LLM models and API pricing
Compare live API prices and explore benchmarked models that do not yet have public pricing. Priced rows include the exact model ID to copy and the price delta against the cheapest provider.
Best value right now
GLM 5.3 Flash runs $0.07 / 1M input on OpenRouter, Intelligence Index 57. The cheapest model in the top 10% for quality.
z-ai/glm-5.3-flashModels tracked
1,656
1,473 priced + 183 benchmark-only
Model makers
61
labs and providers
Serving providers
81
API endpoints
Best value
$0.07
top 10% for quality
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Price status
Maker
Capability
| gpt-oss-120b |  OpenAI | 131K | $0.03 from | $0.17 from | 24.1 | 30.4 | 78% | 19 providers |
| gpt-oss-20b | OpenAI | 131K | $0.01 from | $0.07 from | 15.2 | 20.7 | 69% | 13 providers |
| Llama 3.3 70B Instruct |  Meta | 131K | $0.12 from | $0.20 from | 9.3 | 11.9 | 50% | 13 providers |
| R1 |  DeepSeek | 164K | $0.40 from | $0.40 from | 20.4 | n/a | 81% | 13 providers |
| DeepSeek V4 Flash 0423 | DeepSeek | 1M | $0.09 from | $0.17 from | 51.8 | 69.1 | 91% | 12 providers |
| DeepSeek V3 0324 | DeepSeek | 164K | $0.20 from | $0.40 from | 15.2 | 21.2 | 65% | 11 providers |
| Llama 4 Scout 17B 16e Instruct | Meta | 10.5M | $0.05 from | $0.10 from | n/a | n/a | n/a | 10 providers |
| R1 Distill Llama 70B | DeepSeek | 131K | $0.20 from | $0.38 from | 9.8 | n/a | 40% | 10 providers |
| DeepSeek V4 Pro 0423 | DeepSeek | 1M | $0.43 from | $0.87 from | 53.2 | 68.8 | 93% | 10 providers |
| GLM 5.2 |  Zhipu | 1M | $0.61 from | $1.98 from | 52.6 | 68.8 | 89% | 10 providers |
| DeepSeek | DeepSeek | 164K | $0.20 from | $0.20 from | n/a | n/a | n/a | 9 providers |
| Gemma 3 27B |  Google | 131K | $0.00 from | $0.00 from | 7.4 | 10.1 | 43% | 8 providers |
| Llama 3.1 8B Instruct | Meta | 200K | $0.02 from | $0.03 from | 7.4 | 5.4 | 26% | 8 providers |
| Qwen3 32B |  Alibaba | 131K | $0.08 from | $0.23 from | 8.5 | n/a | 54% | 8 providers |
| Gemma 4 31B | Google | 262K | $0.09 from | $0.34 from | n/a | n/a | n/a | 8 providers |
| Gemini 2.5 Flash | Google | 1M | $0.15 from | $0.60 from | 14.2 | n/a | 68% | 8 providers |
| R1 0528 | DeepSeek | 164K | $0.20 from | $0.25 from | n/a | n/a | n/a | 8 providers |
| MiniMax M3 |  MiniMax | 1M | $0.23 from | $0.96 from | 45.4 | 58.6 | 93% | 8 providers |
| DeepSeek V3 1 | DeepSeek | 164K | $0.25 from | $0.95 from | 21.4 | n/a | 74% | 8 providers |
| Kimi K2.5 |  Moonshot | 262K | $0.45 from | $2.25 from | 36.0 | 46.8 | 88% | 8 providers |
| Kimi K2.6 | Moonshot | 262K | $0.65 from | $3.40 from | 45.1 | 61.8 | 91% | 8 providers |
| Claude Haiku 4.5 |  Anthropic | 200K | $1.00 from | $5.00 from | n/a | n/a | n/a | 8 providers |
| Claude Sonnet 4.5 | Anthropic | 1M | $3.00 from | $15.00 from | n/a | n/a | n/a | 8 providers |
| Claude Sonnet 4.6 | Anthropic | 1M | $3.00 from | $15.00 from | 36.8 | n/a | 80% | 8 providers |
| DeepSeek V4 Flash 0731 | DeepSeek | 1M | $0.04 from | $0.09 from | n/a | n/a | n/a | 7 providers |
| Qwen3.6 35B A3B | Alibaba | 262K | $0.10 from | $0.45 from | 32.1 | 41.9 | 84% | 7 providers |
| QwQ 32B | Alibaba | 131K | $0.15 from | $0.20 from | 13.4 | n/a | 59% | 7 providers |
| DeepSeek V3.2 | DeepSeek | 164K | $0.26 from | $0.38 from | 25.1 | n/a | 75% | 7 providers |
| GLM 4.6 | Zhipu | 205K | $0.43 from | $1.75 from | 23.4 | n/a | 63% | 7 providers |
| Kimi K2 Thinking | Moonshot | 262K | $0.60 from | $1.20 from | 33.5 | n/a | 84% | 7 providers |
| Kimi K2.7 Code | Moonshot | 262K | $0.66 from | $3.40 from | 43.0 | 60.8 | 90% | 7 providers |
| Gemini 2.5 Pro | Google | 1M | $1.25 from | $10.00 from | 25.9 | 33.3 | 84% | 7 providers |
| Claude Sonnet 5 | Anthropic | 1M | $2.00 from | $10.00 from | 55.3 | 71.5 | 91% | 7 providers |
| Kimi K3 | Moonshot | 1M | $2.85 from | $14.25 from | 59.7 | 76.2 | 94% | 7 providers |
| Claude Opus 4.5 | Anthropic | 410K | $5.00 from | $25.00 from | 35.6 | n/a | 81% | 7 providers |
| Claude Opus 4.6 | Anthropic | 1M | $5.00 from | $25.00 from | 38.8 | n/a | 84% | 7 providers |
| Claude Opus 4.7 | Anthropic | 1M | $5.00 from | $25.00 from | 55.0 | 73.6 | 91% | 7 providers |
| Claude Opus 4.8 | Anthropic | 1M | $5.00 from | $25.00 from | 57.3 | 74.3 | 92% | 7 providers |
| Claude Opus 5 | Anthropic | 1M | $5.00 from | $25.00 from | 63.0 | 78.0 | 93% | 7 providers |
| Claude Fable 5 | Anthropic | 1M | $10.00 from | $50.00 from | 62.1 | 76.5 | 93% | 7 providers |
| Mixtral 8x7B Instruct V0 1 |  Mistral | 33K | $0.00 from | $0.00 from | n/a | n/a | n/a | 6 providers |
| Meta Llama 3.1 8B Instruct | Meta | 131K | $0.02 from | $0.05 from | n/a | n/a | n/a | 6 providers |
| Llama 3.2 3B Instruct | Meta | 131K | $0.02 from | $0.02 from | 3.9 | n/a | 25% | 6 providers |
| Llama 4 Maverick 17B 128e Instruct FP8 | Meta | 1M | $0.05 from | $0.10 from | n/a | n/a | n/a | 6 providers |
| Qwen3 Next 80B A3B Instruct | Alibaba | 262K | $0.09 from | $0.90 from | 13.8 | n/a | 74% | 6 providers |
| Qwen3 235B A22b Instruct 2507 | Alibaba | 262K | $0.09 from | $0.55 from | 18.4 | n/a | 75% | 6 providers |
| Qwen3 Next 80B A3B Thinking | Alibaba | 262K | $0.14 from | $0.90 from | n/a | n/a | n/a | 6 providers |
| GPT-4o-mini | OpenAI | 131K | $0.15 from | $0.60 from | 6.7 | 11.4 | 43% | 6 providers |
| Qwen3.6 27B | Alibaba | 262K | $0.15 from | $0.50 from | 37.7 | 53.7 | 84% | 6 providers |
| MiniMax M2.5 | MiniMax | 1M | $0.27 from | $1.08 from | 34.5 | n/a | 85% | 6 providers |
Reasoning modelgpt-oss-120b
OpenAI · 131K CTX
Input $/1M
$0.03from
Output $/1M
$0.17from
Intelligence24.119 providers
Reasoning modelgpt-oss-20b
OpenAI · 131K CTX
Input $/1M
$0.01from
Output $/1M
$0.07from
Intelligence15.213 providers
Llama 3.3 70B Instruct
Meta · 131K CTX
Input $/1M
$0.12from
Output $/1M
$0.20from
Intelligence9.313 providers
Reasoning modelR1
DeepSeek · 164K CTX
Input $/1M
$0.40from
Output $/1M
$0.40from
Intelligence20.413 providers
Reasoning modelDeepSeek V4 Flash 0423
DeepSeek · 1M CTX
Input $/1M
$0.09from
Output $/1M
$0.17from
Intelligence51.812 providers
Reasoning modelDeepSeek V3 0324
DeepSeek · 164K CTX
Input $/1M
$0.20from
Output $/1M
$0.40from
Intelligence15.211 providers
Llama 4 Scout 17B 16e Instruct
Meta · 10.5M CTX
Input $/1M
$0.05from
Output $/1M
$0.10from
Intelligencen/a10 providers
Reasoning modelR1 Distill Llama 70B
DeepSeek · 131K CTX
Input $/1M
$0.20from
Output $/1M
$0.38from
Intelligence9.810 providers
Reasoning modelDeepSeek V4 Pro 0423
DeepSeek · 1M CTX
Input $/1M
$0.43from
Output $/1M
$0.87from
Intelligence53.210 providers
Reasoning modelGLM 5.2
Zhipu · 1M CTX
Input $/1M
$0.61from
Output $/1M
$1.98from
Intelligence52.610 providers
Llama 3.1 8B Instruct
Meta · 200K CTX
Input $/1M
$0.02from
Output $/1M
$0.03from
Intelligence7.48 providers
Reasoning modelQwen3 32B
Alibaba · 131K CTX
Input $/1M
$0.08from
Output $/1M
$0.23from
Intelligence8.58 providers
Reasoning modelGemma 4 31B
Google · 262K CTX
Input $/1M
$0.09from
Output $/1M
$0.34from
Intelligencen/a8 providers
Reasoning modelGemini 2.5 Flash
Google · 1M CTX
Input $/1M
$0.15from
Output $/1M
$0.60from
Intelligence14.28 providers
Reasoning modelR1 0528
DeepSeek · 164K CTX
Input $/1M
$0.20from
Output $/1M
$0.25from
Intelligencen/a8 providers
Reasoning modelMiniMax M3
MiniMax · 1M CTX
Input $/1M
$0.23from
Output $/1M
$0.96from
Intelligence45.48 providers
Reasoning modelDeepSeek V3 1
DeepSeek · 164K CTX
Input $/1M
$0.25from
Output $/1M
$0.95from
Intelligence21.48 providers
Reasoning modelKimi K2.5
Moonshot · 262K CTX
Input $/1M
$0.45from
Output $/1M
$2.25from
Intelligence36.08 providers
Reasoning modelKimi K2.6
Moonshot · 262K CTX
Input $/1M
$0.65from
Output $/1M
$3.40from
Intelligence45.18 providers
Reasoning modelClaude Haiku 4.5
Anthropic · 200K CTX
Input $/1M
$1.00from
Output $/1M
$5.00from
Intelligencen/a8 providers
Reasoning modelClaude Sonnet 4.5
Anthropic · 1M CTX
Input $/1M
$3.00from
Output $/1M
$15.00from
Intelligencen/a8 providers
Reasoning modelClaude Sonnet 4.6
Anthropic · 1M CTX
Input $/1M
$3.00from
Output $/1M
$15.00from
Intelligence36.88 providers
Reasoning modelDeepSeek V4 Flash 0731
DeepSeek · 1M CTX
Input $/1M
$0.04from
Output $/1M
$0.09from
Intelligencen/a7 providers
Reasoning modelQwen3.6 35B A3B
Alibaba · 262K CTX
Input $/1M
$0.10from
Output $/1M
$0.45from
Intelligence32.17 providers
Reasoning modelQwQ 32B
Alibaba · 131K CTX
Input $/1M
$0.15from
Output $/1M
$0.20from
Intelligence13.47 providers
Reasoning modelDeepSeek V3.2
DeepSeek · 164K CTX
Input $/1M
$0.26from
Output $/1M
$0.38from
Intelligence25.17 providers
Reasoning modelGLM 4.6
Zhipu · 205K CTX
Input $/1M
$0.43from
Output $/1M
$1.75from
Intelligence23.47 providers
Reasoning modelKimi K2 Thinking
Moonshot · 262K CTX
Input $/1M
$0.60from
Output $/1M
$1.20from
Intelligence33.57 providers
Reasoning modelKimi K2.7 Code
Moonshot · 262K CTX
Input $/1M
$0.66from
Output $/1M
$3.40from
Intelligence43.07 providers
Reasoning modelGemini 2.5 Pro
Google · 1M CTX
Input $/1M
$1.25from
Output $/1M
$10.00from
Intelligence25.97 providers
Reasoning modelClaude Sonnet 5
Anthropic · 1M CTX
Input $/1M
$2.00from
Output $/1M
$10.00from
Intelligence55.37 providers
Reasoning modelKimi K3
Moonshot · 1M CTX
Input $/1M
$2.85from
Output $/1M
$14.25from
Intelligence59.77 providers
Reasoning modelClaude Opus 4.5
Anthropic · 410K CTX
Input $/1M
$5.00from
Output $/1M
$25.00from
Intelligence35.67 providers
Reasoning modelClaude Opus 4.6
Anthropic · 1M CTX
Input $/1M
$5.00from
Output $/1M
$25.00from
Intelligence38.87 providers
Reasoning modelClaude Opus 4.7
Anthropic · 1M CTX
Input $/1M
$5.00from
Output $/1M
$25.00from
Intelligence55.07 providers
Reasoning modelClaude Opus 4.8
Anthropic · 1M CTX
Input $/1M
$5.00from
Output $/1M
$25.00from
Intelligence57.37 providers
Reasoning modelClaude Opus 5
Anthropic · 1M CTX
Input $/1M
$5.00from
Output $/1M
$25.00from
Intelligence63.07 providers
Reasoning modelClaude Fable 5
Anthropic · 1M CTX
Input $/1M
$10.00from
Output $/1M
$50.00from
Intelligence62.17 providers
Mixtral 8x7B Instruct V0 1
Mistral · 33K CTX
Input $/1M
$0.00from
Output $/1M
$0.00from
Intelligencen/a6 providers
Meta Llama 3.1 8B Instruct
Meta · 131K CTX
Input $/1M
$0.02from
Output $/1M
$0.05from
Intelligencen/a6 providers
Llama 3.2 3B Instruct
Meta · 131K CTX
Input $/1M
$0.02from
Output $/1M
$0.02from
Intelligence3.96 providers
Llama 4 Maverick 17B 128e Instruct FP8
Meta · 1M CTX
Input $/1M
$0.05from
Output $/1M
$0.10from
Intelligencen/a6 providers
Reasoning modelQwen3 Next 80B A3B Instruct
Alibaba · 262K CTX
Input $/1M
$0.09from
Output $/1M
$0.90from
Intelligence13.86 providers
Qwen3 235B A22b Instruct 2507
Alibaba · 262K CTX
Input $/1M
$0.09from
Output $/1M
$0.55from
Intelligence18.46 providers
Reasoning modelQwen3 Next 80B A3B Thinking
Alibaba · 262K CTX
Input $/1M
$0.14from
Output $/1M
$0.90from
Intelligencen/a6 providers
Reasoning modelQwen3.6 27B
Alibaba · 262K CTX
Input $/1M
$0.15from
Output $/1M
$0.50from
Intelligence37.76 providers
Reasoning modelMiniMax M2.5
MiniMax · 1M CTX
Input $/1M
$0.27from
Output $/1M
$1.08from
Intelligence34.56 providers
1–50 of 1,656 models
Page 1 of 34
Pricing verified against LiteLLM + OpenRouter + provider pages · benchmarks sourced from Artificial Analysis, Hugging Face and ARC Prize · refreshed daily
Browse by
narrow the fieldEvery weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI