💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 18h. 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 |
|---|---|---|---|---|---|---|---|---|
| grok-4-fast-non-reasoningazure_ai | — | $0.20 | $0.50 | — | — | — | — | |
| qwen.qwen3-32bbedrock_mantle | — | $0.20 | $0.79 | — | — | — | 32K | |
| grok-4-fast-reasoningazure_ai | — | $0.20 | $0.50 | — | — | — | — | |
| qwen.qwen3-coder-30b-a3b-instructbedrock_mantle | — | $0.20 | $0.79 | — | — | — | 256K | |
| muse-glimmer-30b🖼️empiriolabs | — | $0.20 | $0.80 | $0.0500 | — | — | 131K | |
| qwen3-coder-next💻novita | — | $0.20 | $1.50 | — | — | — | 262K | |
| deepseek-v4-1-flash-1017💬empiriolabs | — | $0.20 | $0.80 | $0.0200 | — | — | 1.0M | |
| deepseek-coder-7b-basefireworks_ai | — | $0.20 | $0.20 | — | — | — | 4K | |
| GLM-4.5-Air-FP8together_ai | — | $0.20 | $1.10 | — | — | — | 131K | |
| llama3-8b-instructgradient_ai | — | $0.20 | $0.20 | — | — | — | 8K | |
| Ministral-3-14B-Instruct-2512together_ai | — | $0.20 | $0.20 | — | — | — | 262K | |
| gemma-7b-itfireworks_ai | — | $0.20 | $0.20 | — | — | — | 8K | |
| mistral.ministral-3-14b-instructbedrock_converse | — | $0.20 | $0.20 | — | — | $0.10 / $0.10 | 128K | |
| Llama-3.3-70B-Instruct💬nscale | 1274 | $0.20 | $0.20 | — | — | — | — | |
| codegemma-7bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 8K | |
| code-qwen-1p5-7bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 66K | |
| gpt-5.6-luna💬aihubmix | — | $0.20 | $1.20 | $0.0200 | $0.25 | — | 1.1M | |
| gpt-5.4-nano💬aihubmix | — | $0.20 | $1.25 | $0.0200 | — | — | 400K | |
| ministral-14b-2512💬mistral | — | $0.20 | $0.20 | $0.0200 | — | — | 262K | |
| DeepSeek-R1-Distill-Qwen-7Bnscale | — | $0.20 | $0.20 | — | — | — | — | |
| ministral-14b-latestmistral | — | $0.20 | $0.20 | $0.0200 | — | — | 262K | |
| jamba-mini-1.7ai21 | — | $0.20 | $0.40 | — | — | — | 256K | |
| ministral-3-14b-2512mistral | — | $0.20 | $0.20 | $0.0200 | — | — | 262K | |
| Mistral-7B-Instruct-v0.3together_ai | — | $0.20 | $0.20 | — | — | — | 33K | |
| moonshot-v1-8kmoonshot | — | $0.20 | $2.00 | — | — | — | 8K | |
| Llama-4-Maverick-17B-128E-Instruct-FP8deepinfra | — | $0.20 | $0.80 | — | — | — | 1.0M | |
| code-llama-7b-pythonfireworks_ai | — | $0.20 | $0.20 | — | — | — | 16K | |
| code-llama-7b-instructfireworks_ai | — | $0.20 | $0.20 | — | — | — | 16K | |
| deepseek-coder-7b-base-v1p5fireworks_ai | — | $0.20 | $0.20 | — | — | — | 4K | |
| deepseek-coder-7b-instruct-v1p5fireworks_ai | — | $0.20 | $0.20 | — | — | — | 4K | |
| DeepSeek-R1-Distill-Llama-70B🧮deepinfra | — | $0.20 | $0.60 | — | — | — | 131K | |
| granite-3-8b-instructwatsonx | — | $0.20 | $0.20 | — | — | — | 8K | |
| code-llama-7bfireworks_ai | — | $0.20 | $0.20 | — | — | — | 16K | |
| granite-3-3-8b-instructwatsonx | — | $0.20 | $0.20 | — | — | — | 8K | |
| coding-xiaomi-mimo-v2.5-proaihubmix | — | $0.20 | $0.40 | $0.0016 | — | — | 1.0M | |
| gemma2-9b-itfireworks_ai | — | $0.20 | $0.20 | — | — | — | 8K | |
| qwen3.6-35b-a3b💬zerogpu | — | $0.20 | $1.50 | $0.20 | — | — | 262K | |
| gpt-5.4-nano-2026-03-17openai | — | $0.20 | $1.25 | $0.0200 | — | $0.10 / $0.63 | 272K | |
| gpt-5.4-nano💬openai | — | $0.20 | $1.25 | $0.0200 | — | $0.10 / $0.63 | 272K | |
| Qwen3-235B-A22B💬nebius | 1366 | $0.20 | $0.60 | — | — | — | 262K | |
| Llama-3.3-70B-Instruct💬crusoe | 1274 | $0.20 | $0.20 | — | — | — | 131K | |
| Qwen2.5-VL-32B-Instructdeepinfra | — | $0.20 | $0.60 | — | — | — | 128K | |
| morph-glm53flashmorph | — | $0.20 | $0.70 | $0.0400 | — | — | 1.0M | |
| moonshot-v1-8k-vision-previewmoonshot | — | $0.20 | $2.00 | — | — | — | 8K | |
| openai.gpt-oss-120bbedrock_mantle | — | $0.20 | $0.79 | — | — | — | 131K | |
| mercury-2.5💬inception | — | $0.20 | $0.75 | $0.0200 | — | — | 260K | |
| gpt-5.4-nano💬zerogpu | — | $0.20 | $1.25 | $0.0200 | — | — | 272K | |
| Qwen3-235B-A22B-Instruct-2507nebius | — | $0.20 | $0.60 | $0.0500 | — | — | 262K | |
| nvidia.nemotron-nano-12b-v2bedrock_converse | — | $0.20 | $0.60 | — | — | $0.10 / $0.30 | 128K | |
| step-3-7-flash💬empiriolabs | — | $0.20 | $1.15 | $0.0400 | — | — | 262K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068014h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023014h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078414h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039914h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4214h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6214h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6014h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2614h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070014h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3614h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090014h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1814h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0014h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3314h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050014h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9614h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3214h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1814h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060014h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2314h
Price cuts are green — they make AI cheaper for everyone.