.69 | — | |
| qwen3-235b-a22b-thinking-2507🧮fireworks_ai | 1416 | $0.22 | $0.88 | — | — | — | 262K | |
| deepseek-v4-flash-0731💬fireworks_ai | — | $0.22 | $0.66 | $0.0070 | — | — | 1.0M | |
| qwen3-235b-a22b-instruct-2507-maasvertex_ai-qwen_models | — | $0.22 | $0.88 | — | — | $0.11 / $0.44 | 262K | |
| Llama-3.1-8B-Instruct💬wandb | 1187 | $0.22 | $0.22 | — | — | — | 128K | |
| qwen3-coder-480b-a35b-instruct-maasvertex_ai-qwen_models | — | $0.22 | $1.80 | $0.0220 | — | $0.11 / $0.90 | 262K | |
| gpt-5.6-luna💬azure | — | $0.22 | $1.32 | $0.0220 | $0.28 | — | 922K | |
| qwen.qwen3-235b-a22b-2507bedrock_mantle | — | $0.22 | $0.88 | — | — | $0.11 / $0.44 | 256K | |
| step-3.7-flash💬aihubmix | — | $0.22 | $1.32 | $0.0440 | — | — | 256K | |
| qwen.qwen3-235b-a22b-2507-v1:0bedrock_converse | — | $0.22 | $0.88 | — | — | $0.11 / $0.44 | 262K | |
| qwen3-235b-a22b💬fireworks_ai | 1366 | $0.22 | $0.88 | — | — | — | 131K | |
| qwen.qwen3-next-80b-a3b-instructbedrock_mantle | — | $0.22 | $1.86 | — | — | — | 256K | |
| MiniMax-M2.7💬gmi | 1405 | $0.21 | $0.84 | $0.0420 | — | — | 197K | |
| gpt-4o-mini💬azure | — | $0.21 | $0.82 | $0.10 | — | — | 128K | |
| mistral.ministral-3-14b-instructbedrock_mantle | — | $0.21 | $0.21 | — | — | — | 128K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068013h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023013h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078413h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039913h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4213h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6213h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6013h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2613h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070013h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3613h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090013h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1813h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0013h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3313h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050013h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9613h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3213h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1813h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060013h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2313h
Price cuts are green — they make AI cheaper for everyone.