💲 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 |
|---|---|---|---|---|---|---|---|---|
| nvidia.nemotron-nano-3-30bbedrock_converse | — | $0.0900 | $0.37 | — | — | — | 256K | |
| mythomax-l2-13b💬novita | — | $0.0900 | $0.0900 | — | — | — | 4K | |
| qwen3-30b-a3b-fp8novita | — | $0.0900 | $0.45 | — | — | — | 41K | |
| nvidia.nemotron-nano-9b-v2bedrock_converse | — | $0.0900 | $0.36 | — | — | — | 128K | |
| gpt-oss-20b💬replicate | 1288 | $0.0900 | $0.36 | — | — | — | — | |
| Qwen3-Next-80B-A3B-Instruct💬deepinfra | 1417 | $0.0900 | $1.10 | — | — | — | 262K | |
| nvidia.nemotron-nano-3-30bbedrock_mantle | — | $0.0900 | $0.37 | — | — | — | 256K | |
| gemma-4-31B-it-turbodeepinfra | — | $0.0900 | $0.34 | $0.0500 | — | — | 262K | |
| nvidia.nemotron-nano-9b-v2bedrock_mantle | — | $0.0900 | $0.36 | — | — | — | 128K | |
| qwen3-30b-a3b💬pinstripes | 1317 | $0.0900 | $0.20 | — | — | — | 131K | |
| qwen3-5-9b💬empiriolabs | — | $0.0900 | $0.13 | $0.0450 | — | — | 262K | |
| qwen3-5-flashempiriolabs | — | $0.0900 | $0.37 | — | — | — | 996K | |
| google.gemma-3-12b-itbedrock_mantle | — | $0.0900 | $0.29 | — | — | $0.0500 / $0.15 | 128K | |
| google.gemma-3-12b-itbedrock_converse | — | $0.0900 | $0.29 | — | — | $0.0500 / $0.15 | 128K | |
| Llama-4-Scout-17B-16E-Instructnscale | — | $0.0900 | $0.29 | — | — | — | — | |
| Qwen3-235B-A22B-Instruct-2507deepinfra | — | $0.0900 | $0.55 | — | — | — | 262K | |
| Mistral-Small-3.2-24B-Instruct-2506ovhcloud | — | $0.0900 | $0.28 | — | — | — | 128K | |
| openai.gpt-oss-20b-1:0bedrock_converse | — | $0.0900 | $0.40 | — | — | — | 128K | |
| openai.gpt-oss-20bbedrock_mantle | — | $0.0900 | $0.40 | — | — | — | 131K | |
| qwen3-235b-a22b-instruct-2507novita | — | $0.0900 | $0.58 | — | — | — | 131K | |
| gpt-oss-120b-maasvertex_ai-openai_models | — | $0.0900 | $0.36 | — | — | $0.0450 / $0.18 | 131K | |
| cohere.command-a-translate-08-2025oci | — | $0.0900 | $0.0900 | — | — | — | 256K | |
| DeepSeek-V4-Flash-0731💬sail | — | $0.0900 | $0.18 | $0.0200 | — | — | 1.0M | |
| DeepSeek-V4.1-Flash💬sail | — | $0.0900 | $0.30 | $0.0060 | — | — | 1.0M | |
| openai.gpt-oss-20b-1:0bedrock_converse | — | $0.0900 | $0.40 | — | — | — | 128K | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0880 | $0.35 | $0.0220 | — | — | 300K | |
| eu.amazon.nova-lite-v1:0bedrock_converse | — | $0.0880 | $0.35 | $0.0220 | — | — | 300K | |
| Qwen3-235B-A22B-Instruct-2507-FP8gmi | — | $0.0875 | $0.35 | $0.0175 | — | — | 262K | |
| qwen3-5-27b💬empiriolabs | 1409 | $0.0860 | $0.69 | — | — | — | 258K | |
| openai.gpt-oss-safeguard-20bbedrock_mantle | — | $0.0840 | $0.24 | — | — | — | 131K | |
| us-gov.openai.gpt-oss-20b-1:0bedrock_converse | — | $0.0840 | $0.36 | — | — | — | 128K | |
| openai.gpt-oss-20bbedrock_mantle | — | $0.0840 | $0.36 | — | — | $0.0420 / $0.18 | 131K | |
| openai.gpt-oss-safeguard-20bbedrock_mantle | — | $0.0840 | $0.24 | — | — | — | 131K | |
| openai.gpt-oss-20bbedrock_mantle | — | $0.0840 | $0.36 | — | — | $0.0420 / $0.18 | 131K | |
| openai.gpt-oss-20b-1:0bedrock | — | $0.0840 | $0.36 | — | — | $0.0420 / $0.18 | 128K | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0840 | $0.34 | — | — | — | 300K | |
| openai.gpt-oss-safeguard-20bbedrock_mantle | — | $0.0840 | $0.24 | — | — | — | 131K | |
| openai.gpt-oss-20b-1:0bedrock | — | $0.0840 | $0.36 | — | — | $0.0420 / $0.18 | 128K | |
| apac.amazon.nova-lite-v1:0bedrock_converse | — | $0.0810 | $0.32 | $0.0203 | — | — | 300K | |
| glm-4.7-flash💬kyma | 1351 | $0.0810 | $0.54 | $0.0135 | — | — | 203K | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0810 | $0.32 | $0.0203 | — | — | 300K | |
| nemotron-3.5-super-vl👁️kyma | — | $0.0810 | $0.47 | $0.0135 | — | — | 1.0M | |
| openai.gpt-oss-20bbedrock_mantle | — | $0.0800 | $0.35 | — | — | — | 131K | |
| zai.glm-4.7-flashbedrock_converse | — | $0.0800 | $0.48 | — | — | — | 203K | |
| openai.gpt-oss-safeguard-20bbedrock_converse | — | $0.0800 | $0.24 | — | — | — | 128K | |
| openai.gpt-oss-20b-1:0bedrock_converse | — | $0.0800 | $0.36 | — | — | — | 128K | |
| Qwen3-32B💬ovhcloud | 1340 | $0.0800 | $0.23 | — | — | — | 32K | |
| gpt-oss-120b💬ovhcloud | 1366 | $0.0800 | $0.40 | — | — | — | 131K | |
| qwen3-vl-8b-instruct👁️novita | — | $0.0800 | $0.50 | — | — | — | 131K | |
| dolphin3-8bllamagate | — | $0.0800 | $0.15 | — | — | — | 128K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068016h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023016h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078416h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039916h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4216h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6216h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6016h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2616h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070016h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3616h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090016h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1816h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0016h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3316h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050016h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9616h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3216h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1816h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060016h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2316h
Price cuts are green — they make AI cheaper for everyone.