💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 20h. 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 |
|---|---|---|---|---|---|---|---|---|
| llama-v3p2-3bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| llama-v3p2-1bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| llama-v3p1-70b-instruct-1bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 4K | |
| llama-v3p1-405b-instruct-longfireworks_ai | — | $0.10 | $0.10 | — | — | — | 4K | |
| llama-v2-70bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 4K | |
| llama-guard-3-1bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| gemma-2b-itfireworks_ai | — | $0.10 | $0.10 | — | — | — | 8K | |
| flux-1-schnellfireworks_ai | — | $0.10 | $0.10 | — | — | — | 4K | |
| flux-1-devfireworks_ai | — | $0.10 | $0.10 | — | — | — | 4K | |
| ernie-4p5-300b-a47b-ptfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| ernie-4p5-21b-a3b-ptfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| deepseek-r1-distill-qwen-1p5bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| deepseek-coder-1b-basefireworks_ai | — | $0.10 | $0.10 | — | — | — | 16K | |
| cogito-v1-preview-llama-3bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| codegemma-2bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 8K | |
| glm-4-32b-0414-128kzai | — | $0.10 | $0.10 | — | — | — | 128K | |
| mistral-small-2503watsonx | — | $0.10 | $0.30 | — | — | — | 32K | |
| llama-3-2-1b-instruct💬watsonx | 1055 | $0.10 | $0.10 | — | — | — | 128K | |
| granite-vision-3-2-2bwatsonx | — | $0.10 | $0.10 | — | — | — | 8K | |
| granite-guardian-3-2-2bwatsonx | — | $0.10 | $0.10 | — | — | — | 8K | |
| mistral-small-2503@001vertex_ai-mistral_models | — | $0.10 | $0.30 | — | — | — | 32K | |
| mistral-small-2503vertex_ai-mistral_models | — | $0.10 | $0.30 | — | — | — | 128K | |
| gpt-4.1-nano💬vercel_ai_gateway | — | $0.10 | $0.40 | $0.0250 | free | — | 1.0M | |
| mistral-smallvercel_ai_gateway | — | $0.10 | $0.30 | — | — | — | 32K | |
| mistral-embedvercel_ai_gateway | — | $0.10 | free | — | — | — | 0 | |
| ministral-8b💬vercel_ai_gateway | — | $0.10 | $0.10 | — | — | — | 128K | |
| llama-4-scout💬vercel_ai_gateway | — | $0.10 | $0.30 | — | — | — | 131K | |
| llama-3.2-1bvercel_ai_gateway | — | $0.10 | $0.10 | — | — | — | 128K | |
| qwen-3-32bvercel_ai_gateway | — | $0.10 | $0.30 | — | — | — | 41K | |
| qwen-3-30bvercel_ai_gateway | — | $0.10 | $0.30 | — | — | — | 41K | |
| qwen2p5-coder-0p5b-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| qwen2p5-coder-0p5bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| qwen2p5-1p5b-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| qwen2p5-0p5b-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| qwen2-vl-2b-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| phi-3-mini-128k-instructfireworks_ai | — | $0.10 | $0.10 | — | — | — | 131K | |
| phi-2-3bfireworks_ai | — | $0.10 | $0.10 | — | — | — | 2K | |
| qwen-2-1.5b-instructtogether_ai | — | $0.10 | $0.10 | — | — | — | 33K | |
| together-ai-up-to-4btogether_ai | — | $0.10 | $0.10 | — | — | — | — | |
| llama3.2-1bsnowflake | — | $0.10 | $0.10 | — | — | — | 128K | |
| claude-haiku-5-5💬snowflake | — | $0.10 | $0.50 | $0.0100 | $0.13 | — | — | |
| gpt-4.1-nano💬replicate | — | $0.10 | $0.40 | — | — | — | — | |
| llama-2-13b-chatreplicate | — | $0.10 | $0.50 | — | — | — | 4K | |
| llama-2-13breplicate | — | $0.10 | $0.50 | — | — | — | 4K | |
| Mistral-7B-Instruct-v0.3ovhcloud | — | $0.10 | $0.10 | — | — | — | 127K | |
| Llama-3.1-8B-Instruct💬ovhcloud | 1187 | $0.10 | $0.10 | — | — | — | 131K | |
| Qwen3-30B-A3B-Instruct-2507💬nebius | 1384 | $0.10 | $0.30 | $0.10 | — | — | 262K | |
| Cosmos3-Super-Reasonernebius | — | $0.10 | $0.30 | — | — | — | 262K | |
| Qwen3-30B-A3B💬nebius | 1317 | $0.10 | $0.30 | — | — | — | 33K | |
| Qwen3-32B💬nebius | 1340 | $0.10 | $0.30 | — | — | — | 41K |
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.