💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 21h. 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-mini-3b-2507bedrock_mantle | — | $0.0480 | $0.0480 | — | — | — | 33K | |
| google.gemma-3-4b-itbedrock_mantle | — | $0.0480 | $0.0960 | — | — | — | 128K | |
| google.gemma-4-e2bbedrock_mantle | — | $0.0480 | $0.0960 | — | — | — / $0.0480 | 128K | |
| google.gemma-3-4b-itbedrock_mantle | — | $0.0480 | $0.0960 | — | — | — | 128K | |
| google.gemma-4-e2bbedrock_mantle | — | $0.0480 | $0.0960 | — | — | — | 128K | |
| gpt-oss-120b💬kyma | 1366 | $0.0473 | $0.23 | — | — | — | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0470 | $0.19 | $0.0118 | — | — | 128K | |
| eu.amazon.nova-micro-v1:0bedrock_converse | — | $0.0460 | $0.18 | $0.0115 | — | — | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0460 | $0.18 | $0.0115 | — | — | 128K | |
| trinity-mini💬together_ai | — | $0.0450 | $0.15 | — | — | — | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0440 | $0.18 | $0.0110 | free | — | 128K | |
| qwen3.7-flash💬kyma | — | $0.0435 | $0.19 | $0.0081 | — | — | 1.0M | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0420 | $0.17 | $0.0105 | — | — | 128K | |
| amazon.nova-micro-v1:0bedrock | — | $0.0420 | $0.17 | $0.0105 | — | $0.0210 / $0.0840 | 128K | |
| Tev1-4B-experimentaltogether_ai | — | $0.0420 | free | — | — | — | 33K | |
| mistral.voxtral-mini-3b-2507bedrock_mantle | — | $0.0412 | $0.0412 | — | — | — | 33K | |
| google.gemma-3-4b-itbedrock_mantle | — | $0.0412 | $0.0824 | — | — | — | 128K | |
| mistral.voxtral-mini-3b-2507bedrock | — | $0.0412 | $0.0412 | — | — | $0.0206 / $0.0206 | 33K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0410 | $0.16 | $0.0103 | — | — | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0410 | $0.16 | $0.0103 | — | — | 128K | |
| gpt-oss-20b💬ovhcloud | 1288 | $0.0400 | $0.15 | — | — | — | 131K | |
| google.gemma-4-e2bbedrock_mantle | — | $0.0400 | $0.0800 | — | — | $0.0200 / $0.0400 | 128K | |
| eu.amazon.nova-micro-v1:0bedrock_converse | — | $0.0400 | $0.16 | $0.0100 | — | — | 128K | |
| llama-prompt-guard-2-86mgroq | — | $0.0400 | $0.0400 | — | — | — | 512 | |
| ministral-3bazure_ai | — | $0.0400 | $0.0400 | — | — | — | 128K | |
| L3-8B-Lunaris-v1-Turbodeepinfra | — | $0.0400 | $0.0500 | — | — | — | 8K | |
| google.gemma-3-4b-itbedrock_converse | — | $0.0400 | $0.0800 | — | — | $0.0200 / $0.0400 | 128K | |
| google.gemma-3-4b-itbedrock_mantle | — | $0.0400 | $0.0800 | — | — | $0.0200 / $0.0400 | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0400 | $0.16 | $0.0100 | — | — | 128K | |
| nova-micro-1-0empiriolabs | — | $0.0400 | $0.16 | $0.0224 | — | — | 133K | |
| NVIDIA-Nemotron-Nano-9B-v2deepinfra | — | $0.0400 | $0.16 | — | — | — | 131K | |
| gpt-oss-20b💬novita | 1288 | $0.0400 | $0.15 | — | — | — | 131K | |
| Mistral-Nemo-Instruct-2407nebius | — | $0.0400 | $0.12 | — | — | — | 128K | |
| mistral.voxtral-mini-3b-2507bedrock_mantle | — | $0.0400 | $0.0400 | — | — | $0.0200 / $0.0200 | 33K | |
| ministral-3bvercel_ai_gateway | — | $0.0400 | $0.0400 | — | — | — | 128K | |
| gpt-oss-20b💬inferenceapis | 1288 | $0.0400 | $0.19 | — | — | — | 131K | |
| gpt-oss-20b💬inferenceapis | 1288 | $0.0400 | $0.19 | — | — | — | 131K | |
| qwen3-8b💬llamagate | — | $0.0400 | $0.14 | — | — | — | 33K | |
| llama-3-8b-instruct💬novita | 1166 | $0.0400 | $0.0400 | — | — | — | 8K | |
| llama-3.2-3bllamagate | — | $0.0400 | $0.0800 | — | — | — | 131K | |
| mistral-nemo💬novita | — | $0.0400 | $0.17 | — | — | — | 60K | |
| mistral.voxtral-mini-3b-2507bedrock_converse | — | $0.0400 | $0.0400 | — | — | $0.0200 / $0.0200 | 33K | |
| gpt-oss-20b💬gmi | 1288 | $0.0400 | $0.15 | — | — | — | 131K | |
| qwen3-5-4bempiriolabs | — | $0.0400 | $0.0700 | $0.0200 | — | — | 262K | |
| Qwen2.5-7B-Instructdeepinfra | — | $0.0400 | $0.10 | — | — | — | 33K | |
| glm-4-6v-flashxempiriolabs | — | $0.0400 | $0.40 | $0.0360 | — | — | 131K | |
| eu.amazon.nova-micro-v1:0bedrock_converse | — | $0.0390 | $0.16 | $0.0097 | — | — | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0390 | $0.16 | $0.0097 | — | — | 128K | |
| amazon.nova-micro-v1:0bedrock_converse | — | $0.0380 | $0.15 | $0.0095 | — | — | 128K | |
| eu.amazon.nova-micro-v1:0bedrock_converse | — | $0.0380 | $0.15 | $0.0095 | — | — | 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.