💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 11h. 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 |
|---|---|---|---|---|---|---|---|---|
| claude-opus-5💬anthropic | — | $5.00 | $25.0 | $0.50 | $6.25 | $2.50 / $12.5 | 1.0M | |
| claude-opus-4.7💬replicate | 1483 | $5.00 | $25.0 | — | — | — | — | |
| claude-opus-5💬deepinfra | — | $5.00 | $25.0 | — | — | — | 1.0M | |
| claude-opus-4-8💬deepinfra | 1454 | $5.00 | $25.0 | — | — | — | 1.0M | |
| claude-opus-4-7💬deepinfra | 1483 | $5.00 | $25.0 | — | — | — | 1.0M | |
| xai.grok-code-fast-1oci | — | $5.00 | $25.0 | — | — | — | 131K | |
| gpt-chat-latest💬aihubmix | — | $5.00 | $30.0 | $0.50 | — | — | 400K | |
| gpt-5.6-sol💬gmi | — | $5.00 | $30.0 | $0.50 | — | — | 1.1M | |
| claude-opus-4-7-20260416anthropic | — | $5.00 | $25.0 | $0.50 | $6.25 | $2.50 / $12.5 | 1.0M | |
| claude-opus-4-8@defaultvertex_ai-anthropic_models | — | $5.00 | $25.0 | $0.50 | $6.25 | $2.50 / $12.5 | 1.0M | |
| gpt-5.5-2026-04-24azure_ai | — | $5.00 | $30.0 | $0.50 | — | — | 922K | |
| claude-opus-4-7💬anthropic | 1483 | $5.00 | $25.0 | $0.50 | $6.25 | $2.50 / $12.5 | 1.0M | |
| gpt-5.5-2026-04-23azure_ai | — | $5.00 | $30.0 | $0.50 | — | — | 922K | |
| claude-opus-5💬github_copilot | — | $5.00 | $25.0 | $0.50 | $6.25 | — | 200K | |
| gpt-chat-latest💬azure_ai | — | $5.00 | $30.0 | $0.50 | — | — | 128K | |
| gpt-5.5💬aihubmix | 1466 | $5.00 | $30.0 | $0.50 | — | — | 1.1M | |
| claude-opus-4-8💬anthropic | 1454 | $5.00 | $25.0 | $0.50 | $6.25 | $2.50 / $12.5 | 1.0M | |
| gpt-5.5💬azure_ai | 1466 | $5.00 | $30.0 | $0.50 | — | — | 922K | |
| xai.grok-4.1-fastoci | — | $5.00 | $25.0 | — | — | — | 131K | |
| claude-opus-4.5💬vercel_ai_gateway | — | $5.00 | $25.0 | $0.50 | $6.25 | — | 200K | |
| global.anthropic.claude-opus-5bedrock_converse | — | $5.00 | $25.0 | $0.50 | $6.25 | $2.50 / $12.5 | 1.0M | |
| gpt-5.5-2026-04-23openai | — | $5.00 | $30.0 | $0.50 | — | $2.50 / $15.0 | 1.1M | |
| claude-opus-4-6💬anthropic | 1497 | $5.00 | $25.0 | $0.50 | $6.25 | $2.50 / $12.5 | 1.0M | |
| DeepSeek-R1🧮sambanova | 1373 | $5.00 | $7.00 | — | — | — | 33K | |
| gpt-5.5-2026-04-24azure | — | $5.00 | $30.0 | $0.50 | — | $2.50 / $15.0 | 922K | |
| anthropic.claude-opus-5bedrock_converse | — | $5.00 | $25.0 | $0.50 | $6.25 | $2.50 / $12.5 | 1.0M | |
| claude-4-opussnowflake | — | $5.00 | $25.0 | $0.50 | — | — | 200K | |
| gpt-5.5-2026-04-23azure | — | $5.00 | $30.0 | $0.50 | — | $2.50 / $15.0 | 922K | |
| gpt-5.5💬azure | 1466 | $5.00 | $30.0 | $0.50 | — | $2.50 / $15.0 | 922K | |
| global.openai.gpt-5.5bedrock_converse | — | $5.00 | $30.0 | $0.50 | — | — | 922K | |
| claude-opus-4-8💬azure_ai | 1454 | $5.00 | $25.0 | $0.50 | $6.25 | — | 1.0M | |
| claude-opus-4-7💬vertex_ai-anthropic_models | 1483 | $5.00 | $25.0 | $0.50 | $6.25 | $2.50 / $12.5 | 1.0M | |
| us-gov.anthropic.claude-opus-5-5bedrock_converse | — | $4.80 | $24.0 | $0.24 | $6.00 | — | 1.0M | |
| perplexity-sonar-reasoning-proempiriolabs | — | $4.80 | $19.0 | — | — | — | 919K | |
| perplexity-deep-researchempiriolabs | — | $4.80 | $19.0 | — | — | — | 919K | |
| anthropic.claude-opus-5-5bedrock_mantle | — | $4.80 | $24.0 | $0.24 | $6.00 | — | 1.0M | |
| anthropic.claude-opus-5-5bedrock | — | $4.80 | $24.0 | $0.24 | $6.00 | — | 1.0M | |
| anthropic.claude-opus-5-5bedrock | — | $4.80 | $24.0 | $0.24 | $6.00 | — | 1.0M | |
| mistral.mistral-large-2402-v1:0bedrock | — | $4.80 | $14.4 | — | — | — | 32K | |
| mistral.mistral-large-2402-v1:0bedrock | — | $4.60 | $13.8 | — | — | — | 32K | |
| kimi-fast-latestfireworks_ai | — | $4.50 | $22.5 | $0.45 | — | — | 1.0M | |
| kimi-k3-usfireworks_ai | — | $4.50 | $22.5 | $0.45 | — | — | 1.0M | |
| kimi-k3-fastfireworks_ai | — | $4.50 | $22.5 | $0.45 | — | — | 1.0M | |
| kimi-k3-usfireworks_ai | — | $4.50 | $22.5 | $0.45 | — | — | 1.0M | |
| kimi-k3-fastfireworks_ai | — | $4.50 | $22.5 | $0.45 | — | — | 1.0M | |
| meta.llama3-70b-instruct-v1:0bedrock | — | $4.45 | $5.88 | — | — | — | 8K | |
| gpt-5.6azure | — | $4.40 | $22.0 | $0.44 | $5.50 | — | 922K | |
| gpt-5.6-sol💬azure | — | $4.40 | $22.0 | $0.44 | $5.50 | — | 922K | |
| anthropic.claude-opus-5-5bedrock | — | $4.40 | $22.0 | $0.22 | $5.50 | — | 1.0M | |
| us.openai.gpt-daybreak-blue-5.6-solbedrock_converse | — | $4.40 | $22.0 | $0.44 | $5.50 | — | 922K |
Recent price changes
- ▼ 1.4%Z.ai: GLM 5.3 Flash (batch)z-ai · output $0.0690 → $0.06806h
- ▼ 4.2%Z.ai: GLM 5.3 Flash (batch)z-ai · input $0.0240 → $0.02306h
- ▼ 84.3%Z.ai: GLM 5.3 Flashz-ai · output $0.50 → $0.07846h
- ▼ 73.4%Z.ai: GLM 5.3 Flashz-ai · input $0.15 → $0.03996h
- ▼ 64.4%Z.ai: GLM 5.2z-ai · output $6.80 → $2.426h
- ▲ 8757.1%Z.ai: GLM 5.2z-ai · input $0.0070 → $0.626h
- ▲ 66.7%Qwen: Qwen3.5-27Bqwen · output $1.56 → $2.606h
- ▲ 33.3%Qwen: Qwen3.5-27Bqwen · input $0.20 → $0.266h
- ▲ 16.7%Particle AI: Particle-1particle-ai · input $0.0600 → $0.07006h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · output $0.60 → $0.366h
- ▼ 40.0%OpenAI: gpt-oss-120bopenai · input $0.15 → $0.09006h
- ▼ 1.0%MoonshotAI: Kimi Latestmoonshotai · input $0.18 → $0.186h
- ▼ 14.3%MoonshotAI: Kimi K2.7 Codemoonshotai · output $3.50 → $3.006h
- ▼ 1.5%Meta: Llama 3.2 3B Instructmeta-llama · output $0.34 → $0.336h
- ▼ 1.8%Meta: Llama 3.2 3B Instructmeta-llama · input $0.0509 → $0.05006h
- ▼ 10.8%DeepSeek: DeepSeek V4 Pro 0813deepseek · output $4.44 → $3.966h
- ▲ 1089.2%DeepSeek: DeepSeek V4 Pro 0813deepseek · input $0.11 → $1.326h
- ▼ 40.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · output $0.30 → $0.186h
- ▲ 20.0%DeepSeek: DeepSeek V4 Flash Latestdeepseek · input $0.0500 → $0.06006h
- ▼ 23.3%DeepSeek: DeepSeek V4 Flash 0731deepseek · output $0.30 → $0.236h
Price cuts are green — they make AI cheaper for everyone.