💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 19h. 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 |
|---|---|---|---|---|---|---|---|---|
| glm-5.3-flash💬zai | 1471 | $0.15 | $0.50 | $0.0300 | free | — | 1.0M | |
| qwen3-30b-a3b💬fireworks_ai | 1317 | $0.15 | $0.60 | — | — | — | 131K | |
| qwen3-coder-30b-a3b-instruct💻fireworks_ai | — | $0.15 | $0.60 | — | — | — | 262K | |
| qwen3-vl-30b-a3b-instruct👁️fireworks_ai | — | $0.15 | $0.60 | — | — | — | 262K | |
| qwen3-vl-30b-a3b-thinking🧮fireworks_ai | — | $0.15 | $0.60 | — | — | — | 262K | |
| mistral-small-3.2-24b-instruct-2506scaleway | — | $0.15 | $0.35 | — | — | — | 128K | |
| qwen3-next-80b-a3b-instruct💬novita | 1417 | $0.15 | $1.50 | — | — | — | 131K | |
| qwen3-next-80b-a3b-thinking🧮novita | 1368 | $0.15 | $1.50 | — | — | — | 131K | |
| deepseek-r1-distill-qwen-14bnovita | — | $0.15 | $0.15 | — | — | — | 33K | |
| qwen3-vl-8bllamagate | — | $0.15 | $0.55 | — | — | — | 33K | |
| hermes-3-8b-teelibertai | — | $0.15 | $0.60 | — | — | — | 16K | |
| gemma-4-31b-it💬libertai | — | $0.15 | $0.40 | — | — | — | 262K | |
| gemma-4-31b-it-thinkinglibertai | — | $0.15 | $0.40 | — | — | — | 262K | |
| qwen3.6-27b💬libertai | — | $0.15 | $0.50 | — | — | — | 262K | |
| qwen3.6-27b-thinkinglibertai | — | $0.15 | $0.50 | — | — | — | 262K | |
| qwen3.6-35b-a3b💬libertai | — | $0.15 | $0.50 | — | — | — | 262K | |
| qwen3.6-35b-a3b-thinkinglibertai | — | $0.15 | $0.50 | — | — | — | 262K | |
| openai.gpt-oss-120bbedrock_mantle | — | $0.15 | $0.60 | — | — | $0.0750 / $0.30 | 131K | |
| openai.gpt-oss-safeguard-120bbedrock_mantle | — | $0.15 | $0.60 | — | — | $0.0700 / $0.30 | 131K | |
| gpt-oss-120b💬tensormesh | 1366 | $0.15 | $0.60 | free | — | — | 131K | |
| GLM-5.3-Flash💬streamlake | 1471 | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| glm-5.3-flash💬tencent | 1471 | $0.15 | $0.50 | $0.0300 | free | — | 1.0M | |
| mistral-small-2603💬mistral | — | $0.15 | $0.60 | $0.0150 | — | — | 262K | |
| gpt-oss-120b-Turbodeepinfra | — | $0.15 | $0.60 | — | — | — | 131K | |
| Qwen3-VL-30B-A3B-Instruct👁️deepinfra | — | $0.15 | $0.60 | — | — | — | 262K | |
| GLM-5.3-Flash💬deepinfra | 1471 | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| NVIDIA-Nemotron-3.5-Super-VLdeepinfra | — | $0.15 | $0.50 | $0.0200 | — | — | 262K | |
| mistral-vibe-cli-fastmistral | — | $0.15 | $0.60 | $0.0150 | — | — | 262K | |
| glm-5p3-flashfireworks_ai | — | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| glm-flash-latest💬fireworks_ai | — | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| glm-5p3-flashfireworks_ai | — | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| gpt-oss-120b💬zerogpu | 1366 | $0.15 | $0.60 | $0.0300 | — | — | 128K | |
| llama-3.1-8b-instruct-fastzerogpu | — | $0.15 | $0.28 | $0.0250 | — | — | 131K | |
| Qwen3.8-Flash💬together_ai | — | $0.15 | $0.47 | — | — | — | 1.0M | |
| FW-DeepSeek-V4-Flashazure_ai | — | $0.15 | $0.31 | $0.0300 | — | — | 1.0M | |
| mistral.ministral-3-8b-instructbedrock_mantle | — | $0.15 | $0.15 | — | — | $0.0700 / $0.0700 | 128K | |
| nvidia.nemotron-super-3-120bbedrock_mantle | — | $0.15 | $0.65 | — | — | $0.0750 / $0.33 | 256K | |
| writer.palmyra-vision-7bbedrock_mantle | — | $0.15 | $0.60 | — | — | $0.0750 / $0.30 | 4K | |
| qwen.qwen3-32bbedrock_mantle | — | $0.15 | $0.60 | — | — | $0.0750 / $0.30 | 32K | |
| qwen.qwen3-coder-30b-a3b-instructbedrock_mantle | — | $0.15 | $0.60 | — | — | $0.0750 / $0.30 | 256K | |
| gemma-4-26b-a4b-it💬vertex_ai | — | $0.15 | $0.60 | $0.0150 | — | — | — | |
| Qwen3-Next-80B-A3B-Instruct💬together_ai | 1417 | $0.15 | $1.50 | — | — | — | 262K | |
| Qwen3-Next-80B-A3B-Thinking🧮together_ai | 1368 | $0.15 | $1.50 | — | — | — | 262K | |
| rnj-1-instructtogether_ai | — | $0.15 | $0.15 | — | — | — | — | |
| deepseek-v4-flash💬aiand | 1432 | $0.15 | $0.25 | $0.0800 | — | — | 1.0M | |
| gpt-oss-120b💬aiand | 1366 | $0.15 | $0.60 | $0.0800 | — | — | 131K | |
| glm-5.3-flash💬aiand | 1471 | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| GLM-5.3-Flash💬baseten | 1471 | $0.15 | $0.50 | $0.0300 | — | — | 1.0M | |
| gemini-2.0-flashvertex_ai | — | $0.15 | $0.60 | — | — | $0.0750 / $0.30 | — | |
| NVIDIA-Nemotron-3.5-Super-VLtogether_ai | — | $0.15 | $0.50 | $0.0200 | — | — | 262K |
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.