💲 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 |
|---|---|---|---|---|---|---|---|---|
| grok-3-miniazure_ai | — | $0.25 | $1.27 | — | — | — | — | |
| Qwen3.5-35B-A3B💬wandb | 1395 | $0.25 | $1.25 | — | — | — | 262K | |
| claude-3-haiku💬vertex_ai-anthropic_models | — | $0.25 | $1.25 | — | — | — | 200K | |
| DeepSeek-R1-Distill-Llama-70B🧮nebius | — | $0.25 | $0.75 | — | — | — | 128K | |
| gemma-4-26b-a4b-it💬scaleway | — | $0.25 | $0.50 | — | — | — | 256K | |
| mercury-2💬inception | 1355 | $0.25 | $0.75 | $0.0250 | — | — | 128K | |
| llama-4-scout-17b-128e-instruct-maasvertex_ai-llama_models | — | $0.25 | $0.70 | — | — | $0.13 / $0.35 | 10.0M | |
| claude-3-haiku@20240307vertex_ai-anthropic_models | — | $0.25 | $1.25 | — | — | — | 200K | |
| Qwen2.5-VL-72B-Instruct👁️nebius | — | $0.25 | $0.75 | — | — | — | 32K | |
| claude-3-haiku💬vercel_ai_gateway | — | $0.25 | $1.25 | $0.0300 | $0.30 | — | 200K | |
| openai.gpt-5-minioci | — | $0.25 | $2.00 | — | — | — | 272K | |
| Llama-4-Maverick-17B-128E-Instruct-FP8gmi | — | $0.25 | $0.80 | — | — | — | 1.0M | |
| Llama-3.3-70B-Instruct💬gmi | 1274 | $0.25 | $0.75 | — | — | — | 131K | |
| beamnebius | — | $0.25 | $1.00 | $0.0500 | — | — | 1.0M | |
| gemini-3.1-flash-lite-preview💬vertex_ai-language-models | 1416 | $0.25 | $1.50 | $0.0250 | — | — | 1.0M | |
| qwen3-6-flash💬empiriolabs | — | $0.25 | $1.50 | — | — | — | 984K | |
| gemini-3.1-flash-lite-preview💬gmi | 1416 | $0.25 | $1.50 | $0.0250 | — | — | 1.0M | |
| gemini-3.1-flash-lite💬gemini | — | $0.25 | $1.50 | $0.0250 | — | $0.13 / $0.75 | 1.0M | |
| mercury-coder-smallvercel_ai_gateway | — | $0.25 | $1.00 | — | — | — | 32K | |
| llama-4-maverick-instructreplicate | — | $0.25 | $0.95 | — | — | — | — | |
| Llama-2-13b-chat-hfanyscale | — | $0.25 | $0.25 | — | — | — | 4K | |
| mistral.mistral-7b-instruct-v0:2bedrock | — | $0.25 | $0.34 | — | — | — | 32K | |
| gpt-5-mini-2025-08-07openai | — | $0.25 | $2.00 | $0.0250 | — | $0.13 / $1.00 | 272K | |
| gemini-3.1-flash-lite💬vertex_ai-language-models | — | $0.25 | $1.50 | $0.0250 | — | $0.13 / $0.75 | 1.0M | |
| openai-gpt-5-minisnowflake | — | $0.25 | $2.00 | $0.0300 | — | — | 1.0M | |
| qwen3.5-35b-a3b💬novita | 1395 | $0.25 | $2.00 | — | — | — | 262K | |
| llama-4-scout-17b-16e-instruct-maasvertex_ai-llama_models | — | $0.25 | $0.70 | — | — | $0.13 / $0.35 | 10.0M | |
| gemini-3.1-flash-lite-preview💬gemini | 1416 | $0.25 | $1.50 | $0.0250 | — | $0.13 / $0.75 | 1.0M | |
| qwen3-omni-30b-a3b-thinkingnovita | — | $0.25 | $0.97 | — | — | — | 66K | |
| gpt-5-mini💬github_copilot | — | $0.25 | $2.00 | $0.0250 | — | — | 128K | |
| qwen3.6-35b-a3b💬scaleway | — | $0.25 | $1.50 | — | — | — | 256K | |
| gpt-5-mini💬replicate | — | $0.25 | $2.00 | — | — | — | — | |
| Llama-4-Maverick-17B-128E-Instruct-FP8azure_ai | — | $0.25 | $1.00 | — | — | — | 1.0M | |
| gpt-5-mini-2025-08-07azure | — | $0.25 | $2.00 | $0.0250 | — | $0.13 / $1.00 | 272K | |
| DeepSeek-R1-Distill-Llama-70B🧮gmi | — | $0.25 | $0.75 | — | — | — | 131K | |
| gpt-5-mini💬azure | — | $0.25 | $2.00 | $0.0250 | — | $0.13 / $1.00 | 272K | |
| DeepSeek-R1-0528🧮hyperbolic | 1428 | $0.25 | $0.25 | — | — | — | 131K | |
| codestral-mamba-latestmistral | — | $0.25 | $0.25 | $0.0250 | — | — | 256K | |
| Seed-1.8deepinfra | — | $0.25 | $2.00 | $0.0500 | — | — | 256K | |
| gemini-3.1-flash-lite💬vertex_ai-language-models | — | $0.25 | $1.50 | $0.0250 | — | $0.13 / $0.75 | 1.0M | |
| gemini-3.1-flash-lite-preview💬vertex_ai-language-models | 1416 | $0.25 | $1.50 | $0.0250 | — | — | 1.0M | |
| deepseek-v4-flash-thinkinglibertai | — | $0.25 | $1.75 | — | — | — | 200K | |
| deepseek-v4-flash💬libertai | 1432 | $0.25 | $1.75 | — | — | — | 200K | |
| qwen3.5-122b-a10b-thinkinglibertai | — | $0.25 | $1.75 | — | — | — | 262K | |
| qwen3.5-122b-a10b💬libertai | 1418 | $0.25 | $1.75 | — | — | — | 262K | |
| mistral-tinymistral | — | $0.25 | $0.25 | $0.0250 | — | — | 32K | |
| MiniMax-M2.7💬deepinfra | 1405 | $0.25 | $1.00 | $0.0500 | — | — | 197K | |
| gpt-5-mini💬openai | — | $0.25 | $2.00 | $0.0250 | — | $0.13 / $1.00 | 272K | |
| Qwen3.5-35B-A3B💬gmi | 1395 | $0.25 | $2.00 | — | — | — | 262K | |
| DeepSeek-V3.1deepinfra | — | $0.25 | $0.95 | $0.13 | — | — | 164K |
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.