← variables.md

2026-10-14

114 change(s) in the model market

added to the catalog

• Pareto Latest (~unbiased/pareto-latest) added to the catalog: 262,144 ctx, $2.5/M in / $7.5/M out
• Google: Gemini 4 Argon (google/gemini-4-argon) added to the catalog: 1,048,576 ctx, $2/M in / $10/M out
• Google: Gemini 4 Argon (batch) (google/gemini-4-argon:batch) added to the catalog: 1,048,576 ctx, $1/M in / $5/M out
• LiquidAI: LFM2.5-24B-A2B (liquid/lfm-2.5-24b-a2b) added to the catalog: 128,000 ctx, $0.05/M in / $0.7/M out
• ScaleDown: Extract (scaledown/extract) added to the catalog: 1,000,000 ctx, $0.04/M in / $0/M out
• ScaleDown: Summarize (scaledown/summarize) added to the catalog: 1,000,000 ctx, $0.04/M in / $0/M out
• Pareto 26.9 (unbiased/pareto-26.9) added to the catalog: 262,144 ctx, $2.5/M in / $7.5/M out

removed from the catalog

• Apodex: Apodex 1.1 Mini (free) (apodex/apodex-1.1-mini:free) removed from the catalog
• inclusionAI: Ling 3.0 Flash Fin (inclusionai/ling-3.0-flash-fin) removed from the catalog
• inclusionAI: Ling 3.0 Flash Sante (inclusionai/ling-3.0-flash-sante) removed from the catalog
• Pareto (unbiased/pareto) removed from the catalog

model price changes

• ~deepseek/deepseek-flash-latest: prompt price $0.044/M → $0.02/M (−54.3%)
• ~deepseek/deepseek-flash-latest: completion price $0.765/M → $0.891/M (+16.5%)
• ~deepseek/deepseek-pro-latest: prompt price $0.25/M → $0.225/M (−10.0%)
• ~deepseek/deepseek-pro-latest: completion price $5/M → $8/M (+60.0%)
• ~moonshotai/kimi-latest: prompt price $0.73/M → $0.496/M (−32.1%)
• ~moonshotai/kimi-latest: completion price $13.5/M → $14/M (+3.7%)
• ~z-ai/glm-flash-latest: prompt price $0.026/M → $0.036/M (+37.9%)
• ~z-ai/glm-latest: prompt price $0.055/M → $0.058/M (+4.7%)
• ~z-ai/glm-latest: completion price $5/M → $4.4/M (−12.0%)
• deepseek/deepseek-v4-flash: prompt price $0.049/M → $0.091/M (+86.5%)
• deepseek/deepseek-v4-flash: completion price $1.28/M → $0.182/M (−85.8%)
• deepseek/deepseek-v4.1-flash: prompt price $0.15/M → $0.02/M (−86.6%)
• deepseek/deepseek-v4.1-flash: completion price $0.6/M → $0.891/M (+48.5%)
• inclusionai/ling-3.0-flash-vl: prompt price $0.021/M → $0.06/M (+185.7%)
• inclusionai/ling-3.0-flash-vl: completion price $0.062/M → $0.18/M (+192.2%)
• inclusionai/ling-3.1-flash: prompt price $0/M → $0.075/M
• inclusionai/ling-3.1-flash: completion price $0/M → $0.225/M
• minimax/minimax-m2: prompt price $0.3/M → $0.255/M (−15.0%)
• minimax/minimax-m2: completion price $1.2/M → $1.02/M (−15.0%)
• moonshotai/kimi-k3: prompt price $0.73/M → $0.62/M (−15.1%)
• moonshotai/kimi-k3: completion price $13.5/M → $15/M (+11.1%)
• openai/gpt-oss-120b: prompt price $0.15/M → $0.037/M (−75.3%)
• openai/gpt-oss-120b: completion price $0.6/M → $0.17/M (−71.7%)
• qwen/qwen3.5-35b-a3b: prompt price $0.08/M → $0.15/M (+87.5%)
• qwen/qwen3.5-35b-a3b: completion price $0.75/M → $1/M (+33.3%)
• qwen/qwen3.5-397b-a17b: prompt price $0.55/M → $0.5/M (−9.1%)
• qwen/qwen3.5-397b-a17b: completion price $3.5/M → $3.6/M (+2.9%)
• z-ai/glm-5.1: prompt price $0.966/M → $1.33/M (+37.7%)
• z-ai/glm-5.1: completion price $3.04/M → $4.18/M (+37.7%)
• z-ai/glm-5.2: prompt price $0.06/M → $0.05/M (−16.7%)
• z-ai/glm-5.3-flash: prompt price $0.026/M → $0.036/M (+37.9%)

model context changes

• inclusionai/ling-3.0-flash-vl: context length 262,144 → 131,072

quantization changes

• ModelRun: minimax/minimax-m3 quantization fp4 → fp8

provider price changes

• OpenInference: deepseek/deepseek-v4-flash prompt price $0.044/M → $0.045/M (+2.5%)
• Relace: deepseek/deepseek-v4-flash prompt price $0.045/M → $0.05/M (+10.6%)
• Inceptron: deepseek/deepseek-v4-flash-0731 prompt price $0.148/M → $0.13/M (−12.2%)
• AtlasCloud: deepseek/deepseek-v4.1-flash prompt price $0.3/M → $0.192/M (−36.0%)
• AtlasCloud: deepseek/deepseek-v4.1-flash completion price $1.2/M → $0.768/M (−36.0%)
• Baidu: deepseek/deepseek-v4.1-flash prompt price $0.3/M → $0.171/M (−43.0%)
• Baidu: deepseek/deepseek-v4.1-flash completion price $1.2/M → $0.684/M (−43.0%)
• Cloudflare: deepseek/deepseek-v4.1-flash prompt price $0.3/M → $0.1/M (−66.7%)
• Cloudflare: deepseek/deepseek-v4.1-flash completion price $1.2/M → $0.9/M (−25.0%)
• InferenceNet: deepseek/deepseek-v4.1-flash prompt price $0.077/M → $0.1/M (+29.9%)
• InferenceNet: deepseek/deepseek-v4.1-flash completion price $0.55/M → $0.66/M (+20.0%)
• Morph: deepseek/deepseek-v4.1-flash prompt price $0.049/M → $0.028/M (−42.9%)
• Morph: deepseek/deepseek-v4.1-flash completion price $0.69/M → $0.8/M (+15.9%)
• OpenInference: deepseek/deepseek-v4.1-flash prompt price $0.044/M → $0.02/M (−54.3%)
• OpenInference: deepseek/deepseek-v4.1-flash completion price $0.765/M → $0.891/M (+16.5%)
• Relace: deepseek/deepseek-v4.1-flash prompt price $0.05/M → $0.022/M (−55.2%)
• Wafer: deepseek/deepseek-v4.1-flash prompt price $0.09/M → $0.1/M (+11.1%)
• Wafer: deepseek/deepseek-v4.1-flash completion price $0.85/M → $0.99/M (+16.5%)
• Io Net: google/gemma-4-26b-a4b-it prompt price $0.123/M → $0.11/M (−10.6%)
• Io Net: google/gemma-4-26b-a4b-it completion price $0.35/M → $0.32/M (−8.6%)
• Novita: inclusionai/ling-3.1-flash prompt price $0/M → $0.075/M
• Novita: inclusionai/ling-3.1-flash completion price $0/M → $0.225/M
• ModelRun: minimax/minimax-m3 prompt price $0.75/M → $0.3/M (−60.0%)
• ModelRun: minimax/minimax-m3 completion price $3/M → $1.3/M (−56.7%)
• Decart: moonshotai/kimi-k3 prompt price $2.55/M → $2.34/M (−8.2%)
• Decart: moonshotai/kimi-k3 completion price $12.8/M → $11.7/M (−8.2%)
• InferenceNet: moonshotai/kimi-k3 prompt price $0.73/M → $0.62/M (−15.1%)
• InferenceNet: moonshotai/kimi-k3 completion price $10/M → $15/M (+50.0%)
• InferenceNet: moonshotai/kimi-k3 completion price $15/M → $18/M (+20.0%)
• Morph: moonshotai/kimi-k3 prompt price $0.75/M → $0.67/M (−10.7%)
• Morph: moonshotai/kimi-k3 completion price $14.9/M → $20/M (+34.2%)
• Relace: moonshotai/kimi-k3 prompt price $2/M → $0.496/M (−75.2%)
• Together: moonshotai/kimi-k3 prompt price $2.7/M → $3/M (+11.1%)
• Together: moonshotai/kimi-k3 completion price $13.5/M → $15/M (+11.1%)
• Wafer: moonshotai/kimi-k3 prompt price $0.84/M → $0.72/M (−14.3%)
• Wafer: moonshotai/kimi-k3 prompt price $2.8/M → $0.7/M (−75.0%)
• Wafer: moonshotai/kimi-k3 completion price $15.5/M → $10/M (−35.5%)
• Darkbloom: qwen/qwen3.8-27b prompt price $0.05/M → $0.035/M (−30.0%)
• Io Net: xiaomi/mimo-v2.6-flash prompt price $0.19/M → $0.15/M (−21.1%)
• Decart: z-ai/glm-5.2 prompt price $0.273/M → $0.358/M (+31.0%)
• Decart: z-ai/glm-5.2 completion price $1.68/M → $2.2/M (+31.0%)
• Inceptron: z-ai/glm-5.2 prompt price $0.95/M → $0.69/M (−27.4%)
• Inceptron: z-ai/glm-5.2 completion price $2.94/M → $3.15/M (+7.1%)
• Morph: z-ai/glm-5.2 prompt price $0.4/M → $0.079/M (−80.3%)
• Wafer: z-ai/glm-5.2 prompt price $0.06/M → $0.05/M (−16.7%)
• Decart: z-ai/glm-5.3 prompt price $0.85/M → $0.84/M (−1.2%)
• Decart: z-ai/glm-5.3 completion price $2.66/M → $2.65/M (−0.4%)
• Inceptron: z-ai/glm-5.3 prompt price $0.6/M → $0.55/M (−8.3%)
• Morph: z-ai/glm-5.3 prompt price $0.055/M → $0.074/M (+34.5%)
• Morph: z-ai/glm-5.3 completion price $5/M → $6/M (+20.0%)
• Sail Research: z-ai/glm-5.3 prompt price $0.2/M → $0.15/M (−25.0%)
• Sail Research: z-ai/glm-5.3 prompt price $0.2/M → $0.15/M (−25.0%)
• Inceptron: z-ai/glm-5.3-flash prompt price $0.078/M → $0.105/M (+34.5%)
• InferenceNet: z-ai/glm-5.3-flash prompt price $0.07/M → $0.1/M (+42.9%)
• InferenceNet: z-ai/glm-5.3-flash completion price $0.05/M → $0.15/M (+200.0%)
• Morph: z-ai/glm-5.3-flash prompt price $0.029/M → $0.044/M (+51.7%)
• OpenInference: z-ai/glm-5.3-flash prompt price $0.026/M → $0.036/M (+37.9%)
• Reka: z-ai/glm-5.3-flash prompt price $0.042/M → $0.06/M (+42.9%)
• Reka: z-ai/glm-5.3-flash completion price $0.84/M → $1.6/M (+90.5%)
• Wafer: z-ai/glm-5.3-flash prompt price $0.065/M → $0.095/M (+46.2%)

provider context changes

• ModelRun: z-ai/glm-5.3 context length 524,288 → 1,048,576

providers added

• Relace now serves deepseek/deepseek-v4-pro-0813 (fp4, 1,048,576 ctx, $0.225/M in / $8/M out)
• Phala now serves moonshotai/kimi-k2.7-code (unknown, 262,144 ctx, $0.95/M in / $4/M out)
• Relace now serves z-ai/glm-5.3 (unknown, 1,048,576 ctx, $0.058/M in / $4.4/M out)
• Makora now serves z-ai/glm-5.3-flash (unknown, 1,048,576 ctx, $0.14/M in / $0.47/M out)

providers removed

• Reka no longer serves deepseek/deepseek-v4-pro-0813 (was unknown)
• Novita no longer serves inclusionai/ling-3.0-flash-vl (was bf16)
• Modal no longer serves qwen/qwen3.8-2.4t-a95b (was unknown)
• Tenstorrent no longer serves qwen/qwen3.8-27b (was fp4)
• Tenstorrent no longer serves z-ai/glm-5.3 (was fp8)

openrouter catalog snapshots 2026-10-13 → 2026-10-14 · schema 1 · generated 2026-10-14T10:14:05.769Z