💲 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 |
|---|---|---|---|---|---|---|---|---|
| Llama-3.3-Nemotron-Super-49B-v1nebius | — | $0.10 | $0.40 | — | — | — | 131K | |
| gemma-3-27b-it💬nebius | 1358 | $0.10 | $0.30 | $0.0400 | — | — | 110K | |
| us.meta.llama3-2-1b-instruct-v1:0bedrock | — | $0.10 | $0.10 | — | — | — | 128K | |
| ministral-3-3b-2512mistral | — | $0.10 | $0.10 | $0.0100 | — | — | 131K | |
| mistral-smallmistral | — | $0.10 | $0.30 | $0.0100 | — | — | 32K | |
| voxtral-small-latestmistral | — | $0.10 | $0.40 | $0.0100 | — | — | 33K | |
| voxtral-small-2507mistral | — | $0.10 | $0.40 | $0.0100 | — | — | 33K | |
| ministral-3b-latestmistral | — | $0.10 | $0.10 | $0.0100 | — | — | 262K | |
| ministral-3b-2512💬mistral | — | $0.10 | $0.10 | $0.0100 | — | — | 262K | |
| devstral-small-latestmistral | — | $0.10 | $0.30 | $0.0100 | — | — | 256K | |
| mistral.voxtral-small-24b-2507bedrock_converse | — | $0.10 | $0.30 | — | — | $0.0500 / $0.15 | 33K | |
| mistral.ministral-3-3b-instructbedrock_converse | — | $0.10 | $0.10 | — | — | $0.0500 / $0.0500 | 128K | |
| muse-spark-1.3-contributor💬meta | — | $0.10 | $0.20 | $0.0020 | — | — | 1.0M | |
| muse-spark-1.2-contributor💬meta | — | $0.10 | $0.20 | $0.0020 | — | — | 1.0M | |
| muse-ember-1.0meta | — | $0.10 | $0.50 | $0.0040 | — | — | 1.0M | |
| meta.llama3-2-1b-instruct-v1:0bedrock | — | $0.10 | $0.10 | — | — | — | 128K | |
| gemma-3-12b-it💬crusoe | 1334 | $0.10 | $0.10 | — | — | — | 131K | |
| gpt-6-luna💬openai | — | $0.10 | $0.50 | $0.0100 | $0.13 | $0.0500 / $0.25 | 922K | |
| gpt-4.1-nano-2025-04-14openai | — | $0.10 | $0.40 | $0.0250 | — | $0.0500 / $0.20 | 1.0M | |
| gpt-4.1-nano💬openai | — | $0.10 | $0.40 | $0.0250 | — | $0.0500 / $0.20 | 1.0M | |
| gpt-oss-120b💬baseten | 1366 | $0.10 | $0.50 | $0.10 | — | — | 128K | |
| lfm-40blambda_ai | — | $0.10 | $0.20 | — | — | — | 131K | |
| gemini-2.5-flash-lite💬gemini | — | $0.10 | $0.40 | $0.0100 | — | $0.0500 / $0.20 | 1.0M | |
| gemini-2.5-flash-lite-preview-09-2025💬vertex_ai-language-models | — | $0.10 | $0.40 | $0.0100 | — | — | 1.0M | |
| gemini-2.5-flash-lite💬vertex_ai-language-models | — | $0.10 | $0.40 | $0.0100 | — | $0.0500 / $0.20 | 1.0M | |
| llama-v3p2-3b-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| llama-v3p2-1b-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| llama-v3p1-8b-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| Llama-3.3-Nemotron-Super-49B-v1.5💬deepinfra | 1338 | $0.10 | $0.40 | — | — | — | 131K | |
| Llama-4-Scout-17B-16E-Instructdeepinfra | — | $0.10 | $0.30 | — | — | — | 328K | |
| Llama-3.3-70B-Instruct-Turbodeepinfra | — | $0.10 | $0.32 | — | — | — | 131K | |
| claude-haiku-5.5💬github_copilot | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 128K | |
| gemma-4-26b-a4b-it💬cloudflare | — | $0.10 | $0.30 | — | — | — | 256K | |
| llama3.1-8bcerebras | — | $0.10 | $0.10 | — | — | — | 128K | |
| llama-3.1-8bcerebras | — | $0.10 | $0.10 | — | — | — | 128K | |
| mistral-small-2503azure_ai | — | $0.10 | $0.30 | — | — | — | 128K | |
| gpt-6-luna-2026-09-22azure | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 922K | |
| gpt-6-luna💬azure | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 922K | |
| gpt-4.1-nano-2025-04-14azure | — | $0.10 | $0.40 | $0.0250 | — | $0.0500 / $0.20 | 1.0M | |
| gpt-4.1-nano💬azure | — | $0.10 | $0.40 | $0.0250 | — | $0.0500 / $0.20 | 1.0M | |
| gpt-6-luna💬azure_ai | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | 922K | |
| NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16gmi | — | $0.10 | $0.50 | $0.0500 | — | — | 33K | |
| eu.amazon.nova-lite-v1:0bedrock_converse | — | $0.0960 | $0.38 | $0.0240 | — | — | 300K | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0960 | $0.38 | $0.0240 | — | — | 300K | |
| google.gemma-3-12b-itbedrock_mantle | — | $0.0927 | $0.30 | — | — | — | 128K | |
| DeepSeek-V4-Flash💬gmi | 1432 | $0.0910 | $0.18 | $0.0182 | — | — | 1.0M | |
| doubao-seed-2-0-lite-260428aihubmix | — | $0.0904 | $0.54 | $0.0181 | — | — | 256K | |
| DeepSeek-V4-Flash💬deepinfra | 1432 | $0.0900 | $0.18 | $0.0180 | — | — | 1.0M | |
| DeepSeek-R1-Distill-Qwen-1.5Bnscale | — | $0.0900 | $0.0900 | — | — | — | — | |
| openai.gpt-oss-20bbedrock_mantle | — | $0.0900 | $0.40 | — | — | — | 131K |
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.