💲 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 |
|---|---|---|---|---|---|---|---|---|
| granite-4-h-smallwatsonx | — | $0.0636 | $0.27 | — | — | — | 131K | |
| apac.amazon.nova-lite-v1:0bedrock_converse | — | $0.0630 | $0.25 | $0.0158 | — | — | 300K | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0630 | $0.25 | $0.0158 | — | — | 300K | |
| nvidia.nemotron-nano-9b-v2bedrock_mantle | — | $0.0618 | $0.24 | — | — | — | 128K | |
| nvidia.nemotron-nano-3-30bbedrock_mantle | — | $0.0618 | $0.25 | — | — | — | 256K | |
| glm-4.7-flash💬cloudflare | 1351 | $0.0605 | $0.40 | — | — | — | 131K | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0600 | $0.24 | $0.0150 | free | — | 300K | |
| openai-gpt-5-nanosnowflake | — | $0.0600 | $0.44 | $0.0100 | — | — | 5.0M | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0600 | $0.24 | $0.0150 | free | — | 300K | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0600 | $0.24 | $0.0150 | free | — | 300K | |
| google.gemma-3-4b-itbedrock_converse | — | $0.0600 | $0.12 | — | — | — | 128K | |
| nvidia.nemotron-nano-3-30bbedrock_converse | — | $0.0600 | $0.24 | — | — | $0.0300 / $0.12 | 256K | |
| nvidia.nemotron-nano-9b-v2bedrock_converse | — | $0.0600 | $0.23 | — | — | $0.0300 / $0.12 | 128K | |
| Nemotron-3_5-Lightning💬nebius | — | $0.0600 | $0.24 | $0.0300 | — | — | 1.0M | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0600 | $0.24 | $0.0150 | free | — | 300K | |
| NVIDIA-Nemotron-3.5-Lightningdeepinfra | — | $0.0600 | $0.16 | $0.0400 | — | — | 262K | |
| Nemotron-3-Nano-Omninebius | — | $0.0600 | $0.24 | — | — | — | 262K | |
| codellama-7bllamagate | — | $0.0600 | $0.12 | — | — | — | 16K | |
| granite-4.1-8b💬replicate | 1291 | $0.0600 | $0.25 | — | — | — | — | |
| granite-4.2-8b💬replicate | 1319 | $0.0600 | $0.25 | — | — | — | — | |
| granite-vision-4.1-4breplicate | — | $0.0600 | $0.25 | — | — | — | — | |
| nova-litevercel_ai_gateway | — | $0.0600 | $0.24 | — | — | — | 300K | |
| nvidia.nemotron-nano-3-30bbedrock_mantle | — | $0.0600 | $0.24 | — | — | $0.0300 / $0.12 | 256K | |
| us.amazon.nova-lite-v1:0bedrock_converse | — | $0.0600 | $0.24 | $0.0150 | — | $0.0300 / $0.12 | 300K | |
| Llama-3.2-1B-Instruct💬together_ai | 1055 | $0.0600 | $0.0600 | — | — | — | 131K | |
| nvidia.nemotron-nano-9b-v2bedrock_mantle | — | $0.0600 | $0.23 | — | — | $0.0300 / $0.12 | 128K | |
| mistral.voxtral-mini-3b-2507bedrock | — | $0.0600 | $0.0600 | — | — | $0.0300 / $0.0300 | 33K | |
| deepseek-coder-6.7bllamagate | — | $0.0600 | $0.12 | — | — | — | 16K | |
| DeepSeek-V4-Flash-0731💬deepinfra | — | $0.0600 | $0.18 | $0.0150 | — | — | 1.0M | |
| Ling-3.0-flash💬deepinfra | — | $0.0600 | $0.18 | $0.0120 | — | — | 131K | |
| ling-3.0-flash💬novita | — | $0.0600 | $0.18 | $0.0120 | — | — | 262K | |
| GLM-4.7-Flash💬deepinfra | 1351 | $0.0600 | $0.40 | $0.0100 | — | — | 203K | |
| granite-4.2-8b💬wandb | 1319 | $0.0600 | $0.15 | $0.0150 | — | — | 131K | |
| deepseek-r1-0528-qwen3-8bnovita | — | $0.0600 | $0.0900 | — | — | — | 128K | |
| Qwen2.5-32B-Instructnebius | — | $0.0600 | $0.20 | — | — | — | 128K | |
| google.gemma-3-4b-itbedrock_mantle | — | $0.0600 | $0.12 | — | — | — | 128K | |
| Llama-3.2-3B-Instruct💬together_ai | 1110 | $0.0600 | $0.0600 | — | — | — | 131K | |
| FW-Nemotron-Lightning-3.5-30B-A3Bazure_ai | — | $0.0600 | $0.22 | $0.0100 | — | — | 262K | |
| Qwen2.5-Coder-32B-Instructnscale | — | $0.0600 | $0.20 | — | — | — | — | |
| NVIDIA-Nemotron-Nano-9B-v2together_ai | — | $0.0600 | $0.25 | — | — | — | 131K | |
| mistral.voxtral-mini-3b-2507bedrock_mantle | — | $0.0600 | $0.0600 | — | — | — | 33K | |
| qwen2.5-coder-7bllamagate | — | $0.0600 | $0.12 | — | — | — | 33K | |
| amazon.nova-lite-v1:0bedrock_converse | — | $0.0600 | $0.24 | $0.0150 | — | $0.0300 / $0.12 | 300K | |
| nova-lite-v1💬amazon_nova | — | $0.0600 | $0.24 | — | — | — | 300K | |
| granite-4.0-h-smallreplicate | — | $0.0600 | $0.25 | — | — | — | — | |
| NVIDIA-Nemotron-3-Nano-30B-A3Bnebius | — | $0.0600 | $0.24 | $0.0120 | — | — | 262K | |
| cc-glm-5.1aihubmix | — | $0.0600 | $0.22 | — | — | — | 200K | |
| coding-glm-5.3aihubmix | — | $0.0600 | $0.22 | $0.0150 | — | — | 1.0M | |
| glm-5.3-flash💬clf_ai_gateway | 1471 | $0.0600 | $0.20 | $0.0120 | — | — | 1.0M | |
| ling-3.0-flash-fastnovita | — | $0.0600 | $0.18 | $0.0120 | — | — | 262K |
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.