LLM PRICING COMPARISON
API token prices for every major AI model.
Input and output cost per 1 million tokens, context windows, and tokenizer accuracy for 41 models, refreshed from official provider pricing pages. Last checked 2026-07-01. Click any model for a dedicated token counter.
| Model | Provider | Input / 1M tok | Output / 1M tok | Context window | Count accuracy |
|---|---|---|---|---|---|
| Qwen3.5 Plus | Alibaba | $0.40 | $2.40 | 1,000,000 | Estimated |
| Qwen3 Max | Alibaba | $1.20 | $6.00 | 252,000 | Exact |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | 200,000 | Estimated |
| Claude Sonnet 4.6 | Anthropic | $3.00 | $15.00 | 200,000 | Estimated |
| Claude Sonnet 4.5 | Anthropic | $3.00 | $15.00 | 200,000 | Estimated |
| Claude Opus 4.8 | Anthropic | $5.00 | $75.00 | 200,000 | Estimated |
| DeepSeek V4 Flash | DeepSeek | $0.14 | $0.28 | 1,000,000 | Estimated |
| DeepSeek V4 Pro | DeepSeek | $0.435 | $0.87 | 1,000,000 | Estimated |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1,048,576 | Estimated | |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 | 1,048,576 | Estimated | |
| Gemini 2.5 Flash | $0.30 | $2.50 | 1,048,576 | Estimated | |
| Gemini 2.5 Pro | $1.25 | $10.00 | 1,048,576 | Estimated | |
| Gemini 3.5 Flash | $1.50 | $9.00 | 1,048,576 | Estimated | |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 1,048,576 | Estimated | |
| Llama 4 Scout | Meta | Self-hosted | Self-hosted | 10,000,000 | Estimated |
| Llama 4 Maverick | Meta | Self-hosted | Self-hosted | 1,000,000 | Estimated |
| Mistral Medium 3.5 | Mistral | $0.40 | $2.00 | 131,000 | Estimated |
| Magistral Medium | Mistral | $2.00 | $5.00 | 128,000 | Estimated |
| Mistral Large | Mistral | $2.00 | $6.00 | 128,000 | Estimated |
| GPT-5 nano | OpenAI | $0.05 | $0.40 | 400,000 | Exact |
| GPT-4.1 nano | OpenAI | $0.10 | $0.40 | 1,047,576 | Exact |
| GPT-4o mini | OpenAI | $0.15 | $0.60 | 128,000 | Exact |
| GPT-5.4 nano | OpenAI | $0.20 | $1.25 | 1,047,576 | Exact |
| GPT-5 mini | OpenAI | $0.25 | $2.00 | 400,000 | Exact |
| GPT-4.1 mini | OpenAI | $0.40 | $1.60 | 1,047,576 | Exact |
| GPT-5.4 mini | OpenAI | $0.75 | $4.50 | 1,047,576 | Exact |
| o4-mini | OpenAI | $1.10 | $4.40 | 200,000 | Exact |
| GPT-5.1 | OpenAI | $1.25 | $10.00 | 400,000 | Exact |
| GPT-5 | OpenAI | $1.25 | $10.00 | 400,000 | Exact |
| GPT-5.2 | OpenAI | $1.75 | $14.00 | 400,000 | Exact |
| GPT-4.1 | OpenAI | $2.00 | $8.00 | 1,047,576 | Exact |
| o3 | OpenAI | $2.00 | $8.00 | 200,000 | Exact |
| GPT-5.4 | OpenAI | $2.50 | $15.00 | 1,047,576 | Exact |
| GPT-4o | OpenAI | $2.50 | $10.00 | 128,000 | Exact |
| GPT-5.5 | OpenAI | $5.00 | $30.00 | 1,047,576 | Exact |
| GPT-5 Pro | OpenAI | $15.00 | $120.00 | 400,000 | Exact |
| GPT-5.2 Pro | OpenAI | $21.00 | $168.00 | 400,000 | Exact |
| GPT-5.5 Pro | OpenAI | $30.00 | $180.00 | 1,047,576 | Exact |
| GPT-5.4 Pro | OpenAI | $30.00 | $180.00 | 1,047,576 | Exact |
| Grok Build 0.1 | xAI | $1.00 | $2.00 | 256,000 | Estimated |
| Grok 4.3 | xAI | $1.25 | $2.50 | 1,000,000 | Estimated |
Extended catalog: 630 more models
Pricing from the community-maintained LiteLLM dataset, refreshed 2026-07-01. Community-tracked rates can lag provider changes — the table above is verified against official pricing pages; this one favors coverage.
| Model | Provider | Input / 1M tok | Output / 1M tok | Context window |
|---|---|---|---|---|
| jamba-1.5 | AI21 Labs | $0.20 | $0.40 | 256,000 |
| jamba-1.5-mini | AI21 Labs | $0.20 | $0.40 | 256,000 |
| jamba-1.5-mini@001 | AI21 Labs | $0.20 | $0.40 | 256,000 |
| jamba-mini-1.6 | AI21 Labs | $0.20 | $0.40 | 256,000 |
| jamba-mini-1.7 | AI21 Labs | $0.20 | $0.40 | 256,000 |
| jamba-1.5-large | AI21 Labs | $2.00 | $8.00 | 256,000 |
| jamba-1.5-large@001 | AI21 Labs | $2.00 | $8.00 | 256,000 |
| jamba-large-1.6 | AI21 Labs | $2.00 | $8.00 | 256,000 |
| jamba-large-1.7 | AI21 Labs | $2.00 | $8.00 | 256,000 |
| qwen-turbo | Alibaba | $0.05 | $0.20 | 129,024 |
| qwen-turbo-2024-11-01 | Alibaba | $0.05 | $0.20 | 1,000,000 |
| qwen-turbo-2025-04-28 | Alibaba | $0.05 | $0.20 | 1,000,000 |
| qwen-turbo-latest | Alibaba | $0.05 | $0.20 | 1,000,000 |
| qwen3-next-80b-a3b-instruct | Alibaba | $0.15 | $1.20 | 262,144 |
| qwen3-next-80b-a3b-thinking | Alibaba | $0.15 | $1.20 | 262,144 |
| qwen3-vl-32b-instruct | Alibaba | $0.16 | $0.64 | 131,072 |
| qwen3-vl-32b-thinking | Alibaba | $0.16 | $2.87 | 131,072 |
| qwen-coder | Alibaba | $0.30 | $1.50 | 1,000,000 |
| qwen-plus | Alibaba | $0.40 | $1.20 | 129,024 |
| qwen-plus-2025-01-25 | Alibaba | $0.40 | $1.20 | 129,024 |
| qwen-plus-2025-04-28 | Alibaba | $0.40 | $1.20 | 129,024 |
| qwen-plus-2025-07-14 | Alibaba | $0.40 | $1.20 | 129,024 |
| qwen3-vl-235b-a22b-instruct | Alibaba | $0.40 | $1.60 | 131,072 |
| qwen3-vl-235b-a22b-thinking | Alibaba | $0.40 | $4.00 | 131,072 |
| qwq-plus | Alibaba | $0.80 | $2.40 | 98,304 |
| qwen-max | Alibaba | $1.60 | $6.40 | 30,720 |
| claude-3-haiku-20240307 | Anthropic | $0.25 | $1.25 | 200,000 |
| claude-haiku-4-5-20251001 | Anthropic | $1.00 | $5.00 | 200,000 |
| claude-3-7-sonnet-20250219 | Anthropic | $3.00 | $15.00 | 200,000 |
| claude-4-sonnet-20250514 | Anthropic | $3.00 | $15.00 | 1,000,000 |
| claude-sonnet-4-20250514 | Anthropic | $3.00 | $15.00 | 1,000,000 |
| claude-sonnet-4-5-20250929 | Anthropic | $3.00 | $15.00 | 200,000 |
| claude-sonnet-5 | Anthropic | $3.00 | $15.00 | 1,000,000 |
| claude-opus-4-5 | Anthropic | $5.00 | $25.00 | 200,000 |
| claude-opus-4-5-20251101 | Anthropic | $5.00 | $25.00 | 200,000 |
| claude-opus-4-6 | Anthropic | $5.00 | $25.00 | 1,000,000 |
| claude-opus-4-6-20260205 | Anthropic | $5.00 | $25.00 | 1,000,000 |
| claude-opus-4-7 | Anthropic | $5.00 | $25.00 | 1,000,000 |
| claude-opus-4-7-20260416 | Anthropic | $5.00 | $25.00 | 1,000,000 |
| claude-fable-5 | Anthropic | $10.00 | $50.00 | 1,000,000 |
| claude-3-opus-20240229 | Anthropic | $15.00 | $75.00 | 200,000 |
| claude-4-opus-20250514 | Anthropic | $15.00 | $75.00 | 200,000 |
| claude-opus-4-1 | Anthropic | $15.00 | $75.00 | 200,000 |
| claude-opus-4-1-20250805 | Anthropic | $15.00 | $75.00 | 200,000 |
| claude-opus-4-20250514 | Anthropic | $15.00 | $75.00 | 200,000 |
| llama3.1-8b | Cerebras | $0.10 | $0.10 | 128,000 |
| llama3.1-70b | Cerebras | $0.60 | $0.60 | 128,000 |
| llama-3.3-70b | Cerebras | $0.85 | $1.20 | 128,000 |
| zai-glm-4.6 | Cerebras | $2.25 | $2.75 | 128,000 |
| zai-glm-4.7 | Cerebras | $2.25 | $2.75 | 128,000 |
| Llama-3.2-3B-Instruct | DeepInfra | $0.02 | $0.02 | 131,072 |
| Meta-Llama-3.1-8B-Instruct-Turbo | DeepInfra | $0.02 | $0.03 | 131,072 |
| Meta-Llama-3-8B-Instruct | DeepInfra | $0.03 | $0.06 | 8,192 |
| gemma-3-4b-it | DeepInfra | $0.04 | $0.08 | 131,072 |
| L3-8B-Lunaris-v1-Turbo | DeepInfra | $0.04 | $0.05 | 8,192 |
| Qwen2.5-7B-Instruct | DeepInfra | $0.04 | $0.10 | 32,768 |
| Llama-3.2-11B-Vision-Instruct | DeepInfra | $0.049 | $0.049 | 131,072 |
| gemma-3-12b-it | DeepInfra | $0.05 | $0.10 | 131,072 |
| phi-4 | DeepInfra | $0.07 | $0.14 | 16,384 |
| Mistral-Small-3.2-24B-Instruct-2506 | DeepInfra | $0.075 | $0.20 | 128,000 |
| Llama-3.3-Nemotron-Super-49B-v1.5 | DeepInfra | $0.10 | $0.40 | 131,072 |
| Meta-Llama-3.1-70B-Instruct-Turbo | DeepInfra | $0.10 | $0.28 | 131,072 |
| Qwen2.5-72B-Instruct | DeepInfra | $0.12 | $0.39 | 32,768 |
| Llama-3.3-70B-Instruct-Turbo | DeepInfra | $0.13 | $0.39 | 131,072 |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | DeepInfra | $0.15 | $0.60 | 1,048,576 |
| Qwen2.5-VL-32B-Instruct | DeepInfra | $0.20 | $0.60 | 128,000 |
| Llama-3.3-70B-Instruct | DeepInfra | $0.23 | $0.40 | 131,072 |
| DeepSeek-V3.1-Terminus | DeepInfra | $0.27 | $1.00 | 163,840 |
| olmOCR-7B-0725-FP8 | DeepInfra | $0.27 | $1.50 | 16,384 |
| Qwen3-Coder-480B-A35B-Instruct-Turbo | DeepInfra | $0.29 | $1.20 | 262,144 |
| Hermes-3-Llama-3.1-70B | DeepInfra | $0.30 | $0.30 | 131,072 |
| GLM-4.5 | DeepInfra | $0.40 | $1.60 | 131,072 |
| Meta-Llama-3.1-70B-Instruct | DeepInfra | $0.40 | $0.40 | 131,072 |
| Mixtral-8x7B-Instruct-v0.1 | DeepInfra | $0.40 | $0.40 | 32,768 |
| WizardLM-2-8x22B | DeepInfra | $0.48 | $0.48 | 65,536 |
| Llama-3.1-Nemotron-70B-Instruct | DeepInfra | $0.60 | $0.60 | 131,072 |
| L3.1-70B-Euryale-v2.2 | DeepInfra | $0.65 | $0.75 | 131,072 |
| L3.3-70B-Euryale-v2.3 | DeepInfra | $0.65 | $0.75 | 131,072 |
| DeepSeek-R1-0528-Turbo | DeepInfra | $1.00 | $3.00 | 32,768 |
| DeepSeek-R1-Turbo | DeepInfra | $1.00 | $3.00 | 40,960 |
| Hermes-3-Llama-3.1-405B | DeepInfra | $1.00 | $1.00 | 131,072 |
| claude-3-7-sonnet-latest | DeepInfra | $3.30 | $16.50 | 200,000 |
| claude-4-sonnet | DeepInfra | $3.30 | $16.50 | 200,000 |
| claude-4-opus | DeepInfra | $16.50 | $82.50 | 200,000 |
| deepseek-coder | DeepSeek | $0.14 | $0.28 | 128,000 |
| deepseek-v3 | DeepSeek | $0.27 | $1.10 | 65,536 |
| deepseek-chat | DeepSeek | $0.28 | $0.42 | 131,072 |
| deepseek-reasoner | DeepSeek | $0.28 | $0.42 | 131,072 |
| deepseek-v3.2 | DeepSeek | $0.28 | $0.40 | 163,840 |
| deepseek-r1 | DeepSeek | $0.55 | $2.19 | 65,536 |
| flux-1-dev-controlnet-union | Fireworks AI | $0.001 | $0.001 | 4,096 |
| codegemma-2b | Fireworks AI | $0.10 | $0.10 | 8,192 |
| cogito-v1-preview-llama-3b | Fireworks AI | $0.10 | $0.10 | 131,072 |
| deepseek-coder-1b-base | Fireworks AI | $0.10 | $0.10 | 16,384 |
| deepseek-r1-distill-qwen-1p5b | Fireworks AI | $0.10 | $0.10 | 131,072 |
| ernie-4p5-21b-a3b-pt | Fireworks AI | $0.10 | $0.10 | 4,096 |
| ernie-4p5-300b-a47b-pt | Fireworks AI | $0.10 | $0.10 | 4,096 |
| flux-1-dev | Fireworks AI | $0.10 | $0.10 | 4,096 |
| flux-1-schnell | Fireworks AI | $0.10 | $0.10 | 4,096 |
| gemma-2b-it | Fireworks AI | $0.10 | $0.10 | 8,192 |
| llama-guard-3-1b | Fireworks AI | $0.10 | $0.10 | 131,072 |
| llama-v2-70b | Fireworks AI | $0.10 | $0.10 | 4,096 |
| llama-v3p1-405b-instruct-long | Fireworks AI | $0.10 | $0.10 | 4,096 |
| llama-v3p1-70b-instruct-1b | Fireworks AI | $0.10 | $0.10 | 4,096 |
| llama-v3p1-8b-instruct | Fireworks AI | $0.10 | $0.10 | 16,384 |
| llama-v3p2-1b | Fireworks AI | $0.10 | $0.10 | 131,072 |
| llama-v3p2-1b-instruct | Fireworks AI | $0.10 | $0.10 | 16,384 |
| llama-v3p2-3b | Fireworks AI | $0.10 | $0.10 | 131,072 |
| llama-v3p2-3b-instruct | Fireworks AI | $0.10 | $0.10 | 16,384 |
| minimax-m1-80k | Fireworks AI | $0.10 | $0.10 | 4,096 |
| ministral-3-3b-instruct-2512 | Fireworks AI | $0.10 | $0.10 | 256,000 |
| nemotron-nano-v2-12b-vl | Fireworks AI | $0.10 | $0.10 | 4,096 |
| phi-2-3b | Fireworks AI | $0.10 | $0.10 | 2,048 |
| phi-3-mini-128k-instruct | Fireworks AI | $0.10 | $0.10 | 131,072 |
| qwen2-vl-2b-instruct | Fireworks AI | $0.10 | $0.10 | 32,768 |
| qwen2p5-0p5b-instruct | Fireworks AI | $0.10 | $0.10 | 32,768 |
| qwen2p5-1p5b-instruct | Fireworks AI | $0.10 | $0.10 | 32,768 |
| qwen2p5-coder-0p5b | Fireworks AI | $0.10 | $0.10 | 32,768 |
| qwen2p5-coder-0p5b-instruct | Fireworks AI | $0.10 | $0.10 | 32,768 |
| qwen2p5-coder-1p5b | Fireworks AI | $0.10 | $0.10 | 32,768 |
| qwen2p5-coder-1p5b-instruct | Fireworks AI | $0.10 | $0.10 | 32,768 |
| qwen2p5-coder-3b | Fireworks AI | $0.10 | $0.10 | 32,768 |
| qwen2p5-coder-3b-instruct | Fireworks AI | $0.10 | $0.10 | 32,768 |
| qwen3-0p6b | Fireworks AI | $0.10 | $0.10 | 40,960 |
| qwen3-1p7b | Fireworks AI | $0.10 | $0.10 | 131,072 |
| qwen3-1p7b-fp8-draft | Fireworks AI | $0.10 | $0.10 | 262,144 |
| qwen3-1p7b-fp8-draft-131072 | Fireworks AI | $0.10 | $0.10 | 131,072 |
| qwen3-1p7b-fp8-draft-40960 | Fireworks AI | $0.10 | $0.10 | 40,960 |
| stablecode-3b | Fireworks AI | $0.10 | $0.10 | 4,096 |
| starcoder2-3b | Fireworks AI | $0.10 | $0.10 | 16,384 |
| llama4-scout-instruct-basic | Fireworks AI | $0.15 | $0.60 | 131,072 |
| qwen3-30b-a3b | Fireworks AI | $0.15 | $0.60 | 131,072 |
| qwen3-coder-30b-a3b-instruct | Fireworks AI | $0.15 | $0.60 | 262,144 |
| qwen3-vl-30b-a3b-instruct | Fireworks AI | $0.15 | $0.60 | 262,144 |
| qwen3-vl-30b-a3b-thinking | Fireworks AI | $0.15 | $0.60 | 262,144 |
| chronos-hermes-13b-v2 | Fireworks AI | $0.20 | $0.20 | 4,096 |
| code-llama-13b | Fireworks AI | $0.20 | $0.20 | 16,384 |
| code-llama-13b-instruct | Fireworks AI | $0.20 | $0.20 | 16,384 |
| code-llama-13b-python | Fireworks AI | $0.20 | $0.20 | 16,384 |
| code-llama-7b | Fireworks AI | $0.20 | $0.20 | 16,384 |
| code-llama-7b-instruct | Fireworks AI | $0.20 | $0.20 | 16,384 |
| code-llama-7b-python | Fireworks AI | $0.20 | $0.20 | 16,384 |
| code-qwen-1p5-7b | Fireworks AI | $0.20 | $0.20 | 65,536 |
| codegemma-7b | Fireworks AI | $0.20 | $0.20 | 8,192 |
| cogito-v1-preview-llama-8b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| cogito-v1-preview-qwen-14b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| deepseek-coder-7b-base | Fireworks AI | $0.20 | $0.20 | 4,096 |
| deepseek-coder-7b-base-v1p5 | Fireworks AI | $0.20 | $0.20 | 4,096 |
| deepseek-coder-7b-instruct-v1p5 | Fireworks AI | $0.20 | $0.20 | 4,096 |
| deepseek-r1-0528-distill-qwen3-8b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| deepseek-r1-distill-llama-8b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| deepseek-r1-distill-qwen-14b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| deepseek-r1-distill-qwen-7b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| dobby-mini-unhinged-plus-llama-3-1-8b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| firellava-13b | Fireworks AI | $0.20 | $0.20 | 4,096 |
| firesearch-ocr-v6 | Fireworks AI | $0.20 | $0.20 | 8,192 |
| gemma-7b | Fireworks AI | $0.20 | $0.20 | 8,192 |
| gemma2-9b-it | Fireworks AI | $0.20 | $0.20 | 8,192 |
| hermes-2-pro-mistral-7b | Fireworks AI | $0.20 | $0.20 | 32,768 |
| internvl3-8b | Fireworks AI | $0.20 | $0.20 | 16,384 |
| llama-guard-2-8b | Fireworks AI | $0.20 | $0.20 | 8,192 |
| llama-guard-3-8b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| llama-v2-13b | Fireworks AI | $0.20 | $0.20 | 4,096 |
| llama-v2-13b-chat | Fireworks AI | $0.20 | $0.20 | 4,096 |
| llama-v2-7b | Fireworks AI | $0.20 | $0.20 | 4,096 |
| llama-v2-7b-chat | Fireworks AI | $0.20 | $0.20 | 4,096 |
| llama-v3-8b | Fireworks AI | $0.20 | $0.20 | 8,192 |
| llama-v3-8b-instruct-hf | Fireworks AI | $0.20 | $0.20 | 8,192 |
| llama-v3p2-11b-vision-instruct | Fireworks AI | $0.20 | $0.20 | 16,384 |
| llamaguard-7b | Fireworks AI | $0.20 | $0.20 | 4,096 |
| ministral-3-14b-instruct-2512 | Fireworks AI | $0.20 | $0.20 | 256,000 |
| ministral-3-8b-instruct-2512 | Fireworks AI | $0.20 | $0.20 | 256,000 |
| mistral-7b | Fireworks AI | $0.20 | $0.20 | 32,768 |
| mistral-7b-instruct-4k | Fireworks AI | $0.20 | $0.20 | 32,768 |
| mistral-7b-instruct-v0p2 | Fireworks AI | $0.20 | $0.20 | 32,768 |
| mistral-7b-instruct-v3 | Fireworks AI | $0.20 | $0.20 | 32,768 |
| mistral-7b-v0p2 | Fireworks AI | $0.20 | $0.20 | 32,768 |
| mistral-nemo-base-2407 | Fireworks AI | $0.20 | $0.20 | 128,000 |
| mistral-nemo-instruct-2407 | Fireworks AI | $0.20 | $0.20 | 128,000 |
| mythomax-l2-13b | Fireworks AI | $0.20 | $0.20 | 4,096 |
| nous-capybara-7b-v1p9 | Fireworks AI | $0.20 | $0.20 | 32,768 |
| nous-hermes-llama2-13b | Fireworks AI | $0.20 | $0.20 | 4,096 |
| nous-hermes-llama2-7b | Fireworks AI | $0.20 | $0.20 | 4,096 |
| nvidia-nemotron-nano-12b-v2 | Fireworks AI | $0.20 | $0.20 | 131,072 |
| nvidia-nemotron-nano-9b-v2 | Fireworks AI | $0.20 | $0.20 | 131,072 |
| openchat-3p5-0106-7b | Fireworks AI | $0.20 | $0.20 | 8,192 |
| openhermes-2-mistral-7b | Fireworks AI | $0.20 | $0.20 | 32,768 |
| openhermes-2p5-mistral-7b | Fireworks AI | $0.20 | $0.20 | 32,768 |
| openorca-7b | Fireworks AI | $0.20 | $0.20 | 32,768 |
| phi-3-vision-128k-instruct | Fireworks AI | $0.20 | $0.20 | 32,064 |
| pythia-12b | Fireworks AI | $0.20 | $0.20 | 2,048 |
| qwen-v2p5-14b-instruct | Fireworks AI | $0.20 | $0.20 | 32,768 |
| qwen-v2p5-7b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| qwen2-7b-instruct | Fireworks AI | $0.20 | $0.20 | 32,768 |
| qwen2-vl-7b-instruct | Fireworks AI | $0.20 | $0.20 | 32,768 |
| qwen2p5-14b | Fireworks AI | $0.20 | $0.20 | 131,072 |
| qwen2p5-7b-instruct | Fireworks AI | $0.20 | $0.20 | 32,768 |
| qwen2p5-coder-14b | Fireworks AI | $0.20 | $0.20 | 32,768 |
| qwen2p5-coder-14b-instruct | Fireworks AI | $0.20 | $0.20 | 32,768 |
| qwen2p5-coder-7b | Fireworks AI | $0.20 | $0.20 | 32,768 |
| qwen2p5-coder-7b-instruct | Fireworks AI | $0.20 | $0.20 | 32,768 |
| qwen2p5-vl-3b-instruct | Fireworks AI | $0.20 | $0.20 | 128,000 |
| qwen2p5-vl-7b-instruct | Fireworks AI | $0.20 | $0.20 | 128,000 |
| qwen3-14b | Fireworks AI | $0.20 | $0.20 | 40,960 |
| qwen3-4b | Fireworks AI | $0.20 | $0.20 | 40,960 |
| qwen3-4b-instruct-2507 | Fireworks AI | $0.20 | $0.20 | 262,144 |
| qwen3-8b | Fireworks AI | $0.20 | $0.20 | 40,960 |
| qwen3-vl-8b-instruct | Fireworks AI | $0.20 | $0.20 | 4,096 |
| rolm-ocr | Fireworks AI | $0.20 | $0.20 | 128,000 |
| snorkel-mistral-7b-pairrm-dpo | Fireworks AI | $0.20 | $0.20 | 32,768 |
| starcoder-16b | Fireworks AI | $0.20 | $0.20 | 8,192 |
| starcoder-7b | Fireworks AI | $0.20 | $0.20 | 8,192 |
| starcoder2-15b | Fireworks AI | $0.20 | $0.20 | 16,384 |
| starcoder2-7b | Fireworks AI | $0.20 | $0.20 | 16,384 |
| toppy-m-7b | Fireworks AI | $0.20 | $0.20 | 32,768 |
| yi-6b | Fireworks AI | $0.20 | $0.20 | 4,096 |
| zephyr-7b-beta | Fireworks AI | $0.20 | $0.20 | 32,768 |
| glm-4p5-air | Fireworks AI | $0.22 | $0.88 | 128,000 |
| llama4-maverick-instruct-basic | Fireworks AI | $0.22 | $0.88 | 131,072 |
| qwen3-235b-a22b | Fireworks AI | $0.22 | $0.88 | 131,072 |
| qwen3-235b-a22b-instruct-2507 | Fireworks AI | $0.22 | $0.88 | 262,144 |
| minimax-m2 | Fireworks AI | $0.30 | $1.20 | 4,096 |
| minimax-m2p1 | Fireworks AI | $0.30 | $1.20 | 204,800 |
| minimax-m2p7 | Fireworks AI | $0.30 | $1.20 | 196,608 |
| minimax-m3 | Fireworks AI | $0.30 | $1.20 | 512,000 |
| qwen3p7-plus | Fireworks AI | $0.40 | $1.60 | 262,144 |
| qwen3-coder-480b-a35b-instruct | Fireworks AI | $0.45 | $1.80 | 262,144 |
| deepseek-coder-v2-lite-base | Fireworks AI | $0.50 | $0.50 | 163,840 |
| deepseek-coder-v2-lite-instruct | Fireworks AI | $0.50 | $0.50 | 163,840 |
| deepseek-v2-lite-chat | Fireworks AI | $0.50 | $0.50 | 163,840 |
| dolphin-2p6-mixtral-8x7b | Fireworks AI | $0.50 | $0.50 | 32,768 |
| firefunction-v1 | Fireworks AI | $0.50 | $0.50 | 32,768 |
| mixtral-8x7b | Fireworks AI | $0.50 | $0.50 | 32,768 |
| mixtral-8x7b-instruct-hf | Fireworks AI | $0.50 | $0.50 | 32,768 |
| nous-hermes-2-mixtral-8x7b-dpo | Fireworks AI | $0.50 | $0.50 | 32,768 |
| qwen3-30b-a3b-instruct-2507 | Fireworks AI | $0.50 | $0.50 | 262,144 |
| deepseek-r1-basic | Fireworks AI | $0.55 | $2.19 | 128,000 |
| glm-4p5 | Fireworks AI | $0.55 | $2.19 | 128,000 |
| glm-4p6 | Fireworks AI | $0.55 | $2.19 | 202,800 |
| deepseek-v3p1 | Fireworks AI | $0.56 | $1.68 | 128,000 |
| deepseek-v3p1-terminus | Fireworks AI | $0.56 | $1.68 | 128,000 |
| deepseek-v3p2 | Fireworks AI | $0.56 | $1.68 | 163,840 |
| glm-4p7 | Fireworks AI | $0.60 | $2.20 | 202,800 |
| kimi-k2-instruct | Fireworks AI | $0.60 | $2.50 | 131,072 |
| kimi-k2p5 | Fireworks AI | $0.60 | $3.00 | 262,144 |
| code-llama-34b | Fireworks AI | $0.90 | $0.90 | 16,384 |
| code-llama-34b-python | Fireworks AI | $0.90 | $0.90 | 16,384 |
| code-llama-70b | Fireworks AI | $0.90 | $0.90 | 4,096 |
| code-llama-70b-python | Fireworks AI | $0.90 | $0.90 | 4,096 |
| cogito-v1-preview-llama-70b | Fireworks AI | $0.90 | $0.90 | 131,072 |
| cogito-v1-preview-qwen-32b | Fireworks AI | $0.90 | $0.90 | 131,072 |
| deepseek-coder-33b-instruct | Fireworks AI | $0.90 | $0.90 | 16,384 |
| deepseek-r1-distill-qwen-32b | Fireworks AI | $0.90 | $0.90 | 131,072 |
| dobby-unhinged-llama-3-3-70b-new | Fireworks AI | $0.90 | $0.90 | 131,072 |
| dolphin-2-9-2-qwen2-72b | Fireworks AI | $0.90 | $0.90 | 131,072 |
| fare-20b | Fireworks AI | $0.90 | $0.90 | 131,072 |
| firefunction-v2 | Fireworks AI | $0.90 | $0.90 | 8,192 |
| internvl3-38b | Fireworks AI | $0.90 | $0.90 | 16,384 |
| internvl3-78b | Fireworks AI | $0.90 | $0.90 | 16,384 |
| kat-coder | Fireworks AI | $0.90 | $0.90 | 262,144 |
| kat-dev-32b | Fireworks AI | $0.90 | $0.90 | 131,072 |
| kat-dev-72b-exp | Fireworks AI | $0.90 | $0.90 | 131,072 |
| llama-v2-70b-chat | Fireworks AI | $0.90 | $0.90 | 2,048 |
| llama-v3-70b-instruct | Fireworks AI | $0.90 | $0.90 | 8,192 |
| llama-v3-70b-instruct-hf | Fireworks AI | $0.90 | $0.90 | 8,192 |
| llama-v3p1-70b-instruct | Fireworks AI | $0.90 | $0.90 | 131,072 |
| llama-v3p1-nemotron-70b-instruct | Fireworks AI | $0.90 | $0.90 | 131,072 |
| llama-v3p2-90b-vision-instruct | Fireworks AI | $0.90 | $0.90 | 16,384 |
| llama-v3p3-70b-instruct | Fireworks AI | $0.90 | $0.90 | 131,072 |
| llava-yi-34b | Fireworks AI | $0.90 | $0.90 | 4,096 |
| mistral-small-24b-instruct-2501 | Fireworks AI | $0.90 | $0.90 | 32,768 |
| nous-hermes-2-yi-34b | Fireworks AI | $0.90 | $0.90 | 4,096 |
| nous-hermes-llama2-70b | Fireworks AI | $0.90 | $0.90 | 4,096 |
| phind-code-llama-34b-python-v1 | Fireworks AI | $0.90 | $0.90 | 16,384 |
| phind-code-llama-34b-v1 | Fireworks AI | $0.90 | $0.90 | 16,384 |
| phind-code-llama-34b-v2 | Fireworks AI | $0.90 | $0.90 | 16,384 |
| qwen-qwq-32b-preview | Fireworks AI | $0.90 | $0.90 | 32,768 |
| qwen1p5-72b-chat | Fireworks AI | $0.90 | $0.90 | 32,768 |
| qwen2-72b-instruct | Fireworks AI | $0.90 | $0.90 | 32,768 |
| qwen2-vl-72b-instruct | Fireworks AI | $0.90 | $0.90 | 32,768 |
| qwen2p5-32b | Fireworks AI | $0.90 | $0.90 | 131,072 |
| qwen2p5-32b-instruct | Fireworks AI | $0.90 | $0.90 | 32,768 |
| qwen2p5-72b | Fireworks AI | $0.90 | $0.90 | 131,072 |
| qwen2p5-72b-instruct | Fireworks AI | $0.90 | $0.90 | 32,768 |
| qwen2p5-coder-32b | Fireworks AI | $0.90 | $0.90 | 32,768 |
| qwen2p5-coder-32b-instruct | Fireworks AI | $0.90 | $0.90 | 4,096 |
| qwen2p5-coder-32b-instruct-128k | Fireworks AI | $0.90 | $0.90 | 131,072 |
| qwen2p5-coder-32b-instruct-32k-rope | Fireworks AI | $0.90 | $0.90 | 32,768 |
| qwen2p5-coder-32b-instruct-64k | Fireworks AI | $0.90 | $0.90 | 65,536 |
| qwen2p5-math-72b-instruct | Fireworks AI | $0.90 | $0.90 | 4,096 |
| qwen2p5-vl-32b-instruct | Fireworks AI | $0.90 | $0.90 | 128,000 |
| qwen2p5-vl-72b-instruct | Fireworks AI | $0.90 | $0.90 | 128,000 |
| qwen3-30b-a3b-thinking-2507 | Fireworks AI | $0.90 | $0.90 | 262,144 |
| qwen3-coder-480b-instruct-bf16 | Fireworks AI | $0.90 | $0.90 | 4,096 |
| yi-34b | Fireworks AI | $0.90 | $0.90 | 4,096 |
| yi-34b-200k-capybara | Fireworks AI | $0.90 | $0.90 | 200,000 |
| yi-34b-chat | Fireworks AI | $0.90 | $0.90 | 4,096 |
| kimi-k2p6 | Fireworks AI | $0.95 | $4.00 | 262,144 |
| kimi-k2p7-code | Fireworks AI | $0.95 | $4.00 | 262,144 |
| cogito-671b-v2-p1 | Fireworks AI | $1.20 | $1.20 | 163,840 |
| dbrx-instruct | Fireworks AI | $1.20 | $1.20 | 32,768 |
| deepseek-coder-v2-instruct | Fireworks AI | $1.20 | $1.20 | 65,536 |
| deepseek-prover-v2 | Fireworks AI | $1.20 | $1.20 | 163,840 |
| deepseek-v2p5 | Fireworks AI | $1.20 | $1.20 | 32,768 |
| glm-4p5v | Fireworks AI | $1.20 | $1.20 | 131,072 |
| gpt-oss-safeguard-120b | Fireworks AI | $1.20 | $1.20 | 131,072 |
| mistral-large-3-fp8 | Fireworks AI | $1.20 | $1.20 | 256,000 |
| mixtral-8x22b | Fireworks AI | $1.20 | $1.20 | 65,536 |
| mixtral-8x22b-instruct | Fireworks AI | $1.20 | $1.20 | 65,536 |
| mixtral-8x22b-instruct-hf | Fireworks AI | $1.20 | $1.20 | 65,536 |
| glm-5p1 | Fireworks AI | $1.40 | $4.40 | 202,800 |
| glm-5p2 | Fireworks AI | $1.40 | $4.40 | 1,048,576 |
| kimi-k2p7-code-fast | Fireworks AI | $1.90 | $8.00 | 262,144 |
| kimi-k2p6-fast | Fireworks AI | $2.00 | $8.00 | 262,144 |
| glm-5p1-fast | Fireworks AI | $2.80 | $8.80 | 202,800 |
| deepseek-r1-0528 | Fireworks AI | $3.00 | $8.00 | 160,000 |
| llama-v3p1-405b-instruct | Fireworks AI | $3.00 | $3.00 | 128,000 |
| yi-large | Fireworks AI | $3.00 | $3.00 | 32,768 |
| gemini-exp-1114 | $0.00 | $0.00 | 1,048,576 | |
| gemini-exp-1206 | $0.00 | $0.00 | 2,097,152 | |
| gemma-3-27b-it | $0.00 | $0.00 | 131,072 | |
| learnlm-1.5-pro-experimental | $0.00 | $0.00 | 32,767 | |
| lyria-3-clip-preview | $0.00 | $0.00 | 131,072 | |
| lyria-3-pro-preview | $0.00 | $0.00 | 131,072 | |
| gemini-2.0-flash-lite | $0.075 | $0.30 | 1,048,576 | |
| gemini-2.0-flash-lite-001 | $0.075 | $0.30 | 1,048,576 | |
| gemini-2.0-flash | $0.10 | $0.40 | 1,048,576 | |
| gemini-2.0-flash-001 | $0.10 | $0.40 | 1,048,576 | |
| gemini-2.5-flash-lite-preview-06-17 | $0.10 | $0.40 | 1,048,576 | |
| gemini-2.5-flash-lite-preview-09-2025 | $0.10 | $0.40 | 1,048,576 | |
| gemini-flash-lite-latest | $0.10 | $0.40 | 1,048,576 | |
| gemini-3.1-flash-lite-preview | $0.25 | $1.50 | 1,048,576 | |
| gemini-2.5-flash-native-audio-latest | $0.30 | $2.50 | 1,048,576 | |
| gemini-2.5-flash-native-audio-preview-09-2025 | $0.30 | $2.50 | 1,048,576 | |
| gemini-2.5-flash-native-audio-preview-12-2025 | $0.30 | $2.50 | 1,048,576 | |
| gemini-2.5-flash-preview-09-2025 | $0.30 | $2.50 | 1,048,576 | |
| gemini-flash-latest | $0.30 | $2.50 | 1,048,576 | |
| gemini-robotics-er-1.5-preview | $0.30 | $2.50 | 1,048,576 | |
| gemini-gemma-2-27b-it | $0.35 | $1.05 | 8,192 | |
| gemini-gemma-2-9b-it | $0.35 | $1.05 | 8,192 | |
| gemini-3-flash-preview | $0.50 | $3.00 | 1,048,576 | |
| gemini-3.1-flash-live-preview | $0.75 | $4.50 | 131,072 | |
| gemini-2.5-computer-use-preview-10-2025 | $1.25 | $10.00 | 128,000 | |
| gemini-2.5-pro-preview-tts | $1.25 | $10.00 | 1,048,576 | |
| gemini-pro-latest | $1.25 | $10.00 | 1,048,576 | |
| gemini-3-pro-preview | $2.00 | $12.00 | 1,048,576 | |
| gemini-3.1-pro-preview-customtools | $2.00 | $12.00 | 1,048,576 | |
| gemma-7b-it | Groq | $0.05 | $0.08 | 8,192 |
| llama-3.1-8b-instant | Groq | $0.05 | $0.08 | 128,000 |
| gpt-oss-20b | Groq | $0.075 | $0.30 | 131,072 |
| gpt-oss-safeguard-20b | Groq | $0.075 | $0.30 | 131,072 |
| llama-4-scout-17b-16e-instruct | Groq | $0.11 | $0.34 | 131,072 |
| gpt-oss-120b | Groq | $0.15 | $0.60 | 131,072 |
| llama-4-maverick-17b-128e-instruct | Groq | $0.20 | $0.60 | 131,072 |
| llama-guard-4-12b | Groq | $0.20 | $0.20 | 8,192 |
| qwen3-32b | Groq | $0.29 | $0.59 | 131,000 |
| llama-3.3-70b-versatile | Groq | $0.59 | $0.79 | 128,000 |
| kimi-k2-instruct-0905 | Groq | $1.00 | $3.00 | 262,144 |
| mistral-small-3-2-2506 | Mistral | $0.06 | $0.18 | 131,072 |
| mistral-small-latest | Mistral | $0.06 | $0.18 | 131,072 |
| devstral-small-2505 | Mistral | $0.10 | $0.30 | 128,000 |
| devstral-small-2507 | Mistral | $0.10 | $0.30 | 128,000 |
| devstral-small-latest | Mistral | $0.10 | $0.30 | 256,000 |
| labs-devstral-small-2512 | Mistral | $0.10 | $0.30 | 256,000 |
| ministral-3-3b-2512 | Mistral | $0.10 | $0.10 | 131,072 |
| mistral-small | Mistral | $0.10 | $0.30 | 32,000 |
| ministral-3-8b-2512 | Mistral | $0.15 | $0.15 | 262,144 |
| ministral-8b-2512 | Mistral | $0.15 | $0.15 | 262,144 |
| ministral-8b-latest | Mistral | $0.15 | $0.15 | 262,144 |
| pixtral-12b-2409 | Mistral | $0.15 | $0.15 | 128,000 |
| ministral-3-14b-2512 | Mistral | $0.20 | $0.20 | 262,144 |
| codestral-mamba-latest | Mistral | $0.25 | $0.25 | 256,000 |
| mistral-tiny | Mistral | $0.25 | $0.25 | 32,000 |
| open-codestral-mamba | Mistral | $0.25 | $0.25 | 256,000 |
| open-mistral-7b | Mistral | $0.25 | $0.25 | 32,000 |
| codestral-2508 | Mistral | $0.30 | $0.90 | 256,000 |
| open-mistral-nemo | Mistral | $0.30 | $0.30 | 128,000 |
| open-mistral-nemo-2407 | Mistral | $0.30 | $0.30 | 128,000 |
| devstral-2512 | Mistral | $0.40 | $2.00 | 256,000 |
| devstral-latest | Mistral | $0.40 | $2.00 | 256,000 |
| devstral-medium-2507 | Mistral | $0.40 | $2.00 | 128,000 |
| devstral-medium-latest | Mistral | $0.40 | $2.00 | 256,000 |
| mistral-medium-2505 | Mistral | $0.40 | $2.00 | 131,072 |
| mistral-medium-2508 | Mistral | $0.40 | $2.00 | 131,072 |
| mistral-medium-3-1-2508 | Mistral | $0.40 | $2.00 | 131,072 |
| magistral-small-1-2-2509 | Mistral | $0.50 | $1.50 | 40,000 |
| magistral-small-2506 | Mistral | $0.50 | $1.50 | 40,000 |
| magistral-small-latest | Mistral | $0.50 | $1.50 | 40,000 |
| mistral-large-2512 | Mistral | $0.50 | $1.50 | 262,144 |
| mistral-large-3 | Mistral | $0.50 | $1.50 | 262,144 |
| mistral-large-latest | Mistral | $0.50 | $1.50 | 262,144 |
| open-mixtral-8x7b | Mistral | $0.70 | $0.70 | 32,000 |
| codestral-2405 | Mistral | $1.00 | $3.00 | 32,000 |
| codestral-latest | Mistral | $1.00 | $3.00 | 32,000 |
| mistral-medium-2604 | Mistral | $1.50 | $7.50 | 262,144 |
| mistral-medium-latest | Mistral | $1.50 | $7.50 | 262,144 |
| magistral-medium-1-2-2509 | Mistral | $2.00 | $5.00 | 40,000 |
| magistral-medium-2506 | Mistral | $2.00 | $5.00 | 40,000 |
| magistral-medium-2509 | Mistral | $2.00 | $5.00 | 40,000 |
| magistral-medium-latest | Mistral | $2.00 | $5.00 | 40,000 |
| mistral-large-2411 | Mistral | $2.00 | $6.00 | 128,000 |
| open-mixtral-8x22b | Mistral | $2.00 | $6.00 | 65,336 |
| pixtral-large-2411 | Mistral | $2.00 | $6.00 | 128,000 |
| pixtral-large-latest | Mistral | $2.00 | $6.00 | 128,000 |
| mistral-medium | Mistral | $2.70 | $8.10 | 32,000 |
| mistral-medium-2312 | Mistral | $2.70 | $8.10 | 32,000 |
| mistral-large-2407 | Mistral | $3.00 | $9.00 | 128,000 |
| mistral-large-2402 | Mistral | $4.00 | $12.00 | 32,000 |
| kimi-latest-8k | Moonshot AI | $0.20 | $2.00 | 8,192 |
| moonshot-v1-8k | Moonshot AI | $0.20 | $2.00 | 8,192 |
| moonshot-v1-8k-0430 | Moonshot AI | $0.20 | $2.00 | 8,192 |
| moonshot-v1-8k-vision-preview | Moonshot AI | $0.20 | $2.00 | 8,192 |
| kimi-k2-0711-preview | Moonshot AI | $0.60 | $2.50 | 131,072 |
| kimi-k2-0905-preview | Moonshot AI | $0.60 | $2.50 | 262,144 |
| kimi-k2-thinking | Moonshot AI | $0.60 | $2.50 | 262,144 |
| kimi-k2.5 | Moonshot AI | $0.60 | $3.00 | 262,144 |
| kimi-thinking-preview | Moonshot AI | $0.60 | $2.50 | 131,072 |
| kimi-k2.6 | Moonshot AI | $0.95 | $4.00 | 262,144 |
| kimi-latest-32k | Moonshot AI | $1.00 | $3.00 | 32,768 |
| moonshot-v1-32k | Moonshot AI | $1.00 | $3.00 | 32,768 |
| moonshot-v1-32k-0430 | Moonshot AI | $1.00 | $3.00 | 32,768 |
| moonshot-v1-32k-vision-preview | Moonshot AI | $1.00 | $3.00 | 32,768 |
| kimi-k2-thinking-turbo | Moonshot AI | $1.15 | $8.00 | 262,144 |
| kimi-k2-turbo-preview | Moonshot AI | $1.15 | $8.00 | 262,144 |
| kimi-latest | Moonshot AI | $2.00 | $5.00 | 131,072 |
| kimi-latest-128k | Moonshot AI | $2.00 | $5.00 | 131,072 |
| moonshot-v1-128k | Moonshot AI | $2.00 | $5.00 | 131,072 |
| moonshot-v1-128k-0430 | Moonshot AI | $2.00 | $5.00 | 131,072 |
| moonshot-v1-128k-vision-preview | Moonshot AI | $2.00 | $5.00 | 131,072 |
| moonshot-v1-auto | Moonshot AI | $2.00 | $5.00 | 131,072 |
| Qwen2.5-Coder-7B | Nebius | $0.01 | $0.03 | 32,768 |
| Qwen2.5-32B-Instruct | Nebius | $0.06 | $0.20 | 128,000 |
| Llama-3.3-Nemotron-Super-49B-v1 | Nebius | $0.10 | $0.40 | 131,072 |
| Llama-3.1-Nemotron-Ultra-253B-v1 | Nebius | $0.60 | $1.80 | 128,000 |
| paddleocr-vl | Novita | $0.02 | $0.02 | 16,384 |
| deepseek-ocr | Novita | $0.03 | $0.03 | 8,192 |
| qwen3-4b-fp8 | Novita | $0.03 | $0.03 | 128,000 |
| autoglm-phone-9b-multilingual | Novita | $0.035 | $0.138 | 65,536 |
| qwen3-8b-fp8 | Novita | $0.035 | $0.138 | 128,000 |
| llama-3-8b-instruct | Novita | $0.04 | $0.04 | 8,192 |
| mistral-nemo | Novita | $0.04 | $0.17 | 60,288 |
| l3-8b-lunaris | Novita | $0.05 | $0.05 | 8,192 |
| L3-8B-Stheno-v3.2 | Novita | $0.05 | $0.05 | 8,192 |
| deepseek-r1-0528-qwen3-8b | Novita | $0.06 | $0.09 | 128,000 |
| baichuan-m2-32b | Novita | $0.07 | $0.07 | 131,072 |
| ernie-4.5-21B-a3b | Novita | $0.07 | $0.28 | 120,000 |
| ernie-4.5-21B-a3b-thinking | Novita | $0.07 | $0.28 | 131,072 |
| qwen3-30b-a3b-fp8 | Novita | $0.09 | $0.45 | 40,960 |
| mimo-v2-flash | Novita | $0.10 | $0.30 | 262,144 |
| qwen3-32b-fp8 | Novita | $0.10 | $0.45 | 40,960 |
| glm-4.5-air | Novita | $0.13 | $0.85 | 131,072 |
| ernie-4.5-vl-28b-a3b | Novita | $0.14 | $0.56 | 30,000 |
| hermes-2-pro-llama-3-8b | Novita | $0.14 | $0.14 | 8,192 |
| qwen3-235b-a22b-fp8 | Novita | $0.20 | $0.80 | 40,960 |
| r1v4-lite | Novita | $0.20 | $0.60 | 262,144 |
| qwen-mt-plus | Novita | $0.25 | $0.75 | 16,384 |
| qwen3-omni-30b-a3b-instruct | Novita | $0.25 | $0.97 | 65,536 |
| qwen3-omni-30b-a3b-thinking | Novita | $0.25 | $0.97 | 65,536 |
| deepseek-v3.2-exp | Novita | $0.27 | $0.41 | 163,840 |
| ernie-4.5-300b-a47b-paddle | Novita | $0.28 | $1.10 | 123,000 |
| glm-4.6v | Novita | $0.30 | $0.90 | 131,072 |
| kat-coder-pro | Novita | $0.30 | $1.20 | 256,000 |
| minimax-m2.1 | Novita | $0.30 | $1.20 | 204,800 |
| ernie-4.5-vl-28b-a3b-thinking | Novita | $0.39 | $0.39 | 131,072 |
| deepseek-v3-turbo | Novita | $0.40 | $1.30 | 64,000 |
| ernie-4.5-vl-424b-a47b | Novita | $0.42 | $1.25 | 123,000 |
| llama-3-70b-instruct | Novita | $0.51 | $0.74 | 8,192 |
| glm-4.5v | Novita | $0.60 | $1.80 | 65,536 |
| kimi-k2-0905 | Novita | $0.60 | $2.50 | 262,144 |
| deepseek-prover-v2-671b | Novita | $0.70 | $2.50 | 160,000 |
| qwen2.5-vl-72b-instruct | Novita | $0.80 | $0.80 | 32,768 |
| l3-70b-euryale-v2.1 | Novita | $1.48 | $1.48 | 8,192 |
| gpt-5-nano-2025-08-07 | OpenAI | $0.05 | $0.40 | 272,000 |
| gpt-4.1-nano-2025-04-14 | OpenAI | $0.10 | $0.40 | 1,047,576 |
| gpt-4o-mini-2024-07-18 | OpenAI | $0.15 | $0.60 | 128,000 |
| gpt-4o-mini-audio-preview | OpenAI | $0.15 | $0.60 | 128,000 |
| gpt-4o-mini-audio-preview-2024-12-17 | OpenAI | $0.15 | $0.60 | 128,000 |
| gpt-4o-mini-search-preview | OpenAI | $0.15 | $0.60 | 128,000 |
| gpt-4o-mini-search-preview-2025-03-11 | OpenAI | $0.15 | $0.60 | 128,000 |
| gpt-5.4-nano-2026-03-17 | OpenAI | $0.20 | $1.25 | 1,050,000 |
| gpt-5-mini-2025-08-07 | OpenAI | $0.25 | $2.00 | 272,000 |
| gpt-4.1-mini-2025-04-14 | OpenAI | $0.40 | $1.60 | 1,047,576 |
| gpt-3.5-turbo | OpenAI | $0.50 | $1.50 | 16,385 |
| gpt-3.5-turbo-0125 | OpenAI | $0.50 | $1.50 | 16,385 |
| gpt-4o-mini-realtime-preview | OpenAI | $0.60 | $2.40 | 128,000 |
| gpt-4o-mini-realtime-preview-2024-12-17 | OpenAI | $0.60 | $2.40 | 128,000 |
| gpt-audio-mini | OpenAI | $0.60 | $2.40 | 128,000 |
| gpt-audio-mini-2025-10-06 | OpenAI | $0.60 | $2.40 | 128,000 |
| gpt-audio-mini-2025-12-15 | OpenAI | $0.60 | $2.40 | 128,000 |
| gpt-realtime-mini | OpenAI | $0.60 | $2.40 | 128,000 |
| gpt-realtime-mini-2025-10-06 | OpenAI | $0.60 | $2.40 | 128,000 |
| gpt-realtime-mini-2025-12-15 | OpenAI | $0.60 | $2.40 | 128,000 |
| gpt-5.4-mini-2026-03-17 | OpenAI | $0.75 | $4.50 | 1,050,000 |
| gpt-3.5-turbo-1106 | OpenAI | $1.00 | $2.00 | 16,385 |
| o3-mini | OpenAI | $1.10 | $4.40 | 200,000 |
| o3-mini-2025-01-31 | OpenAI | $1.10 | $4.40 | 200,000 |
| o4-mini-2025-04-16 | OpenAI | $1.10 | $4.40 | 200,000 |
| gpt-5-2025-08-07 | OpenAI | $1.25 | $10.00 | 272,000 |
| gpt-5-chat | OpenAI | $1.25 | $10.00 | 128,000 |
| gpt-5-chat-latest | OpenAI | $1.25 | $10.00 | 128,000 |
| gpt-5-search-api | OpenAI | $1.25 | $10.00 | 272,000 |
| gpt-5-search-api-2025-10-14 | OpenAI | $1.25 | $10.00 | 272,000 |
| gpt-5.1-2025-11-13 | OpenAI | $1.25 | $10.00 | 272,000 |
| gpt-5.1-chat-latest | OpenAI | $1.25 | $10.00 | 128,000 |
| gpt-5.2-2025-12-11 | OpenAI | $1.75 | $14.00 | 272,000 |
| gpt-5.2-chat-latest | OpenAI | $1.75 | $14.00 | 128,000 |
| gpt-5.3-chat-latest | OpenAI | $1.75 | $14.00 | 128,000 |
| gpt-4.1-2025-04-14 | OpenAI | $2.00 | $8.00 | 1,047,576 |
| o3-2025-04-16 | OpenAI | $2.00 | $8.00 | 200,000 |
| gpt-4o-2024-08-06 | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-4o-2024-11-20 | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-4o-audio-preview | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-4o-audio-preview-2024-12-17 | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-4o-audio-preview-2025-06-03 | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-4o-search-preview | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-4o-search-preview-2025-03-11 | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-5.4-2026-03-05 | OpenAI | $2.50 | $15.00 | 1,050,000 |
| gpt-audio | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-audio-1.5 | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-audio-2025-08-28 | OpenAI | $2.50 | $10.00 | 128,000 |
| gpt-3.5-turbo-16k | OpenAI | $3.00 | $4.00 | 16,385 |
| gpt-realtime | OpenAI | $4.00 | $16.00 | 32,000 |
| gpt-realtime-1.5 | OpenAI | $4.00 | $16.00 | 32,000 |
| gpt-realtime-2 | OpenAI | $4.00 | $16.00 | 32,000 |
| gpt-realtime-2025-08-28 | OpenAI | $4.00 | $16.00 | 32,000 |
| chatgpt-4o-latest | OpenAI | $5.00 | $15.00 | 128,000 |
| gpt-4o-2024-05-13 | OpenAI | $5.00 | $15.00 | 128,000 |
| gpt-4o-realtime-preview | OpenAI | $5.00 | $20.00 | 128,000 |
| gpt-4o-realtime-preview-2024-12-17 | OpenAI | $5.00 | $20.00 | 128,000 |
| gpt-4o-realtime-preview-2025-06-03 | OpenAI | $5.00 | $20.00 | 128,000 |
| gpt-5.5-2026-04-23 | OpenAI | $5.00 | $30.00 | 1,050,000 |
| gpt-4-0125-preview | OpenAI | $10.00 | $30.00 | 128,000 |
| gpt-4-1106-preview | OpenAI | $10.00 | $30.00 | 128,000 |
| gpt-4-turbo | OpenAI | $10.00 | $30.00 | 128,000 |
| gpt-4-turbo-2024-04-09 | OpenAI | $10.00 | $30.00 | 128,000 |
| gpt-4-turbo-preview | OpenAI | $10.00 | $30.00 | 128,000 |
| o1 | OpenAI | $15.00 | $60.00 | 200,000 |
| o1-2024-12-17 | OpenAI | $15.00 | $60.00 | 200,000 |
| gpt-4 | OpenAI | $30.00 | $60.00 | 8,192 |
| gpt-4-0314 | OpenAI | $30.00 | $60.00 | 8,192 |
| gpt-4-0613 | OpenAI | $30.00 | $60.00 | 8,192 |
| pplx-70b-online | Perplexity | $0.00 | $2.80 | 4,096 |
| pplx-7b-online | Perplexity | $0.00 | $0.28 | 4,096 |
| sonar-medium-online | Perplexity | $0.00 | $1.80 | 12,000 |
| sonar-small-online | Perplexity | $0.00 | $0.28 | 12,000 |
| mistral-7b-instruct | Perplexity | $0.07 | $0.28 | 4,096 |
| mixtral-8x7b-instruct | Perplexity | $0.07 | $0.28 | 4,096 |
| pplx-7b-chat | Perplexity | $0.07 | $0.28 | 8,192 |
| sonar-small-chat | Perplexity | $0.07 | $0.28 | 16,384 |
| llama-3.1-8b-instruct | Perplexity | $0.20 | $0.20 | 131,072 |
| codellama-34b-instruct | Perplexity | $0.35 | $1.40 | 16,384 |
| sonar-medium-chat | Perplexity | $0.60 | $1.80 | 16,384 |
| codellama-70b-instruct | Perplexity | $0.70 | $2.80 | 16,384 |
| llama-2-70b-chat | Perplexity | $0.70 | $2.80 | 4,096 |
| pplx-70b-chat | Perplexity | $0.70 | $2.80 | 4,096 |
| llama-3.1-70b-instruct | Perplexity | $1.00 | $1.00 | 131,072 |
| sonar | Perplexity | $1.00 | $1.00 | 128,000 |
| sonar-reasoning | Perplexity | $1.00 | $5.00 | 128,000 |
| sonar-deep-research | Perplexity | $2.00 | $8.00 | 128,000 |
| sonar-reasoning-pro | Perplexity | $2.00 | $8.00 | 128,000 |
| sonar-pro | Perplexity | $3.00 | $15.00 | 200,000 |
| llama-2-7b | Replicate | $0.05 | $0.25 | 4,096 |
| llama-2-7b-chat | Replicate | $0.05 | $0.25 | 4,096 |
| llama-3-8b | Replicate | $0.05 | $0.25 | 8,086 |
| mistral-7b-instruct-v0.2 | Replicate | $0.05 | $0.25 | 4,096 |
| mistral-7b-v0.1 | Replicate | $0.05 | $0.25 | 4,096 |
| llama-2-13b | Replicate | $0.10 | $0.50 | 4,096 |
| llama-2-13b-chat | Replicate | $0.10 | $0.50 | 4,096 |
| llama-2-70b | Replicate | $0.65 | $2.75 | 4,096 |
| llama-3-70b | Replicate | $0.65 | $2.75 | 8,192 |
| Meta-Llama-3.2-1B-Instruct | SambaNova | $0.04 | $0.08 | 16,384 |
| Meta-Llama-3.2-3B-Instruct | SambaNova | $0.08 | $0.16 | 4,096 |
| Meta-Llama-3.1-8B-Instruct | SambaNova | $0.10 | $0.20 | 16,384 |
| Meta-Llama-Guard-3-8B | SambaNova | $0.30 | $0.30 | 16,384 |
| gemma-4-31B-it | SambaNova | $0.38 | $1.15 | 131,072 |
| Qwen2-Audio-7B-Instruct | SambaNova | $0.50 | $100.00 | 4,096 |
| QwQ-32B | SambaNova | $0.50 | $1.00 | 16,384 |
| Meta-Llama-3.3-70B-Instruct | SambaNova | $0.60 | $1.20 | 131,072 |
| MiniMax-M2.7 | SambaNova | $0.60 | $2.40 | 196,608 |
| DeepSeek-R1-Distill-Llama-70B | SambaNova | $0.70 | $1.40 | 131,072 |
| DeepSeek-V3-0324 | SambaNova | $3.00 | $4.50 | 32,768 |
| DeepSeek-V3.1 | SambaNova | $3.00 | $4.50 | 131,072 |
| Meta-Llama-3.1-405B-Instruct | SambaNova | $5.00 | $10.00 | 16,384 |
| GLM-4.5-Air-FP8 | Together AI | $0.20 | $1.10 | 128,000 |
| Qwen3-235B-A22B-fp8-tput | Together AI | $0.20 | $0.60 | 40,000 |
| Qwen3-235B-A22B-Instruct-2507-tput | Together AI | $0.20 | $6.00 | 262,000 |
| together-ai-8.1b-21b | Together AI | $0.30 | $0.30 | 1,000 |
| GLM-4.7 | Together AI | $0.45 | $2.00 | 200,000 |
| DeepSeek-R1-0528-tput | Together AI | $0.55 | $2.19 | 128,000 |
| GLM-4.6 | Together AI | $0.60 | $2.20 | 200,000 |
| Qwen3.5-397B-A17B | Together AI | $0.60 | $3.60 | 262,144 |
| Qwen3-235B-A22B-Thinking-2507 | Together AI | $0.65 | $3.00 | 256,000 |
| Qwen3-Coder-480B-A35B-Instruct-FP8 | Together AI | $2.00 | $2.00 | 256,000 |
| grok-4-1-fast | xAI | $0.20 | $0.50 | 2,000,000 |
| grok-4-1-fast-non-reasoning | xAI | $0.20 | $0.50 | 2,000,000 |
| grok-4-1-fast-non-reasoning-latest | xAI | $0.20 | $0.50 | 2,000,000 |
| grok-4-1-fast-reasoning | xAI | $0.20 | $0.50 | 2,000,000 |
| grok-4-1-fast-reasoning-latest | xAI | $0.20 | $0.50 | 2,000,000 |
| grok-4-fast-non-reasoning | xAI | $0.20 | $0.50 | 2,000,000 |
| grok-4-fast-reasoning | xAI | $0.20 | $0.50 | 2,000,000 |
| grok-code-fast | xAI | $0.20 | $1.50 | 256,000 |
| grok-code-fast-1 | xAI | $0.20 | $1.50 | 256,000 |
| grok-code-fast-1-0825 | xAI | $0.20 | $1.50 | 256,000 |
| grok-3-mini | xAI | $0.30 | $0.50 | 131,072 |
| grok-3-mini-beta | xAI | $0.30 | $0.50 | 131,072 |
| grok-3-mini-latest | xAI | $0.30 | $0.50 | 131,072 |
| grok-3-mini-fast | xAI | $0.60 | $4.00 | 131,072 |
| grok-3-mini-fast-beta | xAI | $0.60 | $4.00 | 131,072 |
| grok-3-mini-fast-latest | xAI | $0.60 | $4.00 | 131,072 |
| grok-4.3-latest | xAI | $1.25 | $2.50 | 1,000,000 |
| grok-2 | xAI | $2.00 | $10.00 | 131,072 |
| grok-2-1212 | xAI | $2.00 | $10.00 | 131,072 |
| grok-2-latest | xAI | $2.00 | $10.00 | 131,072 |
| grok-2-vision | xAI | $2.00 | $10.00 | 32,768 |
| grok-2-vision-1212 | xAI | $2.00 | $10.00 | 32,768 |
| grok-2-vision-latest | xAI | $2.00 | $10.00 | 32,768 |
| grok-4.20-0309-reasoning | xAI | $2.00 | $6.00 | 2,000,000 |
| grok-4.20-beta-0309-non-reasoning | xAI | $2.00 | $6.00 | 2,000,000 |
| grok-4.20-beta-0309-reasoning | xAI | $2.00 | $6.00 | 2,000,000 |
| grok-4.20-multi-agent-beta-0309 | xAI | $2.00 | $6.00 | 2,000,000 |
| grok-3 | xAI | $3.00 | $15.00 | 131,072 |
| grok-3-beta | xAI | $3.00 | $15.00 | 131,072 |
| grok-3-latest | xAI | $3.00 | $15.00 | 131,072 |
| grok-4 | xAI | $3.00 | $15.00 | 256,000 |
| grok-4-0709 | xAI | $3.00 | $15.00 | 256,000 |
| grok-4-latest | xAI | $3.00 | $15.00 | 256,000 |
| grok-3-fast-beta | xAI | $5.00 | $25.00 | 131,072 |
| grok-3-fast-latest | xAI | $5.00 | $25.00 | 131,072 |
| grok-beta | xAI | $5.00 | $15.00 | 131,072 |
| grok-vision-beta | xAI | $5.00 | $15.00 | 8,192 |
Want to know what a specific prompt costs on each of these models? Paste it into the token counter and cost analyzer and open the Compare tab.
Free pricing data API
This entire table is available as a free JSON dataset at freetokencounter.com/api/pricing.json — current input and output rates, context windows, pricing tiers, and official source links for every model, regenerated whenever the catalog refreshes. CORS is enabled, so you can fetch it directly from scripts, dashboards, or CI. Free to use with attribution to freetokencounter.com. Price moves are logged on the pricing change tracker, with an RSS feed you can subscribe to.
FAQ
LLM pricing FAQ
How is LLM API pricing structured?
Providers bill separately for input tokens (the prompt and context you send) and output tokens (the model response), usually quoted per 1 million tokens. Total request cost is input tokens times the input rate plus output tokens times the output rate.
Which LLM is cheapest right now?
Among paid API models in this table, DeepSeek V4 Flash currently has the lowest combined rate at about $0.14 input plus $0.28 output per 1M tokens, based on pricing checked 2026-07-01. Open-weight models like Llama can be cheaper or more expensive depending on hosting.
Which LLM is most expensive?
GPT-5.5 Pro has the highest output rate in this table at $180.00 per 1M output tokens as of 2026-07-01. High-end reasoning models generally carry the largest premiums on output tokens.
How often is this pricing table updated?
Prices are pulled from official provider pricing pages through an automated catalog refresh. The current data was checked on 2026-07-01. Treat all figures as estimates and confirm on the linked provider page before budgeting.