Tools / LLM Pricing Tracker
Live LLM Pricing Tracker
USD per million tokens for 330 models across every major provider — checked daily by an automated pipeline, with every price move logged below. Prices as of 2026-08-03.
Estimating a monthly bill instead? Use the LLM API Cost Calculator.
Recent price changes
2026-08-03
▼ Meta: Llama 3.3 70B Instruct input: $0.13 → $0.10/Mtok (-23%)
▼ Meta: Llama 3.3 70B Instruct output: $0.40 → $0.32/Mtok (-20%)
▲ Qwen: Qwen3 235B A22B Instruct 2507 input: $0.09 → $0.15/Mtok (+66%)
▲ Qwen: Qwen3 235B A22B Instruct 2507 output: $0.55 → $0.60/Mtok (+9%)
▼ Qwen: Qwen3 Coder 30B A3B Instruct output: $0.28 → $0.27/Mtok (-4%)
▲ Qwen: Qwen3 VL 235B A22B Thinking input: $0.40 → $0.98/Mtok (+145%)
▼ Qwen: Qwen3 VL 235B A22B Thinking output: $4.00 → $3.95/Mtok (-1%)
▼ Qwen: Qwen3.6 27B input: $0.30 → $0.29/Mtok (-4%)
▲ Qwen: Qwen3.6 27B output: $2.00 → $2.40/Mtok (+20%)
▲ Z.ai: GLM 5.2 input: $0.28 → $0.63/Mtok (+121%)
▲ Z.ai: GLM 5.2 output: $0.89 → $1.98/Mtok (+121%)
New: Qwen: Qwen3.8 Max ($2.00/$6.00 per Mtok)
2026-08-02
▼ Z.ai: GLM 5.2 input: $0.42 → $0.28/Mtok (-32%)
▼ Z.ai: GLM 5.2 output: $1.32 → $0.89/Mtok (-32%)
2026-08-01
▼ DeepSeek: DeepSeek V4 Flash 0731 input: $0.14 → $0.09/Mtok (-36%)
▼ DeepSeek: DeepSeek V4 Flash 0731 output: $0.28 → $0.18/Mtok (-36%)
▲ MoonshotAI: Kimi K2.6 input: $0.59 → $0.60/Mtok (+2%)
▲ MoonshotAI: Kimi K2.6 output: $2.48 → $3.41/Mtok (+38%)
▼ OpenAI: gpt-oss-20b output: $0.14 → $0.13/Mtok (-7%)
▲ Qwen: Qwen2.5 VL 72B Instruct input: $0.25 → $0.80/Mtok (+220%)
▲ Qwen: Qwen2.5 VL 72B Instruct output: $0.75 → $1.00/Mtok (+33%)
▲ Qwen: Qwen3 Coder 30B A3B Instruct output: $0.27 → $0.28/Mtok (+4%)
▼ Z.ai: GLM 5.2 input: $1.12 → $0.42/Mtok (-63%)
▼ Z.ai: GLM 5.2 output: $3.52 → $1.32/Mtok (-62%)
New: DeepSeek V4 Flash Latest ($0.09/$0.18 per Mtok)
2026-07-31
▼ Mistral: Mistral Small 3.2 24B input: $0.10 → $0.07/Mtok (-25%)
▼ Mistral: Mistral Small 3.2 24B output: $0.30 → $0.20/Mtok (-33%)
▼ MoonshotAI: Kimi K2.6 input: $0.95 → $0.59/Mtok (-38%)
▼ MoonshotAI: Kimi K2.6 output: $4.00 → $2.48/Mtok (-38%)
▲ OpenAI: gpt-oss-20b output: $0.13 → $0.14/Mtok (+8%)
▼ Qwen: Qwen2.5 VL 72B Instruct input: $0.80 → $0.25/Mtok (-69%)
▼ Qwen: Qwen2.5 VL 72B Instruct output: $1.00 → $0.75/Mtok (-25%)
▼ Qwen: Qwen3 235B A22B Thinking 2507 input: $0.30 → $0.23/Mtok (-23%)
▼ Qwen: Qwen3 235B A22B Thinking 2507 output: $3.00 → $2.30/Mtok (-23%)
▼ Qwen: Qwen3 VL 30B A3B Instruct input: $0.15 → $0.13/Mtok (-13%)
▼ Qwen: Qwen3 VL 30B A3B Instruct output: $0.60 → $0.52/Mtok (-13%)
▲ Z.ai: GLM 5.2 input: $0.97 → $1.12/Mtok (+16%)
New: DeepSeek: DeepSeek V4 Flash 0731 ($0.14/$0.28 per Mtok) · Thinking Machines: Inkling Small ($0.50/$1.20 per Mtok)
2026-07-30
▲ DeepSeek: DeepSeek V3 input: $0.20 → $0.26/Mtok (+29%)
▲ DeepSeek: DeepSeek V3 output: $0.80 → $1.03/Mtok (+29%)
▼ Google: Gemma 4 31B input: $0.14 → $0.10/Mtok (-29%)
▼ Google: Gemma 4 31B output: $0.40 → $0.34/Mtok (-15%)
▲ MoonshotAI: Kimi K2.6 input: $0.65 → $0.95/Mtok (+47%)
▲ MoonshotAI: Kimi K2.6 output: $2.72 → $4.00/Mtok (+47%)
▲ NVIDIA: Nemotron 3 Ultra input: $0.50 → $0.60/Mtok (+20%)
▲ NVIDIA: Nemotron 3 Ultra output: $2.20 → $3.60/Mtok (+64%)
▼ OpenAI: GPT-5.6 Luna input: $0.50 → $0.10/Mtok (-80%)
▼ OpenAI: GPT-5.6 Luna output: $3.00 → $0.60/Mtok (-80%)
▼ OpenAI: GPT-5.6 Luna Pro input: $0.50 → $0.10/Mtok (-80%)
▼ OpenAI: GPT-5.6 Luna Pro output: $3.00 → $0.60/Mtok (-80%)
2026-07-29
▼ Google: Gemma 4 26B A4B input: $0.14 → $0.07/Mtok (-50%)
▼ Google: Gemma 4 26B A4B output: $0.45 → $0.34/Mtok (-24%)
▲ Meta: Llama 3.3 70B Instruct input: $0.10 → $0.13/Mtok (+30%)
▲ Meta: Llama 3.3 70B Instruct output: $0.32 → $0.40/Mtok (+25%)
▼ OpenAI: gpt-oss-20b output: $0.14 → $0.13/Mtok (-7%)
▼ Qwen: Qwen3 Coder Next input: $0.18 → $0.12/Mtok (-33%)
▼ Qwen: Qwen3 Coder Next output: $0.90 → $0.80/Mtok (-11%)
▼ Qwen: Qwen3 VL 30B A3B Instruct input: $0.15 → $0.13/Mtok (-13%)
▼ Qwen: Qwen3 VL 30B A3B Instruct output: $0.60 → $0.52/Mtok (-13%)
▲ Qwen: Qwen3.6 35B A3B input: $0.10 → $0.14/Mtok (+40%)
▲ Qwen: Qwen3.6 35B A3B output: $0.95 → $1.00/Mtok (+5%)
▼ Qwen: Qwen3.6 Max Preview input: $1.04 → $1.03/Mtok (-1%)
2026-07-28
▲ Google: Gemma 4 26B A4B output: $0.42 → $0.45/Mtok (+7%)
▼ Meta: Llama 3.3 70B Instruct input: $0.13 → $0.10/Mtok (-23%)
▼ Meta: Llama 3.3 70B Instruct output: $0.40 → $0.32/Mtok (-20%)
▲ Qwen: Qwen Plus 0728 (thinking) input: $0.26 → $0.40/Mtok (+54%)
▲ Qwen: Qwen Plus 0728 (thinking) output: $0.78 → $1.20/Mtok (+54%)
▲ Qwen: Qwen3 30B A3B Thinking 2507 input: $0.13 → $0.20/Mtok (+54%)
▲ Qwen: Qwen3 30B A3B Thinking 2507 output: $1.56 → $2.40/Mtok (+54%)
▲ Qwen: Qwen3 Coder Next input: $0.11 → $0.18/Mtok (+64%)
▲ Qwen: Qwen3 Coder Next output: $0.80 → $0.90/Mtok (+12%)
▲ Qwen: Qwen3 Next 80B A3B Thinking input: $0.10 → $0.15/Mtok (+54%)
▲ Qwen: Qwen3 Next 80B A3B Thinking output: $0.78 → $1.20/Mtok (+54%)
▲ Qwen: Qwen3 VL 235B A22B Thinking input: $0.26 → $0.40/Mtok (+54%)
New: Anthropic: Claude Fable 5 (batch) ($5.00/$25.00 per Mtok) · Anthropic: Claude Haiku 4.5 (batch) ($0.50/$2.50 per Mtok) · Anthropic: Claude Opus 4.1 (batch) ($7.50/$37.50 per Mtok) · Anthropic: Claude Opus 4.5 (batch) ($2.50/$12.50 per Mtok) · Anthropic: Claude Opus 4.6 (batch) ($2.50/$12.50 per Mtok) · Anthropic: Claude Opus 4.7 (batch) ($2.50/$12.50 per Mtok) · Anthropic: Claude Opus 4.8 (batch) ($2.50/$12.50 per Mtok) · Anthropic: Claude Sonnet 4.5 (batch) ($1.50/$7.50 per Mtok)
2026-07-27
▲ Google: Gemma 4 26B A4B input: $0.12 → $0.14/Mtok (+17%)
▲ Google: Gemma 4 26B A4B output: $0.34 → $0.42/Mtok (+24%)
▼ NVIDIA: Nemotron 3 Ultra input: $0.60 → $0.50/Mtok (-17%)
▼ NVIDIA: Nemotron 3 Ultra output: $3.60 → $2.20/Mtok (-39%)
▼ OpenAI: GPT-5.6 Luna input: $1.00 → $0.50/Mtok (-50%)
▼ OpenAI: GPT-5.6 Luna output: $6.00 → $3.00/Mtok (-50%)
▼ OpenAI: GPT-5.6 Luna Pro input: $1.00 → $0.50/Mtok (-50%)
▼ OpenAI: GPT-5.6 Luna Pro output: $6.00 → $3.00/Mtok (-50%)
▼ OpenAI: GPT-5.6 Terra input: $2.50 → $1.25/Mtok (-50%)
▼ OpenAI: GPT-5.6 Terra output: $15.00 → $7.50/Mtok (-50%)
▼ OpenAI: GPT-5.6 Terra Pro input: $2.50 → $1.25/Mtok (-50%)
▼ OpenAI: GPT-5.6 Terra Pro output: $15.00 → $7.50/Mtok (-50%)
2026-07-26
▲ DeepSeek: DeepSeek V4 Flash input: $0.10 → $0.14/Mtok (+43%)
▲ DeepSeek: DeepSeek V4 Flash output: $0.20 → $0.28/Mtok (+43%)
▼ MoonshotAI: Kimi K2.7 Code input: $0.78 → $0.73/Mtok (-6%)
▲ OpenAI: gpt-oss-20b output: $0.13 → $0.14/Mtok (+8%)
▼ Qwen: Qwen3 30B A3B input: $0.13 → $0.12/Mtok (-8%)
▼ Qwen: Qwen3 30B A3B output: $0.52 → $0.50/Mtok (-4%)
▲ Qwen: Qwen3.6 27B input: $0.29 → $0.30/Mtok (+4%)
▼ Qwen: Qwen3.6 27B output: $2.40 → $2.00/Mtok (-17%)
▼ Z.ai: GLM 5.2 input: $0.70 → $0.67/Mtok (-4%)
▼ Z.ai: GLM 5.2 output: $2.20 → $2.10/Mtok (-4%)
2026-07-25
▼ Arcee AI: Trinity Large Thinking input: $0.25 → $0.22/Mtok (-12%)
▲ Arcee AI: Trinity Large Thinking output: $0.80 → $0.85/Mtok (+6%)
▼ MoonshotAI: Kimi K2.6 input: $0.68 → $0.65/Mtok (-6%)
▼ MoonshotAI: Kimi K2.6 output: $3.42 → $2.72/Mtok (-20%)
▼ Qwen: Qwen3 30B A3B Instruct 2507 input: $0.10 → $0.05/Mtok (-52%)
▼ Qwen: Qwen3 30B A3B Instruct 2507 output: $0.30 → $0.19/Mtok (-36%)
▼ Z.ai: GLM 5.2 input: $0.83 → $0.70/Mtok (-15%)
▼ Z.ai: GLM 5.2 output: $2.60 → $2.20/Mtok (-15%)
2026-07-24
▲ Google: Gemma 4 31B input: $0.12 → $0.14/Mtok (+17%)
▲ Google: Gemma 4 31B output: $0.35 → $0.40/Mtok (+14%)
▼ MoonshotAI: Kimi K2.7 Code input: $0.82 → $0.78/Mtok (-5%)
▼ MoonshotAI: Kimi K2.7 Code output: $3.75 → $3.50/Mtok (-7%)
▼ NVIDIA: Nemotron 3 Super output: $0.45 → $0.40/Mtok (-11%)
▲ NVIDIA: Nemotron 3 Ultra input: $0.50 → $0.60/Mtok (+20%)
▲ NVIDIA: Nemotron 3 Ultra output: $2.20 → $3.60/Mtok (+64%)
▼ Qwen: Qwen3 Next 80B A3B Instruct input: $0.15 → $0.10/Mtok (-33%)
▼ Qwen: Qwen3 Next 80B A3B Instruct output: $1.20 → $1.10/Mtok (-8%)
▼ Qwen: Qwen3.6 27B input: $0.60 → $0.29/Mtok (-52%)
▼ Qwen: Qwen3.6 27B output: $3.60 → $2.40/Mtok (-33%)
▼ Tencent: Hy3 output: $0.58 → $0.53/Mtok (-9%)
New: Claude Opus 5 ($5.00/$25.00 per Mtok) · Claude Opus 5 (Fast) ($10.00/$50.00 per Mtok)
2026-07-23
▼ Google: Gemma 3 27B input: $0.10 → $0.08/Mtok (-20%)
▲ Google: Gemma 3 27B output: $0.30 → $0.45/Mtok (+50%)
▲ Google: Gemma 4 26B A4B input: $0.07 → $0.12/Mtok (+71%)
▼ MiniMax: MiniMax M2 input: $0.30 → $0.26/Mtok (-15%)
▼ MiniMax: MiniMax M2 output: $1.20 → $1.02/Mtok (-15%)
▼ NVIDIA: Nemotron 3 Ultra input: $0.60 → $0.50/Mtok (-17%)
▼ NVIDIA: Nemotron 3 Ultra output: $3.60 → $2.20/Mtok (-39%)
▲ Qwen: Qwen3 Next 80B A3B Instruct input: $0.10 → $0.15/Mtok (+50%)
▲ Qwen: Qwen3 Next 80B A3B Instruct output: $1.10 → $1.20/Mtok (+9%)
▲ Qwen: Qwen3 VL 30B A3B Instruct input: $0.13 → $0.15/Mtok (+15%)
▲ Qwen: Qwen3 VL 30B A3B Instruct output: $0.52 → $0.60/Mtok (+15%)
▼ Qwen: Qwen3.5-27B input: $0.26 → $0.20/Mtok (-25%)
New: Ling-3.0-flash (free) (free/free per Mtok)
2026-07-22
▼ Google: Gemma 4 31B output: $0.37 → $0.35/Mtok (-5%)
▲ Qwen: Qwen3 14B input: $0.12 → $0.23/Mtok (+90%)
▲ Qwen: Qwen3 14B output: $0.24 → $0.91/Mtok (+279%)
▲ Qwen: Qwen3 Next 80B A3B Instruct output: $0.78 → $1.10/Mtok (+41%)
New: Anthropic: Claude Fable 5 (batch) ($5.00/$25.00 per Mtok) · Anthropic: Claude Opus 4.1 (batch) ($7.50/$37.50 per Mtok) · Anthropic: Claude Opus 4.5 (batch) ($2.50/$12.50 per Mtok) · Anthropic: Claude Opus 4.6 (batch) ($2.50/$12.50 per Mtok) · Anthropic: Claude Opus 4.7 (batch) ($2.50/$12.50 per Mtok) · Anthropic: Claude Opus 4.8 (batch) ($2.50/$12.50 per Mtok) · OpenAI: GPT-3.5 Turbo (batch) ($0.25/$0.75 per Mtok) · OpenAI: GPT-4 Turbo (batch) ($5.00/$15.00 per Mtok)
2026-07-21
▲ NVIDIA: Nemotron 3 Super output: $0.40 → $0.45/Mtok (+12%)
▼ Qwen: Qwen3 Next 80B A3B Instruct output: $1.10 → $0.78/Mtok (-29%)
▼ Tencent: Hy3 input: $0.20 → $0.14/Mtok (-30%)
▼ Tencent: Hy3 output: $0.80 → $0.58/Mtok (-28%)
▼ Z.ai: GLM 5.2 input: $0.98 → $0.77/Mtok (-21%)
▼ Z.ai: GLM 5.2 output: $3.08 → $2.42/Mtok (-21%)
▼ Google Gemini Flash Latest output: $9.00 → $7.50/Mtok (-17%)
New: Google: Gemini 3.5 Flash-Lite ($0.30/$2.50 per Mtok) · Google: Gemini 3.6 Flash ($1.50/$7.50 per Mtok) · Poolside: Laguna S 2.1 ($0.10/$0.20 per Mtok) · Poolside: Laguna S 2.1 (free) (free/free per Mtok)
2026-07-20
▼ Google: Gemma 4 31B input: $0.22 → $0.12/Mtok (-45%)
▼ Google: Gemma 4 31B output: $0.55 → $0.37/Mtok (-33%)
▲ Z.ai: GLM 5.2 input: $0.95 → $0.98/Mtok (+3%)
▲ Z.ai: GLM 5.2 output: $2.99 → $3.08/Mtok (+3%)
Current prices
| Qwen: Qwen3.8 Maxqwen | $2.00 | $6.00 | 1M | Aug 2026 |
| DeepSeek V4 Flash Latestdeepseek | $0.09 | $0.18 | 1M | Aug 2026 |
| DeepSeek: DeepSeek V4 Flash 0731deepseek | $0.09 | $0.18 | 1M | Jul 2026 |
| Thinking Machines: Inkling Smallthinkingmachines | $0.50 | $1.20 | 524K | Jul 2026 |
| Qwen: Qwen3.7 Flashqwen | $0.03 | $0.13 | 1M | Jul 2026 |
| Claude Opus 5 (Fast)anthropic | $10.00 | $50.00 | 1M | Jul 2026 |
| Claude Opus 5anthropic | $5.00 | $25.00 | 1M | Jul 2026 |
| Ling-3.0-flash (free)inclusionai | free | free | 262K | Jul 2026 |
| Poolside: Laguna S 2.1poolside | $0.09 | $0.18 | 1M | Jul 2026 |
| Poolside: Laguna S 2.1 (free)poolside | free | free | 262K | Jul 2026 |
| Google: Gemini 3.6 Flashgoogle | $1.50 | $7.50 | 1M | Jul 2026 |
| Google: Gemini 3.5 Flash Litegoogle | $0.30 | $2.50 | 1M | Jul 2026 |
| Meituan: LongCat 2.0meituan | $0.30 | $1.20 | 1M | Jul 2026 |
| Thinking Machines: Inklingthinkingmachines | $1.00 | $4.05 | 1M | Jul 2026 |
| MoonshotAI: Kimi K3moonshotai | $3.00 | $15.00 | 1M | Jul 2026 |
| Meta: Muse Spark 1.1meta | $1.25 | $4.25 | 1M | Jul 2026 |
| Kwaipilot: KAT-Coder-Air V2.5kwaipilot | $0.15 | $0.60 | 256K | Jul 2026 |
| Kwaipilot: KAT-Coder-Pro V2.5kwaipilot | $0.74 | $2.96 | 256K | Jul 2026 |
| OpenAI: GPT-5.6 Luna Proopenai | $0.10 | $0.60 | 1M | Jul 2026 |
| OpenAI: GPT-5.6 Lunaopenai | $0.10 | $0.60 | 1M | Jul 2026 |
| OpenAI: GPT-5.6 Terra Proopenai | $1.00 | $6.00 | 1M | Jul 2026 |
| OpenAI: GPT-5.6 Terraopenai | $1.00 | $6.00 | 1M | Jul 2026 |
| OpenAI: GPT-5.6 Sol Proopenai | $5.00 | $30.00 | 1M | Jul 2026 |
| OpenAI: GPT-5.6 Solopenai | $5.00 | $30.00 | 1M | Jul 2026 |
| xAI: Grok 4.5x-ai | $2.00 | $6.00 | 500K | Jul 2026 |
| xAI: Grok Latestx-ai | $2.00 | $6.00 | 500K | Jul 2026 |
| AionLabs: Aion-3.0-Miniaion-labs | $0.70 | $1.40 | 131K | Jul 2026 |
| AionLabs: Aion-3.0aion-labs | $3.00 | $6.00 | 131K | Jul 2026 |
| Tencent: Hy3tencent | $0.14 | $0.53 | 262K | Jul 2026 |
| Poolside: Laguna XS 2.1poolside | $0.06 | $0.12 | 262K | Jul 2026 |
| Poolside: Laguna XS 2.1 (free)poolside | free | free | 262K | Jul 2026 |
| Anthropic: Claude Sonnet 5anthropic | $2.00 | $10.00 | 1M | Jun 2026 |
| Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google | $0.25 | $1.50 | 66K | Jun 2026 |
| Nex AGI: Nex-N2-Mininex-agi | $0.03 | $0.10 | 262K | Jun 2026 |
| Sakana: Fugu Ultrasakana | $5.00 | $30.00 | 1M | Jun 2026 |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image)google | $0.50 | $3.00 | 131K | Jun 2026 |
| Google: Nano Banana Pro (Gemini 3 Pro Image)google | $2.00 | $12.00 | 131K | Jun 2026 |
| Cohere: North Mini Code (free)cohere | free | free | 256K | Jun 2026 |
| Z.ai: GLM 5.2z-ai | $0.63 | $1.98 | 1M | Jun 2026 |
| MoonshotAI: Kimi K2.7 Codemoonshotai | $0.73 | $3.50 | 262K | Jun 2026 |
| Anthropic: Claude Fable Latestanthropic | $10.00 | $50.00 | 1M | Jun 2026 |
| Anthropic: Claude Fable 5anthropic | $10.00 | $50.00 | 1M | Jun 2026 |
| Nex AGI: Nex-N2-Pronex-agi | $0.25 | $1.00 | 262K | Jun 2026 |
| NVIDIA: Nemotron 3.5 Content Safety (free)nvidia | free | free | 128K | Jun 2026 |
| NVIDIA: Nemotron 3 Ultranvidia | $0.60 | $3.60 | 512K | Jun 2026 |
| NVIDIA: Nemotron 3 Ultra (free)nvidia | free | free | 1M | Jun 2026 |
| Qwen: Qwen3.7 Plusqwen | $0.32 | $1.28 | 1M | Jun 2026 |
| MiniMax: MiniMax M3minimax | $0.30 | $1.20 | 1M | May 2026 |
| StepFun: Step 3.7 Flashstepfun | $0.20 | $1.15 | 262K | May 2026 |
| Anthropic: Claude Opus 4.8 (Fast)anthropic | $10.00 | $50.00 | 1M | May 2026 |
| Anthropic: Claude Opus 4.8anthropic | $5.00 | $25.00 | 1M | May 2026 |
| Qwen: Qwen3.7 Maxqwen | $1.48 | $4.42 | 1M | May 2026 |
| xAI: Grok Build 0.1x-ai | $1.00 | $2.00 | 256K | May 2026 |
| Google: Gemini 3.5 Flashgoogle | $1.50 | $9.00 | 1M | May 2026 |
| Anthropic: Claude Opus 4.7 (Fast)anthropic | $30.00 | $150.00 | 1M | May 2026 |
| Perceptron: Perceptron Mk1perceptron | $0.15 | $1.50 | 33K | May 2026 |
| inclusionAI: Ring-2.6-1Tinclusionai | $0.07 | $0.63 | 262K | May 2026 |
| Google: Gemini 3.1 Flash Litegoogle | $0.25 | $1.50 | 1M | May 2026 |
| OpenAI: GPT Chat Latestopenai | $5.00 | $30.00 | 400K | May 2026 |
| xAI: Grok 4.3x-ai | $1.25 | $2.50 | 1M | Apr 2026 |
| IBM: Granite 4.1 8Bibm-granite | $0.05 | $0.10 | 131K | Apr 2026 |
| Mistral: Mistral Medium 3.5mistralai | $1.50 | $7.50 | 262K | Apr 2026 |
| NVIDIA: Nemotron 3 Nano Omni (free)nvidia | free | free | 256K | Apr 2026 |
| Anthropic Claude Haiku Latestanthropic | $1.00 | $5.00 | 200K | Apr 2026 |
| OpenAI GPT Mini Latestopenai | $0.75 | $4.50 | 400K | Apr 2026 |
| Google Gemini Pro Latestgoogle | $2.00 | $12.00 | 1M | Apr 2026 |
| MoonshotAI Kimi Latestmoonshotai | $2.90 | $14.00 | 1M | Apr 2026 |
| Google Gemini Flash Latestgoogle | $1.50 | $7.50 | 1M | Apr 2026 |
| Anthropic Claude Sonnet Latestanthropic | $2.00 | $10.00 | 1M | Apr 2026 |
| OpenAI GPT Latestopenai | $5.00 | $30.00 | 1M | Apr 2026 |
| Qwen: Qwen3.5 Plus 2026-04-20qwen | $0.30 | $1.80 | 1M | Apr 2026 |
| Qwen: Qwen3.6 Flashqwen | $0.19 | $1.13 | 1M | Apr 2026 |
| Qwen: Qwen3.6 35B A3Bqwen | $0.14 | $1.00 | 262K | Apr 2026 |
| Qwen: Qwen3.6 Max Previewqwen | $1.03 | $6.16 | 262K | Apr 2026 |
| Qwen: Qwen3.6 27Bqwen | $0.29 | $2.40 | 262K | Apr 2026 |
| OpenAI: GPT-5.5 Proopenai | $30.00 | $180.00 | 1M | Apr 2026 |
| OpenAI: GPT-5.5openai | $5.00 | $30.00 | 1M | Apr 2026 |
| DeepSeek: DeepSeek V4 Prodeepseek | $0.43 | $0.87 | 1M | Apr 2026 |
| DeepSeek: DeepSeek V4 Flash 0423deepseek | $0.14 | $0.28 | 1M | Apr 2026 |
| inclusionAI: Ling-2.6-1Tinclusionai | $0.07 | $0.63 | 262K | Apr 2026 |
| Tencent: Hy3 previewtencent | $0.06 | $0.21 | 262K | Apr 2026 |
| Xiaomi: MiMo-V2.5-Proxiaomi | $0.43 | $0.87 | 1M | Apr 2026 |
| Xiaomi: MiMo-V2.5xiaomi | $0.14 | $0.28 | 1M | Apr 2026 |
| OpenAI: GPT-5.4 Image 2openai | $8.00 | $15.00 | 272K | Apr 2026 |
| inclusionAI: Ling-2.6-flashinclusionai | $0.01 | $0.03 | 262K | Apr 2026 |
| Anthropic: Claude Opus Latestanthropic | $5.00 | $25.00 | 1M | Apr 2026 |
| MoonshotAI: Kimi K2.6moonshotai | $0.60 | $3.41 | 262K | Apr 2026 |
| Anthropic: Claude Opus 4.7anthropic | $5.00 | $25.00 | 1M | Apr 2026 |
| Z.ai: GLM 5.1z-ai | $0.97 | $3.04 | 205K | Apr 2026 |
| Google: Gemma 4 26B A4B google | $0.07 | $0.34 | 262K | Apr 2026 |
| Google: Gemma 4 26B A4B (free)google | free | free | 262K | Apr 2026 |
| Google: Gemma 4 31Bgoogle | $0.10 | $0.34 | 262K | Apr 2026 |
| Google: Gemma 4 31B (free)google | free | free | 262K | Apr 2026 |
| Qwen: Qwen3.6 Plusqwen | $0.33 | $1.95 | 1M | Apr 2026 |
| Z.ai: GLM 5V Turboz-ai | $1.20 | $4.00 | 203K | Apr 2026 |
| Arcee AI: Trinity Large Thinkingarcee-ai | $0.22 | $0.85 | 262K | Apr 2026 |
| xAI: Grok 4.20 Multi-Agentx-ai | $1.25 | $2.50 | 1.9M | Mar 2026 |
| xAI: Grok 4.20x-ai | $1.25 | $2.50 | 1.9M | Mar 2026 |
| Kwaipilot: KAT-Coder-Pro V2kwaipilot | $0.30 | $1.20 | 262K | Mar 2026 |
| Reka Edgerekaai | $0.10 | $0.10 | 16K | Mar 2026 |
| MiniMax: MiniMax M2.7minimax | $0.25 | $1.00 | 205K | Mar 2026 |
| OpenAI: GPT-5.4 Nanoopenai | $0.20 | $1.25 | 400K | Mar 2026 |
| OpenAI: GPT-5.4 Miniopenai | $0.75 | $4.50 | 400K | Mar 2026 |
| Mistral: Mistral Small 4mistralai | $0.15 | $0.60 | 262K | Mar 2026 |
| Z.ai: GLM 5 Turboz-ai | $1.20 | $4.00 | 203K | Mar 2026 |
| NVIDIA: Nemotron 3 Supernvidia | $0.09 | $0.40 | 1M | Mar 2026 |
| NVIDIA: Nemotron 3 Super (free)nvidia | free | free | 262K | Mar 2026 |
| ByteDance Seed: Seed-2.0-Litebytedance-seed | $0.25 | $2.00 | 262K | Mar 2026 |
| Qwen: Qwen3.5-9Bqwen | $0.10 | $0.15 | 262K | Mar 2026 |
| OpenAI: GPT-5.4 Proopenai | $30.00 | $180.00 | 1M | Mar 2026 |
| OpenAI: GPT-5.4openai | $2.50 | $15.00 | 1M | Mar 2026 |
| Inception: Mercury 2inception | $0.25 | $0.75 | 128K | Mar 2026 |
| OpenAI: GPT-5.3 Chatopenai | $1.75 | $14.00 | 128K | Mar 2026 |
| Google: Gemini 3.1 Flash Lite Previewgoogle | $0.25 | $1.50 | 1M | Mar 2026 |
| ByteDance Seed: Seed-2.0-Minibytedance-seed | $0.10 | $0.40 | 262K | Feb 2026 |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)google | $0.50 | $3.00 | 66K | Feb 2026 |
| Qwen: Qwen3.5-35B-A3Bqwen | $0.14 | $1.00 | 262K | Feb 2026 |
| Qwen: Qwen3.5-27Bqwen | $0.20 | $1.56 | 262K | Feb 2026 |
| Qwen: Qwen3.5-122B-A10Bqwen | $0.26 | $2.08 | 262K | Feb 2026 |
| Qwen: Qwen3.5-Flashqwen | $0.07 | $0.26 | 1M | Feb 2026 |
| Google: Gemini 3.1 Pro Preview Custom Toolsgoogle | $2.00 | $12.00 | 1M | Feb 2026 |
| OpenAI: GPT-5.3-Codexopenai | $1.75 | $14.00 | 400K | Feb 2026 |
| AionLabs: Aion-2.0aion-labs | $0.80 | $1.60 | 131K | Feb 2026 |
| Google: Gemini 3.1 Pro Previewgoogle | $2.00 | $12.00 | 1M | Feb 2026 |
| Anthropic: Claude Sonnet 4.6anthropic | $3.00 | $15.00 | 1M | Feb 2026 |
| Qwen: Qwen3.5 Plus 2026-02-15qwen | $0.26 | $1.56 | 1M | Feb 2026 |
| Qwen: Qwen3.5 397B A17Bqwen | $0.39 | $2.34 | 262K | Feb 2026 |
| MiniMax: MiniMax M2.5minimax | $0.15 | $0.90 | 205K | Feb 2026 |
| Z.ai: GLM 5z-ai | $0.95 | $2.55 | 205K | Feb 2026 |
| Qwen: Qwen3 Max Thinkingqwen | $0.78 | $3.90 | 262K | Feb 2026 |
| Anthropic: Claude Opus 4.6anthropic | $5.00 | $25.00 | 1M | Feb 2026 |
| Qwen: Qwen3 Coder Nextqwen | $0.12 | $0.80 | 262K | Feb 2026 |
| StepFun: Step 3.5 Flashstepfun | $0.10 | $0.30 | 262K | Jan 2026 |
| MoonshotAI: Kimi K2.5moonshotai | $0.57 | $2.85 | 262K | Jan 2026 |
| Upstage: Solar Pro 3upstage | $0.15 | $0.60 | 128K | Jan 2026 |
| MiniMax: MiniMax M2-herminimax | $0.30 | $1.20 | 66K | Jan 2026 |
| Writer: Palmyra X5writer | $0.60 | $6.00 | 1M | Jan 2026 |
| OpenAI: GPT Audioopenai | $2.50 | $10.00 | 128K | Jan 2026 |
| OpenAI: GPT Audio Miniopenai | $0.60 | $2.40 | 128K | Jan 2026 |
| Z.ai: GLM 4.7 Flashz-ai | $0.06 | $0.40 | 203K | Jan 2026 |
| OpenAI: GPT-5.2-Codexopenai | $1.75 | $14.00 | 400K | Jan 2026 |
| ByteDance Seed: Seed 1.6 Flashbytedance-seed | $0.07 | $0.30 | 262K | Dec 2025 |
| ByteDance Seed: Seed 1.6bytedance-seed | $0.25 | $2.00 | 262K | Dec 2025 |
| MiniMax: MiniMax M2.1minimax | $0.30 | $1.20 | 205K | Dec 2025 |
| Z.ai: GLM 4.7z-ai | $0.40 | $1.75 | 205K | Dec 2025 |
| Google: Gemini 3 Flash Previewgoogle | $0.50 | $3.00 | 1M | Dec 2025 |
| NVIDIA: Nemotron 3 Nano 30B A3Bnvidia | $0.05 | $0.20 | 262K | Dec 2025 |
| NVIDIA: Nemotron 3 Nano 30B A3B (free)nvidia | free | free | 256K | Dec 2025 |
| OpenAI: GPT-5.2 Chatopenai | $1.75 | $14.00 | 128K | Dec 2025 |
| OpenAI: GPT-5.2 Proopenai | $21.00 | $168.00 | 400K | Dec 2025 |
| OpenAI: GPT-5.2openai | $1.75 | $14.00 | 400K | Dec 2025 |
| Relace: Relace Searchrelace | $1.00 | $3.00 | 256K | Dec 2025 |
| Z.ai: GLM 4.6Vz-ai | $0.30 | $0.90 | 131K | Dec 2025 |
| OpenAI: GPT-5.1-Codex-Maxopenai | $1.25 | $10.00 | 400K | Dec 2025 |
| Amazon: Nova 2 Liteamazon | $0.30 | $2.50 | 1M | Dec 2025 |
| Mistral: Ministral 3 14B 2512mistralai | $0.20 | $0.20 | 262K | Dec 2025 |
| Mistral: Ministral 3 8B 2512mistralai | $0.15 | $0.15 | 262K | Dec 2025 |
| Mistral: Ministral 3 3B 2512mistralai | $0.10 | $0.10 | 131K | Dec 2025 |
| Mistral: Mistral Large 3 2512mistralai | $0.50 | $1.50 | 262K | Dec 2025 |
| DeepSeek: DeepSeek V3.2deepseek | $0.27 | $0.40 | 164K | Dec 2025 |
| Anthropic: Claude Opus 4.5anthropic | $5.00 | $25.00 | 200K | Nov 2025 |
| AllenAI: Olmo 3 32B Thinkallenai | $0.15 | $0.50 | 66K | Nov 2025 |
| Google: Nano Banana Pro (Gemini 3 Pro Image Preview)google | $2.00 | $12.00 | 66K | Nov 2025 |
| Deep Cogito: Cogito v2.1 671Bdeepcogito | $1.25 | $1.25 | 128K | Nov 2025 |
| OpenAI: GPT-5.1openai | $1.25 | $10.00 | 400K | Nov 2025 |
| OpenAI: GPT-5.1-Codexopenai | $1.25 | $10.00 | 400K | Nov 2025 |
| OpenAI: GPT-5.1-Codex-Miniopenai | $0.25 | $2.00 | 400K | Nov 2025 |
| MoonshotAI: Kimi K2 Thinkingmoonshotai | $0.60 | $2.50 | 262K | Nov 2025 |
| Amazon: Nova Premier 1.0amazon | $2.50 | $12.50 | 1M | Oct 2025 |
| Perplexity: Sonar Pro Searchperplexity | $3.00 | $15.00 | 200K | Oct 2025 |
| Mistral: Voxtral Small 24B 2507mistralai | $0.10 | $0.30 | 32K | Oct 2025 |
| OpenAI: gpt-oss-safeguard-20bopenai | $0.07 | $0.30 | 131K | Oct 2025 |
| NVIDIA: Nemotron Nano 12B 2 VL (free)nvidia | free | free | 128K | Oct 2025 |
| MiniMax: MiniMax M2minimax | $0.26 | $1.02 | 205K | Oct 2025 |
| Qwen: Qwen3 VL 32B Instructqwen | $0.10 | $0.42 | 131K | Oct 2025 |
| IBM: Granite 4.0 Microibm-granite | $0.02 | $0.11 | 131K | Oct 2025 |
| OpenAI: GPT-5 Image Miniopenai | $2.50 | $2.00 | 400K | Oct 2025 |
| Anthropic: Claude Haiku 4.5anthropic | $1.00 | $5.00 | 200K | Oct 2025 |
| Qwen: Qwen3 VL 8B Thinkingqwen | $0.18 | $2.10 | 131K | Oct 2025 |
| Qwen: Qwen3 VL 8B Instructqwen | $0.12 | $0.46 | 262K | Oct 2025 |
| OpenAI: GPT-5 Imageopenai | $10.00 | $10.00 | 400K | Oct 2025 |
| Google: Nano Banana (Gemini 2.5 Flash Image)google | $0.30 | $2.50 | 33K | Oct 2025 |
| Qwen: Qwen3 VL 30B A3B Thinkingqwen | $0.20 | $2.40 | 262K | Oct 2025 |
| Qwen: Qwen3 VL 30B A3B Instructqwen | $0.13 | $0.52 | 262K | Oct 2025 |
| OpenAI: GPT-5 Proopenai | $15.00 | $120.00 | 400K | Oct 2025 |
| Z.ai: GLM 4.6z-ai | $0.50 | $2.00 | 205K | Sep 2025 |
| Anthropic: Claude Sonnet 4.5anthropic | $3.00 | $15.00 | 1M | Sep 2025 |
| DeepSeek: DeepSeek V3.2 Expdeepseek | $0.27 | $0.41 | 164K | Sep 2025 |
| TheDrummer: Cydonia 24B V4.1thedrummer | $0.30 | $0.50 | 131K | Sep 2025 |
| Relace: Relace Apply 3relace | $0.85 | $1.25 | 256K | Sep 2025 |
| Qwen: Qwen3 VL 235B A22B Thinkingqwen | $0.98 | $3.95 | 131K | Sep 2025 |
| Qwen: Qwen3 VL 235B A22B Instructqwen | $0.21 | $1.90 | 262K | Sep 2025 |
| Qwen: Qwen3 Maxqwen | $0.78 | $3.90 | 262K | Sep 2025 |
| Qwen: Qwen3 Coder Plusqwen | $0.65 | $3.25 | 1M | Sep 2025 |
| DeepSeek: DeepSeek V3.1 Terminusdeepseek | $0.27 | $1.00 | 164K | Sep 2025 |
| Qwen: Qwen3 Coder Flashqwen | $0.20 | $0.97 | 1M | Sep 2025 |
| Qwen: Qwen3 Next 80B A3B Thinkingqwen | $0.15 | $1.20 | 262K | Sep 2025 |
| Qwen: Qwen3 Next 80B A3B Instructqwen | $0.10 | $1.10 | 262K | Sep 2025 |
| Qwen: Qwen Plus 0728qwen | $0.26 | $0.78 | 1M | Sep 2025 |
| Qwen: Qwen Plus 0728 (thinking)qwen | $0.40 | $1.20 | 1M | Sep 2025 |
| NVIDIA: Nemotron Nano 9B V2 (free)nvidia | free | free | 128K | Sep 2025 |
| MoonshotAI: Kimi K2 0905moonshotai | $0.60 | $2.50 | 262K | Sep 2025 |
| Qwen: Qwen3 30B A3B Thinking 2507qwen | $0.20 | $2.40 | 82K | Aug 2025 |
| Nous: Hermes 4 70Bnousresearch | $0.13 | $0.40 | 131K | Aug 2025 |
| Nous: Hermes 4 405Bnousresearch | $1.00 | $3.00 | 131K | Aug 2025 |
| DeepSeek: DeepSeek V3.1deepseek | $0.25 | $0.95 | 164K | Aug 2025 |
| Mistral: Mistral Medium 3.1mistralai | $0.40 | $2.00 | 131K | Aug 2025 |
| Z.ai: GLM 4.5Vz-ai | $0.60 | $1.80 | 66K | Aug 2025 |
| AI21: Jamba Large 1.7ai21 | $2.00 | $8.00 | 256K | Aug 2025 |
| OpenAI: GPT-5openai | $1.25 | $10.00 | 400K | Aug 2025 |
| OpenAI: GPT-5 Miniopenai | $0.25 | $2.00 | 400K | Aug 2025 |
| OpenAI: GPT-5 Nanoopenai | $0.05 | $0.40 | 400K | Aug 2025 |
| OpenAI: gpt-oss-120bopenai | $0.04 | $0.17 | 131K | Aug 2025 |
| OpenAI: gpt-oss-20bopenai | $0.03 | $0.13 | 131K | Aug 2025 |
| OpenAI: gpt-oss-20b (free)openai | free | free | 131K | Aug 2025 |
| Anthropic: Claude Opus 4.1anthropic | $15.00 | $75.00 | 200K | Aug 2025 |
| Mistral: Codestral 2508mistralai | $0.30 | $0.90 | 256K | Aug 2025 |
| Qwen: Qwen3 Coder 30B A3B Instructqwen | $0.07 | $0.27 | 262K | Jul 2025 |
| Qwen: Qwen3 30B A3B Instruct 2507qwen | $0.05 | $0.19 | 262K | Jul 2025 |
| Z.ai: GLM 4.5z-ai | $0.60 | $2.20 | 131K | Jul 2025 |
| Z.ai: GLM 4.5 Airz-ai | $0.13 | $0.85 | 131K | Jul 2025 |
| Qwen: Qwen3 235B A22B Thinking 2507qwen | $0.23 | $2.30 | 262K | Jul 2025 |
| Qwen: Qwen3 Coder 480B A35Bqwen | $0.30 | $1.00 | 262K | Jul 2025 |
| ByteDance: UI-TARS 7B bytedance | $0.10 | $0.20 | 128K | Jul 2025 |
| Google: Gemini 2.5 Flash Litegoogle | $0.10 | $0.40 | 1M | Jul 2025 |
| Qwen: Qwen3 235B A22B Instruct 2507qwen | $0.15 | $0.60 | 262K | Jul 2025 |
| MoonshotAI: Kimi K2 0711moonshotai | $0.57 | $2.30 | 131K | Jul 2025 |
| Venice: Uncensoredcognitivecomputations | $0.20 | $0.90 | 128K | Jul 2025 |
| Tencent: Hunyuan A13B Instructtencent | $0.14 | $0.57 | 131K | Jul 2025 |
| Morph: Morph V3 Largemorph | $0.90 | $1.90 | 262K | Jul 2025 |
| Morph: Morph V3 Fastmorph | $0.80 | $1.20 | 82K | Jul 2025 |
| Baidu: ERNIE 4.5 VL 424B A47B baidu | $0.42 | $1.25 | 123K | Jun 2025 |
| Mistral: Mistral Small 3.2 24Bmistralai | $0.07 | $0.20 | 256K | Jun 2025 |
| MiniMax: MiniMax M1minimax | $0.55 | $2.20 | 1M | Jun 2025 |
| Google: Gemini 2.5 Flashgoogle | $0.30 | $2.50 | 1M | Jun 2025 |
| Google: Gemini 2.5 Progoogle | $1.25 | $10.00 | 1M | Jun 2025 |
| OpenAI: o3 Proopenai | $20.00 | $80.00 | 200K | Jun 2025 |
| Google: Gemini 2.5 Pro Preview 06-05google | $1.25 | $10.00 | 1M | Jun 2025 |
| DeepSeek: R1 0528deepseek | $0.50 | $2.15 | 164K | May 2025 |
| Anthropic: Claude Opus 4anthropic | $15.00 | $75.00 | 200K | May 2025 |
| Anthropic: Claude Sonnet 4anthropic | $3.00 | $15.00 | 1M | May 2025 |
| Google: Gemma 3n 4Bgoogle | $0.06 | $0.12 | 33K | May 2025 |
| Mistral: Mistral Medium 3mistralai | $0.40 | $2.00 | 131K | May 2025 |
| Google: Gemini 2.5 Pro Preview 05-06google | $1.25 | $10.00 | 1M | May 2025 |
| Arcee AI: Virtuoso Largearcee-ai | $0.75 | $1.20 | 131K | May 2025 |
| Meta: Llama Guard 4 12Bmeta-llama | $0.18 | $0.18 | 1M | Apr 2025 |
| Qwen: Qwen3 30B A3Bqwen | $0.12 | $0.50 | 131K | Apr 2025 |
| Qwen: Qwen3 8Bqwen | $0.12 | $0.46 | 131K | Apr 2025 |
| Qwen: Qwen3 14Bqwen | $0.23 | $0.91 | 131K | Apr 2025 |
| Qwen: Qwen3 32Bqwen | $0.08 | $0.28 | 131K | Apr 2025 |
| Qwen: Qwen3 235B A22Bqwen | $0.46 | $1.82 | 131K | Apr 2025 |
| OpenAI: o4 Mini Highopenai | $1.10 | $4.40 | 200K | Apr 2025 |
| OpenAI: o3openai | $2.00 | $8.00 | 200K | Apr 2025 |
| OpenAI: o4 Miniopenai | $1.10 | $4.40 | 200K | Apr 2025 |
| OpenAI: GPT-4.1openai | $2.00 | $8.00 | 1M | Apr 2025 |
| OpenAI: GPT-4.1 Miniopenai | $0.40 | $1.60 | 1M | Apr 2025 |
| OpenAI: GPT-4.1 Nanoopenai | $0.10 | $0.40 | 1M | Apr 2025 |
| Meta: Llama 4 Maverickmeta-llama | $0.20 | $0.80 | 1M | Apr 2025 |
| Meta: Llama 4 Scoutmeta-llama | $0.10 | $0.30 | 1.3M | Apr 2025 |
| DeepSeek: DeepSeek V3 0324deepseek | $0.27 | $1.12 | 164K | Mar 2025 |
| OpenAI: o1-proopenai | $150.00 | $600.00 | 200K | Mar 2025 |
| Mistral: Mistral Small 3.1 24Bmistralai | $0.35 | $0.56 | 128K | Mar 2025 |
| Google: Gemma 3 4Bgoogle | $0.05 | $0.10 | 131K | Mar 2025 |
| Google: Gemma 3 12Bgoogle | $0.05 | $0.15 | 131K | Mar 2025 |
| Cohere: Command Acohere | $2.50 | $10.00 | 256K | Mar 2025 |
| Reka Flash 3rekaai | $0.10 | $0.20 | 66K | Mar 2025 |
| Google: Gemma 3 27Bgoogle | $0.08 | $0.45 | 262K | Mar 2025 |
| TheDrummer: Skyfall 36B V2thedrummer | $0.55 | $0.80 | 33K | Mar 2025 |
| Perplexity: Sonar Reasoning Properplexity | $2.00 | $8.00 | 128K | Mar 2025 |
| Perplexity: Sonar Properplexity | $3.00 | $15.00 | 200K | Mar 2025 |
| Perplexity: Sonar Deep Researchperplexity | $2.00 | $8.00 | 128K | Mar 2025 |
| Mistral: Sabamistralai | $0.20 | $0.60 | 33K | Feb 2025 |
| OpenAI: o3 Mini Highopenai | $1.10 | $4.40 | 200K | Feb 2025 |
| AionLabs: Aion-RP 1.0 (8B)aion-labs | $0.80 | $1.60 | 33K | Feb 2025 |
| Qwen: Qwen2.5 VL 72B Instructqwen | $0.80 | $1.00 | 128K | Feb 2025 |
| Qwen: Qwen-Plusqwen | $0.26 | $0.78 | 1M | Feb 2025 |
| OpenAI: o3 Miniopenai | $1.10 | $4.40 | 200K | Jan 2025 |
| Mistral: Mistral Small 3mistralai | $0.05 | $0.08 | 33K | Jan 2025 |
| Perplexity: Sonarperplexity | $1.00 | $1.00 | 127K | Jan 2025 |
| DeepSeek: R1 Distill Llama 70Bdeepseek | $0.80 | $0.80 | 8K | Jan 2025 |
| DeepSeek: R1deepseek | $0.70 | $2.50 | 164K | Jan 2025 |
| MiniMax: MiniMax-01minimax | $0.20 | $1.10 | 1M | Jan 2025 |
| Microsoft: Phi 4microsoft | $0.07 | $0.14 | 16K | Jan 2025 |
| DeepSeek: DeepSeek V3deepseek | $0.26 | $1.03 | 164K | Dec 2024 |
| Sao10K: Llama 3.3 Euryale 70Bsao10k | $0.65 | $0.75 | 131K | Dec 2024 |
| OpenAI: o1openai | $15.00 | $60.00 | 200K | Dec 2024 |
| Cohere: Command R7B (12-2024)cohere | $0.04 | $0.15 | 128K | Dec 2024 |
| Meta: Llama 3.3 70B Instructmeta-llama | $0.10 | $0.32 | 131K | Dec 2024 |
| Amazon: Nova Lite 1.0amazon | $0.06 | $0.24 | 300K | Dec 2024 |
| Amazon: Nova Micro 1.0amazon | $0.04 | $0.14 | 128K | Dec 2024 |
| Amazon: Nova Pro 1.0amazon | $0.80 | $3.20 | 300K | Dec 2024 |
| OpenAI: GPT-4o (2024-11-20)openai | $2.50 | $10.00 | 128K | Nov 2024 |
| Mistral Large 2407mistralai | $2.00 | $6.00 | 131K | Nov 2024 |
| Qwen2.5 Coder 32B Instructqwen | $0.66 | $1.00 | 33K | Nov 2024 |
| TheDrummer: UnslopNemo 12Bthedrummer | $0.40 | $0.40 | 1M | Nov 2024 |
| Magnum v4 72Banthracite-org | $3.00 | $5.00 | 16K | Oct 2024 |
| Qwen: Qwen2.5 7B Instructqwen | $0.10 | $0.20 | 33K | Oct 2024 |
| TheDrummer: Rocinante 12Bthedrummer | $0.25 | $0.50 | 66K | Sep 2024 |
| Meta: Llama 3.2 1B Instructmeta-llama | $0.03 | $0.20 | 60K | Sep 2024 |
| Meta: Llama 3.2 3B Instructmeta-llama | $0.05 | $0.34 | 131K | Sep 2024 |
| Qwen2.5 72B Instructqwen | $0.36 | $0.40 | 33K | Sep 2024 |
| Cohere: Command R (08-2024)cohere | $0.15 | $0.60 | 128K | Aug 2024 |
| Cohere: Command R+ (08-2024)cohere | $2.50 | $10.00 | 128K | Aug 2024 |
| Sao10K: Llama 3.1 Euryale 70B v2.2sao10k | $0.85 | $0.85 | 131K | Aug 2024 |
| Nous: Hermes 3 70B Instructnousresearch | $0.70 | $0.70 | 131K | Aug 2024 |
| Nous: Hermes 3 405B Instructnousresearch | $1.00 | $1.00 | 131K | Aug 2024 |
| Sao10K: Llama 3 8B Lunarissao10k | $0.04 | $0.05 | 8K | Aug 2024 |
| OpenAI: GPT-4o (2024-08-06)openai | $2.50 | $10.00 | 128K | Aug 2024 |
| Meta: Llama 3.1 70B Instructmeta-llama | $0.40 | $0.40 | 131K | Jul 2024 |
| Meta: Llama 3.1 8B Instructmeta-llama | $0.05 | $0.08 | 131K | Jul 2024 |
| Mistral: Mistral Nemomistralai | $0.02 | $0.03 | 131K | Jul 2024 |
| OpenAI: GPT-4o-miniopenai | $0.15 | $0.60 | 128K | Jul 2024 |
| OpenAI: GPT-4o-mini (2024-07-18)openai | $0.15 | $0.60 | 128K | Jul 2024 |
| Google: Gemma 2 27Bgoogle | $0.65 | $0.65 | 8K | Jul 2024 |
| OpenAI: GPT-4oopenai | $2.50 | $10.00 | 128K | May 2024 |
| OpenAI: GPT-4o (2024-05-13)openai | $5.00 | $15.00 | 128K | May 2024 |
| Mistral: Mixtral 8x22B Instructmistralai | $2.00 | $6.00 | 66K | Apr 2024 |
| WizardLM-2 8x22Bmicrosoft | $0.62 | $0.62 | 66K | Apr 2024 |
| OpenAI: GPT-4 Turboopenai | $10.00 | $30.00 | 128K | Apr 2024 |
| Anthropic: Claude 3 Haikuanthropic | $0.25 | $1.25 | 200K | Mar 2024 |
| Mistral Largemistralai | $2.00 | $6.00 | 128K | Feb 2024 |
| OpenAI: GPT-3.5 Turbo (older v0613)openai | $1.00 | $2.00 | 4K | Jan 2024 |
| OpenAI: GPT-4 Turbo Previewopenai | $10.00 | $30.00 | 128K | Jan 2024 |
| OpenAI: GPT-3.5 Turbo Instructopenai | $1.50 | $2.00 | 4K | Sep 2023 |
| OpenAI: GPT-3.5 Turbo 16kopenai | $3.00 | $4.00 | 16K | Aug 2023 |
| Mancer: Weaver (alpha)mancer | $0.50 | $0.75 | 8K | Aug 2023 |
| ReMM SLERP 13Bundi95 | $0.45 | $0.65 | 6K | Jul 2023 |
| MythoMax 13Bgryphe | $0.06 | $0.06 | 8K | Jul 2023 |
| OpenAI: GPT-3.5 Turboopenai | $0.50 | $1.50 | 16K | May 2023 |
| OpenAI: GPT-4openai | $30.00 | $60.00 | 8K | May 2023 |
Showing all 330 tracked models. Click a column header to sort; sorting by price puts free tiers first.
Methodology
Prices are pulled daily from the OpenRouter models API — the routing layer most teams use as a neutral price reference — and normalized to USD per million tokens. The change log records every detected move, so this page doubles as a price history. "free" means a zero-cost routed tier exists; production SLAs on paid tiers differ. Cache-read and batch discounts are not shown.
Get repricing alerts. The Stack Pulse newsletter flags meaningful LLM price moves and what they mean for your inference bill — weekly, free. Subscribe