💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 20h. 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 |
|---|---|---|---|---|---|---|---|---|
| mistral.voxtral-small-24b-2507bedrock_mantle | — | $0.12 | $0.35 | — | — | — | 33K | |
| GLM-5.3-Flash💬wandb | 1471 | $0.12 | $0.38 | $0.0200 | — | — | 1.0M | |
| morph-dsv41flash-1017morph | — | $0.12 | $0.80 | $0.0080 | — | — | 1.0M | |
| morph-dsv41flashmorph | — | $0.12 | $0.80 | $0.0080 | — | — | 1.0M | |
| mistral.voxtral-small-24b-2507bedrock_converse | — | $0.12 | $0.35 | — | — | — | 33K | |
| mistral.voxtral-small-24b-2507bedrock_mantle | — | $0.12 | $0.36 | — | — | — | 33K | |
| mistral.ministral-3-3b-instructbedrock_mantle | — | $0.12 | $0.12 | — | — | — | 128K | |
| mistral.voxtral-small-24b-2507bedrock_converse | — | $0.12 | $0.35 | — | — | — | 33K | |
| mistral.ministral-3-3b-instructbedrock_mantle | — | $0.12 | $0.12 | — | — | — | 128K | |
| Hermes-3-Llama-3.1-70B💬hyperbolic | — | $0.12 | $0.30 | — | — | — | 33K | |
| embed-v4.0vercel_ai_gateway | — | $0.12 | free | — | — | — | 0 | |
| Qwen2.5-72B-Instructhyperbolic | — | $0.12 | $0.30 | — | — | — | 131K | |
| Qwen2.5-Coder-32B-Instructhyperbolic | — | $0.12 | $0.30 | — | — | — | 33K | |
| glm-5.3-flash-abliteratedrefuseless | — | $0.12 | $0.50 | $0.0400 | — | — | 1.0M | |
| Llama-3.2-3B-Instruct💬hyperbolic | 1110 | $0.12 | $0.30 | — | — | — | 33K | |
| Llama-3.3-70B-Instruct💬hyperbolic | 1274 | $0.12 | $0.30 | — | — | — | 131K | |
| Meta-Llama-3-70B-Instructhyperbolic | — | $0.12 | $0.30 | — | — | — | 131K | |
| Meta-Llama-3.1-405B-Instructhyperbolic | — | $0.12 | $0.30 | — | — | — | 33K | |
| Meta-Llama-3.1-70B-Instructhyperbolic | — | $0.12 | $0.30 | — | — | — | 33K | |
| Meta-Llama-3.1-8B-Instructhyperbolic | — | $0.12 | $0.30 | — | — | — | 33K | |
| hermes3-70blambda_ai | — | $0.12 | $0.30 | — | — | — | 131K | |
| llama3.1-70b-instruct-fp8lambda_ai | — | $0.12 | $0.30 | — | — | — | 131K | |
| llama3.1-nemotron-70b-instruct-fp8lambda_ai | — | $0.12 | $0.30 | — | — | — | 131K | |
| llama3.3-70b-instruct-fp8lambda_ai | — | $0.12 | $0.30 | — | — | — | 131K | |
| mistral.voxtral-small-24b-2507bedrock_mantle | — | $0.12 | $0.35 | — | — | — | 33K | |
| mistral.ministral-3-3b-instructbedrock_mantle | — | $0.12 | $0.12 | — | — | — | 128K | |
| mistral.voxtral-small-24b-2507bedrock_mantle | — | $0.12 | $0.36 | — | — | — | 33K | |
| mistral.voxtral-small-24b-2507bedrock | — | $0.12 | $0.36 | — | — | $0.0600 / $0.18 | 33K | |
| mistral.ministral-3-3b-instructbedrock_converse | — | $0.12 | $0.12 | — | — | — | 128K | |
| seed-2-0-mini💬empiriolabs | — | $0.12 | $0.50 | — | — | — | 229K | |
| gpt-6-luna💬azure | — | $0.12 | $0.60 | $0.0120 | $0.15 | — | 922K | |
| mistral.ministral-3-3b-instructbedrock_converse | — | $0.12 | $0.12 | — | — | — | 128K | |
| mistral.ministral-3-3b-instructbedrock_mantle | — | $0.12 | $0.12 | — | — | — | 128K | |
| mistral.voxtral-small-24b-2507bedrock_converse | — | $0.12 | $0.36 | — | — | — | 33K | |
| mistral.ministral-3-3b-instructbedrock_converse | — | $0.12 | $0.12 | — | — | — | 128K | |
| anthropic.claude-haiku-5-5bedrock | — | $0.12 | $0.60 | $0.0120 | $0.15 | — | 1.0M | |
| deepseek-v4.1-flash💬clf_ai_gateway | — | $0.12 | $0.48 | $0.0020 | — | — | 1.0M | |
| mistral.ministral-3-3b-instructbedrock_mantle | — | $0.12 | $0.12 | — | — | — | 128K | |
| mistral.voxtral-small-24b-2507bedrock_mantle | — | $0.12 | $0.36 | — | — | — | 33K | |
| mistral.voxtral-small-24b-2507bedrock_mantle | — | $0.12 | $0.36 | — | — | — | 33K | |
| mistral.ministral-3-3b-instructbedrock_mantle | — | $0.12 | $0.12 | — | — | — | 128K | |
| Qwen3-30B-A3B💬deepinfra | 1317 | $0.12 | $0.50 | — | — | — | 41K | |
| mistral.voxtral-small-24b-2507bedrock_converse | — | $0.12 | $0.35 | — | — | — | 33K | |
| Qwen3-14B💬deepinfra | — | $0.12 | $0.24 | — | — | — | 41K | |
| mistral.ministral-3-3b-instructbedrock_mantle | — | $0.12 | $0.12 | — | — | — | 128K | |
| mistral.voxtral-small-24b-2507bedrock_mantle | — | $0.12 | $0.35 | — | — | — | 33K | |
| mistral.ministral-3-3b-instructbedrock_converse | — | $0.12 | $0.12 | — | — | — | 128K | |
| gemma-3-27b-it💬novita | 1358 | $0.12 | $0.20 | — | — | — | 98K | |
| MiMo-V2.5💬gmi | 1428 | $0.12 | $0.24 | $0.0024 | — | — | 1.1M | |
| qwen3-5-122b-a10b💬empiriolabs | 1418 | $0.12 | $0.92 | — | — | — | 258K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068015h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023015h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078415h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039915h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4215h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6215h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6015h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2615h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070015h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3615h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090015h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1815h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0015h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3315h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050015h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9615h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3215h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1815h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060015h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2315h
Price cuts are green — they make AI cheaper for everyone.