💲 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 | — | $0.10 | $0.31 | — | — | $0.0515 / $0.15 | 33K | |
| databricks-claude-haiku-5-5databricks | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 1.0M | |
| qwen2p5-coder-3bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| DeepSeek-R1-Distill-Qwen-7Bgmi | — | $0.10 | $0.20 | — | — | — | 131K | |
| Qwen3-32B-FP8gmi | — | $0.10 | $0.60 | — | — | — | 33K | |
| gpt-6-luna💬gmi | — | $0.10 | $0.50 | $0.0100 | — | — | 1.1M | |
| step-3-5-flash-2603empiriolabs | — | $0.10 | $0.30 | $0.0200 | — | — | 262K | |
| step-3-5-flash💬empiriolabs | 1403 | $0.10 | $0.30 | $0.0200 | — | — | 262K | |
| claude-haiku-5-5💬bedrock | — | $0.10 | $0.50 | $0.0100 | $0.13 | $0.0500 / $0.25 | 1.0M | |
| claude-haiku-5-5💬opencode_go | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 1.0M | |
| claude-haiku-5-5@defaultvertex_ai-anthropic_models | — | $0.10 | $0.50 | $0.0100 | $0.13 | $0.0500 / $0.25 | 1.0M | |
| claude-haiku-5-5💬vertex_ai-anthropic_models | — | $0.10 | $0.50 | $0.0100 | $0.13 | $0.0500 / $0.25 | 1.0M | |
| global.anthropic.claude-haiku-5-5bedrock_converse | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 1.0M | |
| claude-haiku-5-5💬azure_ai | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 1.0M | |
| anthropic.claude-haiku-5-5bedrock_converse | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 1.0M | |
| claude-haiku-5-5💬anthropic | — | $0.10 | $0.50 | $0.0100 | $0.13 | $0.0500 / $0.25 | 1.0M | |
| gemma-4-26B-A4B-it💬wandb | — | $0.10 | $0.30 | $0.0500 | — | — | 262K | |
| granite-20b-code-instruct-8kreplicate | — | $0.10 | $0.50 | — | — | — | — | |
| Mistral-Small-24B-Instruct-2501💬together_ai | 1234 | $0.10 | $0.30 | — | — | — | 33K | |
| mistral.voxtral-small-24b-2507bedrock_mantle | — | $0.10 | $0.30 | — | — | $0.0500 / $0.15 | 33K | |
| mistral.ministral-3-3b-instructbedrock_mantle | — | $0.10 | $0.10 | — | — | $0.0500 / $0.0500 | 128K | |
| qwen3-30b-a3b-fp8zerogpu | — | $0.10 | $0.45 | $0.0500 | — | — | 33K | |
| gpt-6-luna💬zerogpu | — | $0.10 | $0.50 | $0.0100 | — | — | 272K | |
| glm-5.3-flash💬zerogpu | 1471 | $0.10 | $0.35 | $0.0150 | — | — | 1.0M | |
| Qwen3.5-9B💬deepinfra | — | $0.10 | $0.15 | — | — | — | 262K | |
| Seed-2.0-mini💬deepinfra | — | $0.10 | $0.40 | $0.0200 | — | — | 256K | |
| Qwen3.6-35B-A3B💬deepinfra | — | $0.10 | $0.95 | — | — | — | 262K | |
| Qwen3-30B-A3B-Instruct-2507💬wandb | 1384 | $0.10 | $0.30 | — | — | — | 262K | |
| Qwen3.6-35B-A3B💬wandb | — | $0.10 | $0.89 | $0.0350 | — | — | 262K | |
| gemma-4-31B-it💬wandb | — | $0.10 | $0.34 | — | — | — | 262K | |
| deepseek-v4-flash💬pinstripes | 1432 | $0.10 | $0.20 | — | — | — | 164K | |
| global.openai.gpt-6-lunabedrock_converse | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 922K | |
| openai.gpt-6-lunabedrock_converse | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 922K | |
| llava-7bllamagate | — | $0.10 | $0.20 | — | — | — | 4K | |
| deepseek-r1-8bllamagate | — | $0.10 | $0.20 | — | — | — | 66K | |
| mistral-7b-v0.3llamagate | — | $0.10 | $0.15 | — | — | — | 33K | |
| qwen3-32b-fp8novita | — | $0.10 | $0.45 | — | — | — | 41K | |
| starcoder2-3bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 16K | |
| stablecode-3bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 4K | |
| qwen3-1p7b-fp8-draft-40960fireworks_ai | — | $0.10 | $0.10 | — | — | — | 41K | |
| qwen3-1p7b-fp8-draft-131072fireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| qwen3-1p7b-fp8-draftfireworks_ai | — | $0.10 | $0.10 | — | — | — | 262K | |
| qwen3-1p7bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| qwen3-0p6bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 41K | |
| qwen2p5-coder-3b-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| qwen2p5-coder-1p5b-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| qwen2p5-coder-1p5bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| nemotron-nano-v2-12b-vlfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| ministral-3-3b-instruct-2512fireworks_ai | — | $0.10 | $0.10 | — | — | — | 256K | |
| minimax-m1-80kfireworks_ai | — | $0.10 | $0.10 | — | — | — | 4K |
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.