💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 15h. 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 |
|---|---|---|---|---|---|---|---|---|
| longcat-2.0👁️aihubmix | — | $0.77 | $3.10 | $0.0155 | — | — | 1.0M | |
| DeepSeek-V3-0324baseten | — | $0.77 | $0.77 | — | — | — | — | |
| mistral.mixtral-8x7b-instruct-v0:1bedrock | — | $0.76 | $1.18 | — | — | — | 32K | |
| llama-3-3-70b-instruct💬watsonx | 1274 | $0.75 | $0.75 | — | — | — | 131K | |
| gemini-3.7-flash💬gmi | — | $0.75 | $3.75 | $0.0750 | — | — | 1.0M | |
| gemini-3.8-flash💬gmi | — | $0.75 | $3.75 | $0.0750 | — | — | 1.0M | |
| gemini-3.8-flash💬github_copilot | — | $0.75 | $3.75 | $0.0750 | — | — | 200K | |
| gemini-3.8-flash💬vertex_ai-language-models | — | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-3.7-flash💬vertex_ai-language-models | — | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-3.6-flash💬vertex_ai-language-models | 1479 | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-3.8-flash💬gemini | — | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-3.7-flash💬gemini | — | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-3.6-flash💬gemini | 1479 | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-flash-latest💬gemini | — | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-3.8-flash💬vertex_ai | — | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-3.7-flash💬vertex_ai | — | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-3.6-flash💬vertex_ai | 1479 | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| gemini-3.7-flash💬aihubmix | — | $0.75 | $3.75 | $0.0750 | — | — | 1.0M | |
| kimi-k2.7-code💻aiand | — | $0.75 | $3.50 | $0.20 | — | — | 262K | |
| Kimi-K2.6💬deepinfra | 1456 | $0.75 | $3.50 | $0.15 | — | — | 262K | |
| gpt-5.4-mini💬aihubmix | — | $0.75 | $4.50 | $0.0750 | — | — | 400K | |
| gpt-5.4-mini💬gmi | — | $0.75 | $4.50 | $0.0750 | — | — | 410K | |
| gemini-3.7-flash💬github_copilot | — | $0.75 | $3.75 | $0.0750 | — | — | 200K | |
| qwen3-235b-a22b-instruct-2507scaleway | — | $0.75 | $2.25 | — | — | — | 256K | |
| deepseek-r1-distill-llama-70b🧮vercel_ai_gateway | — | $0.75 | $0.99 | — | — | — | 131K | |
| gemini-3.7-flash💬deepinfra | — | $0.75 | $3.75 | — | — | — | 1.0M | |
| gemini-flash-latest💬gemini | — | $0.75 | $3.75 | $0.0750 | — | $0.38 / $1.88 | 1.0M | |
| GLM-5.3💬wandb | — | $0.75 | $3.00 | $0.19 | — | — | 1.0M | |
| meta.llama2-13b-chat-v1bedrock | — | $0.75 | $1.00 | — | — | — | 4K | |
| gpt-5.4-mini-2026-03-17azure_ai | — | $0.75 | $4.50 | $0.0750 | — | — | 272K | |
| gpt-5.4-mini💬azure_ai | — | $0.75 | $4.50 | $0.0750 | — | — | 272K | |
| GLM-5.2💬deepinfra | — | $0.75 | $2.40 | $0.14 | — | — | 1.0M | |
| gpt-5.4-mini-2026-03-17azure | — | $0.75 | $4.50 | $0.0750 | — | $0.38 / $2.25 | 272K | |
| gpt-5.4-mini💬azure | — | $0.75 | $4.50 | $0.0750 | — | $0.38 / $2.25 | 272K | |
| gpt-5.4-mini-2026-03-17openai | — | $0.75 | $4.50 | $0.0750 | — | $0.38 / $2.25 | 272K | |
| gpt-5.4-mini💬openai | — | $0.75 | $4.50 | $0.0750 | — | $0.38 / $2.25 | 272K | |
| databricks-gpt-5-4-minidatabricks | — | $0.75 | $4.50 | $0.0750 | $0.75 | — | 272K | |
| databricks-gemini-3-6-flashdatabricks | — | $0.75 | $3.75 | $0.0750 | $0.75 | — | 1.0M | |
| databricks-gemini-3-7-flashdatabricks | — | $0.75 | $3.75 | $0.0750 | $0.75 | — | 1.0M | |
| databricks-gemini-3-8-flashdatabricks | — | $0.75 | $3.75 | $0.0750 | $0.75 | — | 1.0M | |
| deepseek-r1🧮kyma | 1373 | $0.74 | $2.96 | — | — | — | 64K | |
| deepseek.v3.2💬bedrock | 1425 | $0.74 | $2.22 | — | — | $0.37 / $1.11 | 156K | |
| deepseek.v3.2💬bedrock_converse | 1425 | $0.74 | $2.22 | — | — | — | 156K | |
| deepseek.v3.2💬bedrock_converse | 1425 | $0.74 | $2.22 | — | — | — | 156K | |
| deepseek.v3.2💬bedrock | 1425 | $0.74 | $2.22 | — | — | $0.37 / $1.11 | 156K | |
| deepseek.v3.2💬bedrock_mantle | 1425 | $0.74 | $2.22 | — | — | — | 156K | |
| deepseek.v3.2💬bedrock_mantle | 1425 | $0.74 | $2.22 | — | — | — | 156K | |
| deepseek.v3.2💬bedrock | 1425 | $0.74 | $2.22 | — | — | — | 156K | |
| deepseek.v3.2💬bedrock | 1425 | $0.74 | $2.22 | — | — | $0.37 / $1.11 | 156K | |
| deepseek.v3.2💬bedrock_converse | 1425 | $0.74 | $2.22 | — | — | — | 156K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.068010h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.023010h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.078410h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.039910h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.4210h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.6210h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.6010h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.2610h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.070010h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.3610h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.090010h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.1810h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.0010h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.3310h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.050010h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.9610h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.3210h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.1810h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.060010h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.2310h
Price cuts are green — they make AI cheaper for everyone.