Model intelligence overview
Artificial Analysis Free API scores and benchmark task costs are paired with OpenCode Go's model-specific monthly allowances. Compare raw benchmark cost or an estimate repriced to Go's token rates and allowance multiplier.
The x-axis is logarithmic. The Pareto frontier connects models that improve the selected score without being dominated by a cheaper model.
Sort by score, effective task cost, or estimated monthly requests. Price and privacy scenarios come from the Go docs.
| Go rate · allowance | Status | Graph | ||||
|---|---|---|---|---|---|---|
MiniMax M2.5 MiniMax-M2.5 · Standard | 22.8 | $0.3 in · $1.20 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.06 · write $0.375 | — — AA cost | — | Unavailable | |
Kimi K3 Kimi K3 (low) · Low | 34.5 | $3.00 in · $15.00 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.3 · write — | — — AA cost | — | Unavailable | |
Kimi K2.6 Kimi K2.6 · Standard | 31.3 | $0.95 in · $4.00 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.16 · write — | — — AA cost | — | Unavailable | |
Kimi K2.6 Kimi K2.6 (Non-reasoning) · Standard | 23.6 | $0.95 in · $4.00 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.16 · write — | — — AA cost | — | Unavailable | |
Kimi K2.5 Kimi K2.5 (Reasoning) · Standard | 23.5 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Unavailable | |
Kimi K2.5 Kimi K2.5 (Non-reasoning) · Standard | 19.4 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Unavailable | |
GLM-5.2 GLM-5.2 (Non-reasoning) · Standard | 22.4 | $1.40 in · $4.40 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.26 · write — | — — AA cost | — | Unavailable | |
GLM-5.2 GLM-5.2 (max) · Max | 38.6 | $1.40 in · $4.40 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.26 · write — | — — AA cost | — | Unavailable | |
GLM-5.1 GLM-5.1 (Non-reasoning) · Standard | 24.2 | $1.40 in · $4.40 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.26 · write — | — — AA cost | — | Unavailable | |
GLM-5 GLM-5 (Reasoning) · Standard | 27.9 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Unavailable | |
GLM-5 GLM-5 (Non-reasoning) · Standard | 21.8 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Unavailable | |
DeepSeek V4 Pro DeepSeek V4 Pro (Non-reasoning) · Standard | 20.8 | $0.435 in · $0.87 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.00363 · write — | — — AA cost | — | Unavailable | |
DeepSeek V4 Flash DeepSeek V4 Flash (Non-reasoning) · Standard | 18.9 | $0.14 in · $0.28 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.0028 · write — | — — AA cost | — | Unavailable | |
Deepseek Flash Awaiting benchmark | — | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Awaiting benchmark | |
Deepseek V4.1 Flash Awaiting benchmark | — | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Awaiting benchmark | |
Qwen3.6 Plus Qwen3.6 Plus · Standard | 27.0 | $0.5 in · $3.00 out $60.00 allowance · 6.0× multiplier · 6× legacy default · ≤ 256K context cache read $0.05 · write $0.625 | — — AA cost | — | Unavailable | |
Qwen3.6 Plus Qwen3.6 Plus · Standard | 27.0 | $2.00 in · $6.00 out $60.00 allowance · 6.0× multiplier · 6× legacy default · > 256K context cache read $0.2 · write $2.50 | — — AA cost | — | Unavailable | |
Qwen3.5 Plus Qwen3.5 397B A17B (Non-reasoning) · Standard | 21.4 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Unavailable | |
MiMo V2 Pro MiMo-V2-Pro · Standard | 28.6 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Unavailable | |
MiMo V2 Omni MiMo-V2-Omni · Standard | 23.9 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Unavailable | |
MiMo V2.5 Pro MiMo-V2.5-Pro (Non-reasoning) · Standard | 18.3 | $0.435 in · $0.87 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.00363 · write — | — — AA cost | — | Unavailable | |
Hy4 Preview Awaiting benchmark | — | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Awaiting benchmark | |
Hy3 Hy3-preview (Non-reasoning) · Standard | 17.0 | $0.14 in · $0.58 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.035 · write — | — — AA cost | — | Unavailable | |
Hy3 Preview Hy3-preview (Reasoning) · Standard | 22.7 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Unavailable | |
Hy3 Preview Hy3-preview (Non-reasoning) · Standard | 17.0 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Unavailable | |
GPT 5.6 Luna GPT-5.6 Luna (low) · Low | 21.8 | $0.2 in · $1.20 out $60.00 allowance · 6.0× multiplier · 6× legacy default · ≤ 272K context cache read $0.02 · write $0.25 | — — AA cost | — | Unavailable | |
GPT 5.6 Luna GPT-5.6 Luna (low) · Low | 21.8 | $0.4 in · $1.80 out $60.00 allowance · 6.0× multiplier · 6× legacy default · > 272K context cache read $0.04 · write $0.5 | — — AA cost | — | Unavailable | |
GPT 5.6 Luna GPT-5.6 Luna (medium) · Medium | 25.8 | $0.2 in · $1.20 out $60.00 allowance · 6.0× multiplier · 6× legacy default · ≤ 272K context cache read $0.02 · write $0.25 | — — AA cost | — | Unavailable | |
GPT 5.6 Luna GPT-5.6 Luna (medium) · Medium | 25.8 | $0.4 in · $1.80 out $60.00 allowance · 6.0× multiplier · 6× legacy default · > 272K context cache read $0.04 · write $0.5 | — — AA cost | — | Unavailable | |
GPT 5.6 Luna GPT-5.6 Luna (Non-reasoning) · Standard | 16.8 | $0.2 in · $1.20 out $60.00 allowance · 6.0× multiplier · 6× legacy default · ≤ 272K context cache read $0.02 · write $0.25 | — — AA cost | — | Unavailable | |
GPT 5.6 Luna GPT-5.6 Luna (Non-reasoning) · Standard | 16.8 | $0.4 in · $1.80 out $60.00 allowance · 6.0× multiplier · 6× legacy default · > 272K context cache read $0.04 · write $0.5 | — — AA cost | — | Unavailable | |
Omen Alpha Awaiting benchmark | — | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | — — AA cost | — | Awaiting benchmark | |
Qwen3.8 Max Qwen3.8 Max · Standard | 40.3 | $2.00 in · $6.00 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.25 · write $2.50 | $0.445 $2.67 AA cost | 22.5 | Estimated | |
Grok 4.6 Grok 4.6 (xhigh) · XHigh | 44.3 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.387 $2.324 AA cost | 25.8 | Estimated | |
GLM 5.3 GLM-5.3 (max) · Max | 44.9 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.334 $2.006 AA cost | 29.9 | Estimated | |
Kimi K3 Kimi K3 (max) · Max | 43.8 | $3.00 in · $15.00 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.3 · write — | $0.333 $2 AA cost | 30 | Estimated | |
Grok 4.6 Grok 4.6 (high) · High | 44.4 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.31 $1.859 AA cost | 32.3 | Estimated | |
Muse Spark 1.3 Contributor Muse Spark 1.3 (max) · Max | 48.2 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.267 $1.605 AA cost | 37.4 | Estimated | |
Grok 4.6 Grok 4.6 (medium) · Medium | 43.0 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.249 $1.496 AA cost | 40.1 | Estimated | |
Qwen3.7 Max Qwen3.7 Max · Standard | 29.9 | $2.50 in · $7.50 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.5 · write $3.13 | $0.191 $1.147 AA cost | 52.3 | Estimated | |
Grok 4.5 Grok 4.5 (high) · High | 39.1 | $2.00 in · $6.00 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.3 · write — | $0.173 $1.036 AA cost | 57.9 | Estimated | |
Qwen3.7 Plus Qwen3.7 Plus · Standard | 25.8 | $1.20 in · $4.80 out $60.00 allowance · 6.0× multiplier · 6× legacy default · > 256K context cache read $0.12 · write $1.50 | $0.163 $0.325 AA cost 3.00× Go/AA price factor | 61.5 | Estimated | |
Muse Spark 1.2 Contributor Muse Spark 1.2 (xhigh) · XHigh | 39.8 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.162 $0.975 AA cost | 61.6 | Estimated | |
GLM-5.1 GLM-5.1 (Reasoning) · Standard | 26.4 | $1.40 in · $4.40 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.26 · write — | $0.154 $0.922 AA cost | 65.1 | Estimated | |
Kimi K2.7 Code Kimi K2.7 Code · Standard | 26.3 | $0.95 in · $4.00 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.19 · write — | $0.09 $0.541 AA cost | 110.9 | Estimated | |
MiniMax M3 MiniMax-M3 · Standard | 29.6 | $0.3 in · $1.20 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.06 · write — | $0.085 $0.508 AA cost | 118.2 | Estimated | |
GLM 5.3 Flash (2x usage) GLM-5.3-Flash · Standard | 41.9 | Token rates not listed $30.00 allowance · 3.0× multiplier · admin override | $0.084 $0.253 AA cost | 118.4 | Estimated | |
Grok 4.6 Grok 4.6 (low) · Low | 35.4 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.079 $0.475 AA cost | 126.2 | Estimated | |
Qwen3.5 Plus Qwen3.5 397B A17B (Reasoning) · Standard | 19.1 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.079 $0.475 AA cost | 126.4 | Estimated | |
Qwen3.8 Flash Qwen3.8-Flash-Next · Standard | 39.9 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.062 $0.372 AA cost | 161.2 | Estimated | |
Qwen3.7 Plus Qwen3.7 Plus · Standard | 25.8 | $0.4 in · $1.60 out $60.00 allowance · 6.0× multiplier · 6× legacy default · ≤ 256K context cache read $0.04 · write $0.5 | $0.054 $0.325 AA cost | 184.4 | Estimated | |
Deepseek V4 Flash Vision Exp DeepSeek V4 Flash Vision (Reasoning, Max Effort) · Max | 35.0 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.052 $0.314 AA cost | 190.8 | Estimated | |
GPT 5.6 Luna GPT-5.6 Luna (max) · Max | 37.5 | $0.4 in · $1.80 out $60.00 allowance · 6.0× multiplier · 6× legacy default · > 272K context cache read $0.04 · write $0.5 | $0.049 $0.178 AA cost 1.66× Go/AA price factor | 203.3 | Estimated | |
GLM 5.3 Flash GLM-5.3-Flash · Standard | 41.9 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.042 $0.253 AA cost | 236.9 | Estimated | |
GPT 5.6 Luna GPT-5.6 Luna (max) · Max | 37.5 | $0.2 in · $1.20 out $60.00 allowance · 6.0× multiplier · 6× legacy default · ≤ 272K context cache read $0.02 · write $0.25 | $0.03 $0.178 AA cost | 336.5 | Estimated | |
DeepSeek V4 Pro DeepSeek V4 Pro 0813 (Reasoning, Max Effort) · Max | 36.3 | $0.435 in · $0.87 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.00363 · write — | $0.029 $0.674 AA cost 0.26× Go/AA price factor | 346.9 | Estimated | |
Longcat 2.0 LongCat 2.0 · Standard | 19.7 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.024 $0.146 AA cost | 410.4 | Estimated | |
GPT 5.6 Luna GPT-5.6 Luna (xhigh) · XHigh | 34.8 | $0.4 in · $1.80 out $60.00 allowance · 6.0× multiplier · 6× legacy default · > 272K context cache read $0.04 · write $0.5 | $0.024 $0.085 AA cost 1.66× Go/AA price factor | 425 | Estimated | |
MiniMax M2.7 MiniMax-M2.7 · Standard | 23.2 | $0.3 in · $1.20 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.06 · write $0.375 | $0.017 $0.102 AA cost | 590 | Estimated | |
GPT 5.6 Luna GPT-5.6 Luna (xhigh) · XHigh | 34.8 | $0.2 in · $1.20 out $60.00 allowance · 6.0× multiplier · 6× legacy default · ≤ 272K context cache read $0.02 · write $0.25 | $0.014 $0.085 AA cost | 703.4 | Estimated | |
GPT 5.6 Luna GPT-5.6 Luna (high) · High | 32.4 | $0.4 in · $1.80 out $60.00 allowance · 6.0× multiplier · 6× legacy default · > 272K context cache read $0.04 · write $0.5 | $0.012 $0.044 AA cost 1.66× Go/AA price factor | 823.9 | Estimated | |
Hy3 Hy3 · Standard | 25.8 | $0.14 in · $0.58 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.035 · write — | $0.012 $0.072 AA cost | 835.7 | Estimated | |
DeepSeek V4 Flash DeepSeek V4 Flash 0731 (Reasoning, Max Effort) · Max | 34.5 | $0.14 in · $0.28 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.0028 · write — | $0.00935 $0.22 AA cost 0.26× Go/AA price factor | 1,070.1 | Estimated | |
MiMo V2.5 Pro MiMo-V2.5-Pro · Standard | 26.4 | $0.435 in · $0.87 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.00363 · write — | $0.00902 $0.054 AA cost | 1,109.1 | Estimated | |
GPT 5.6 Luna GPT-5.6 Luna (high) · High | 32.4 | $0.2 in · $1.20 out $60.00 allowance · 6.0× multiplier · 6× legacy default · ≤ 272K context cache read $0.02 · write $0.25 | $0.00733 $0.044 AA cost | 1,363.6 | Estimated | |
Muse Spark 1.3 Contributor Muse Spark 1.3 (xhigh) · XHigh | 45.2 | Token rates not listed $60.00 allowance · 6.0× multiplier · 6× legacy default | $0.00395 $1.368 AA cost 0.017× Go/AA price factor | 2,530.7 | Estimated | |
MiMo V2.5 MiMo-V2.5 · Standard | 22.3 | $0.14 in · $0.28 out $60.00 allowance · 6.0× multiplier · 6× legacy default · Default cache read $0.0028 · write — | $0.00318 $0.019 AA cost | 3,141.4 | Estimated |
Model IDs come from the OpenCode Go model endpoint. Prices and allowance and privacy values come from Go documentation, the 6× legacy default, or owner overrides. Scores and benchmark task costs come from Artificial Analysis.