💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 13h. 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 |
|---|---|---|---|---|---|---|---|---|
| kimi-k2p7-code-fastfireworks_ai | — | $1.90 | $8.00 | $0.38 | — | — | 262K | |
| kimi-k2.7-code-highspeedgmi | — | $1.90 | $8.00 | $0.38 | — | — | 262K | |
| kimi-k2.7-code-highspeedaihubmix | — | $1.90 | $8.00 | $0.32 | — | — | 262K | |
| glm-5.1💬kyma | 1463 | $1.89 | $5.94 | $0.28 | — | — | 203K | |
| databricks-gemini-nano-banana-2-1databricks | — | $1.88 | $9.38 | $0.19 | $1.88 | — | 131K | — |
| databricks-gemini-3-5-flashdatabricks | — | $1.88 | $11.2 | $0.19 | $1.88 | — | 1.0M | |
| system.ai.gemini-4-hydrogendatabricks | — | $1.88 | $9.38 | $0.0937 | $2.34 | — | 1.0M | |
| us.zai.glm-5.3bedrock_converse | — | $1.85 | $5.81 | $0.34 | $2.31 | $0.92 / $2.90 | 1.0M | |
| glm-5.3💬inferenceapis | — | $1.82 | $5.72 | $0.34 | — | — | 1.0M | |
| GLM-5.3💬inferenceapis | — | $1.82 | $5.72 | $0.34 | — | — | 1.0M | |
| glm-5.2💬scaleway | — | $1.80 | $5.50 | — | — | — | 256K | |
| allam-1-13b-instructwatsonx | — | $1.80 | $1.80 | — | — | — | 8K | |
| jais-13b-chatwatsonx | — | $1.80 | $1.80 | — | — | — | 8K | |
| together-ai-81.1b-110btogether_ai | — | $1.80 | $1.80 | — | — | — | — | |
| muse-spark-1.2🖼️kyma | — | $1.77 | $6.03 | — | — | — | 1.0M | |
| grok-4.20-multi-agent💬kyma | — | $1.77 | $3.53 | — | — | — | 2.0M | |
| grok-4.20💬kyma | — | $1.76 | $3.53 | — | — | — | 2.0M | |
| gpt-5.2💬gmi | 1412 | $1.75 | $14.0 | — | — | — | 410K | |
| DeepSeek-V4-Pro💬nebius | 1451 | $1.75 | $3.50 | $0.14 | — | — | 1.0M | |
| gpt-5.2💬replicate | 1412 | $1.75 | $14.0 | — | — | — | — | |
| gpt-5.2-2025-12-11azure | — | $1.75 | $14.0 | $0.17 | — | $0.88 / $7.00 | 272K | |
| gpt-5.2💬azure | 1412 | $1.75 | $14.0 | $0.17 | — | $0.88 / $7.00 | 272K | |
| gpt-5.3-chat💬azure | 1389 | $1.75 | $14.0 | $0.17 | — | — | 112K | |
| gpt-5.2-chat💬azure | — | $1.75 | $14.0 | $0.17 | — | — | 112K | |
| gpt-5.2-chat-latestopenai | — | $1.75 | $14.0 | $0.17 | — | — | 128K | |
| gpt-5.2-2025-12-11openai | — | $1.75 | $14.0 | $0.17 | — | $0.88 / $7.00 | 272K | |
| databricks-gpt-5-2databricks | — | $1.75 | $14.0 | $0.17 | $1.75 | — | 272K | |
| gpt-5.3-codex💻aihubmix | — | $1.75 | $14.0 | $0.17 | — | — | 400K | |
| gpt-5.3-chat-latestopenai | — | $1.75 | $14.0 | $0.17 | — | — | 128K | |
| gpt-5.2💬openai | 1412 | $1.75 | $14.0 | $0.17 | — | $0.88 / $7.00 | 272K | |
| FW-GLM-5.3azure_ai | — | $1.75 | $5.50 | $0.33 | — | — | 1.0M | |
| deepseek-v4-pro💬streamlake | 1451 | $1.74 | $3.48 | $0.14 | — | — | 1.0M | |
| deepseek-v4-pro💬azure_ai | 1451 | $1.74 | $3.48 | $0.14 | — | — | 1.0M | |
| deepseek-v4-pro💬tencent | 1451 | $1.74 | $3.48 | $0.14 | free | — | 1.0M | |
| DeepSeek-V4-Pro💬baseten | 1451 | $1.74 | $3.48 | $0.14 | — | — | 1.0M | |
| DeepSeek-V4-Pro-0813💬inferenceapis | — | $1.72 | $5.15 | $0.17 | — | — | 1.0M | |
| deepseek-v4-pro💬inferenceapis | 1451 | $1.72 | $5.15 | $0.17 | — | — | 1.0M | |
| DeepSeek-V4-Pro💬inferenceapis | 1451 | $1.72 | $5.15 | $0.17 | — | — | 1.0M | |
| gpt-5.1💬azure | 1422 | $1.72 | $13.8 | $0.17 | — | — | 272K | |
| qwen3.8-max💬aihubmix | 1486 | $1.69 | $5.07 | $0.17 | $2.11 | — | 1.0M | |
| deepseek-v4-pro💬aihubmix | 1451 | $1.69 | $3.38 | $0.14 | — | — | 1.0M | |
| muse-spark-1.3💬kyma | — | $1.69 | $5.74 | — | — | — | 1.0M | |
| muse-spark-open💬kyma | — | $1.69 | $5.74 | — | — | — | 1.0M | |
| global.zai.glm-5.3bedrock_converse | — | $1.68 | $5.28 | $0.31 | $2.10 | $0.84 / $2.64 | 1.0M | |
| qwen3-7-max:variant1empiriolabs | — | $1.65 | $4.95 | — | — | — | 984K | |
| Qwen3.8-Max💬scx-ai | 1486 | $1.65 | $4.99 | $0.21 | — | — | 1.0M | |
| deepseek-v4-pro💬empiriolabs | 1451 | $1.65 | $3.30 | — | — | — | 1.0M | |
| deepseek-v4-pro:variant2empiriolabs | — | $1.65 | $3.30 | $0.14 | — | — | 1.0M | |
| Qwen3.8-Max💬deepinfra | 1486 | $1.65 | $4.95 | $0.21 | — | — | 256K | |
| qwen3-8-max:variant1empiriolabs | — | $1.65 | $4.95 | — | — | — | 984K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.06808h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.02308h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.07848h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.03998h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.428h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.628h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.608h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.268h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.07008h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.368h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.09008h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.188h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.008h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.338h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.05008h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.968h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.328h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.188h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.06008h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.238h
Price cuts are green — they make AI cheaper for everyone.