← variables.md

2026-10-28

93 change(s) in the model market

added to the catalog

• PrismML: Ternary Bonsai 2 9B (prism-ml/ternary-bonsai-2-9b) added to the catalog: 262,144 ctx, $0.08/M in / $0.13/M out

model price changes

• ~deepseek/deepseek-flash-latest: prompt price $0.02/M → $0.013/M (−37.0%)
• ~deepseek/deepseek-flash-latest: completion price $1/M → $1.8/M (+80.0%)
• ~deepseek/deepseek-pro-latest: prompt price $0.243/M → $0.254/M (+4.7%)
• ~moonshotai/kimi-latest: prompt price $0.179/M → $0.159/M (−11.2%)
• ~moonshotai/kimi-latest: completion price $11.5/M → $20/M (+73.9%)
• ~z-ai/glm-flash-latest: prompt price $0.029/M → $0.02/M (−30.9%)
• ~z-ai/glm-flash-latest: completion price $0.092/M → $0.124/M (+34.1%)
• deepseek/deepseek-v4-flash: prompt price $0.05/M → $0.091/M (+82.0%)
• deepseek/deepseek-v4-flash: completion price $0.45/M → $0.182/M (−59.6%)
• meta-llama/llama-3.1-8b-instruct: prompt price $0.05/M → $0.02/M (−60.0%)
• meta-llama/llama-3.1-8b-instruct: completion price $0.08/M → $0.04/M (−50.0%)
• moonshotai/kimi-k2.7-code: prompt price $0.56/M → $0.672/M (+20.1%)
• moonshotai/kimi-k3: prompt price $0.179/M → $0.159/M (−11.2%)
• moonshotai/kimi-k3: completion price $11.5/M → $20/M (+73.9%)
• qwen/qwen3.6-27b: prompt price $0.32/M → $0.45/M (+40.6%)
• qwen/qwen3.6-27b: completion price $3.2/M → $2.7/M (−15.6%)
• qwen/qwen3.6-35b-a3b: completion price $0.95/M → $0.9/M (−5.3%)
• qwen/qwen3.8-27b: prompt price $0.2/M → $0.039/M (−80.5%)
• qwen/qwen3.8-27b: completion price $2.5/M → $1.25/M (−50.0%)
• z-ai/glm-5.1: prompt price $0.966/M → $1.4/M (+44.9%)
• z-ai/glm-5.1: completion price $3.04/M → $4.4/M (+44.9%)
• z-ai/glm-5.2: prompt price $0.034/M → $0.014/M (−58.9%)

model context changes

• inclusionai/ling-3.1-flash: context length 262,144 → 1,000,000

provider price changes

• Inceptron: deepseek/deepseek-v4-flash-0731 completion price $0.413/M → $0.495/M (+20.0%)
• Sail Research: deepseek/deepseek-v4-flash-0731 completion price $0.15/M → $0.3/M (+100.0%)
• Sail Research: deepseek/deepseek-v4-flash-0731 completion price $0.15/M → $0.3/M (+100.0%)
• Wafer: deepseek/deepseek-v4-flash-0731 prompt price $0.13/M → $0.14/M (+7.7%)
• SiliconFlow: deepseek/deepseek-v4-pro prompt price $1.5/M → $1/M (−33.4%)
• Relace: deepseek/deepseek-v4-pro-0813 prompt price $0.243/M → $0.254/M (+4.7%)
• Morph: deepseek/deepseek-v4.1-flash prompt price $0.034/M → $0.063/M (+85.3%)
• Morph: deepseek/deepseek-v4.1-flash completion price $0.6/M → $0.548/M (−8.7%)
• OpenInference: deepseek/deepseek-v4.1-flash prompt price $0.006/M → $0.001/M (−77.6%)
• OpenInference: deepseek/deepseek-v4.1-flash completion price $3.8/M → $0.536/M (−85.9%)
• AtlasCloud: deepseek/deepseek-v4.1-flash-1017 prompt price $0.195/M → $0.135/M (−30.8%)
• AtlasCloud: deepseek/deepseek-v4.1-flash-1017 completion price $0.78/M → $0.54/M (−30.8%)
• DigitalOcean: deepseek/deepseek-v4.1-flash-1017 prompt price $0.225/M → $0.18/M (−20.0%)
• DigitalOcean: deepseek/deepseek-v4.1-flash-1017 completion price $0.9/M → $0.72/M (−20.0%)
• Ionstream: deepseek/deepseek-v4.1-flash-1017 prompt price $0.187/M → $0.15/M (−19.8%)
• Ionstream: deepseek/deepseek-v4.1-flash-1017 completion price $0.51/M → $0.45/M (−11.8%)
• Morph: deepseek/deepseek-v4.1-flash-1017 prompt price $0.034/M → $0.063/M (+85.3%)
• Morph: deepseek/deepseek-v4.1-flash-1017 completion price $0.6/M → $0.548/M (−8.7%)
• OpenInference: deepseek/deepseek-v4.1-flash-1017 prompt price $0.02/M → $0.013/M (−37.0%)
• OpenInference: deepseek/deepseek-v4.1-flash-1017 completion price $1/M → $1.8/M (+80.0%)
• StreamLake: deepseek/deepseek-v4.1-flash-1017 prompt price $0.178/M → $0.15/M (−16.0%)
• StreamLake: deepseek/deepseek-v4.1-flash-1017 completion price $0.714/M → $0.6/M (−16.0%)
• Inceptron: moonshotai/kimi-k2.6 prompt price $0.585/M → $0.624/M (+6.7%)
• Inceptron: moonshotai/kimi-k2.7-code prompt price $0.56/M → $0.672/M (+20.1%)
• Morph: moonshotai/kimi-k3 prompt price $7.34/M → $1.04/M (−85.9%)
• Morph: moonshotai/kimi-k3 completion price $28.1/M → $14.6/M (−48.0%)
• Relace: moonshotai/kimi-k3 prompt price $0.18/M → $0.16/M (−10.6%)
• Relace: moonshotai/kimi-k3 completion price $9.72/M → $8.1/M (−16.7%)
• Sail Research: moonshotai/kimi-k3 prompt price $0.25/M → $0.23/M (−8.0%)
• Wafer: moonshotai/kimi-k3 prompt price $0.179/M → $0.159/M (−11.2%)
• Wafer: moonshotai/kimi-k3 completion price $11.5/M → $20/M (+73.9%)
• Venice: nvidia/nemotron-3.5-super-vl prompt price $0.25/M → $0.2/M (−20.0%)
• Venice: nvidia/nemotron-3.5-super-vl completion price $1.25/M → $0.5/M (−60.0%)
• Reka: qwen/qwen3.6-27b completion price $2/M → $3/M (+50.0%)
• Parasail: qwen/qwen3.6-35b-a3b completion price $0.95/M → $0.9/M (−5.3%)
• Tenstorrent: qwen/qwen3.8-27b prompt price $0.06/M → $0.15/M (+150.0%)
• Tenstorrent: qwen/qwen3.8-27b completion price $0.5/M → $1.5/M (+200.0%)
• DeepInfra: xiaomi/mimo-v2.6-flash prompt price $0.14/M → $0.126/M (−10.0%)
• DeepInfra: xiaomi/mimo-v2.6-flash completion price $0.28/M → $0.252/M (−10.0%)
• Morph: z-ai/glm-5.2 prompt price $6.69/M → $0.203/M (−97.0%)
• Morph: z-ai/glm-5.2 completion price $8.14/M → $2.21/M (−72.9%)
• Relace: z-ai/glm-5.2 prompt price $0.032/M → $0.013/M (−59.0%)
• Relace: z-ai/glm-5.2 completion price $7.15/M → $7.73/M (+8.1%)
• Wafer: z-ai/glm-5.2 prompt price $0.034/M → $0.014/M (−58.9%)
• Morph: z-ai/glm-5.3 prompt price $6.69/M → $0.203/M (−97.0%)
• Morph: z-ai/glm-5.3 completion price $8.14/M → $2.21/M (−72.9%)
• Reka: z-ai/glm-5.3 completion price $4.2/M → $2.1/M (−50.0%)
• InferenceNet: z-ai/glm-5.3-flash prompt price $0.12/M → $0.108/M (−10.0%)
• InferenceNet: z-ai/glm-5.3-flash completion price $0.388/M → $0.35/M (−9.8%)
• InferenceNet: z-ai/glm-5.3-flash prompt price $0.12/M → $0.108/M (−10.0%)
• InferenceNet: z-ai/glm-5.3-flash completion price $0.388/M → $0.35/M (−9.8%)
• Morph: z-ai/glm-5.3-flash prompt price $0.281/M → $0.073/M (−74.0%)
• Morph: z-ai/glm-5.3-flash completion price $0.65/M → $0.322/M (−50.5%)
• OpenInference: z-ai/glm-5.3-flash prompt price $0.03/M → $0.021/M (−31.0%)
• OpenInference: z-ai/glm-5.3-flash completion price $0.1/M → $0.052/M (−48.4%)
• Relace: z-ai/glm-5.3-flash prompt price $0.029/M → $0.02/M (−30.9%)
• Relace: z-ai/glm-5.3-flash completion price $0.092/M → $0.124/M (+34.1%)

provider context changes

• Novita: inclusionai/ling-3.1-flash context length 262,144 → 1,000,000

providers added

• Fireworks now serves deepseek/deepseek-v4.1-flash-1017 (unknown, 1,048,576 ctx, $0.45/M in / $1.8/M out)
• AkashML now serves google/gemma-4-26b-a4b-it (fp4, 131,072 ctx, $0.07/M in / $0.24/M out)
• DekaLLM now serves google/gemma-4-31b-it (unknown, 262,144 ctx, $0.14/M in / $0.4/M out)
• Fireworks now serves minimax/minimax-m3.1-flash (unknown, 1,048,576 ctx, $0.15/M in / $0.6/M out)
• StreamLake now serves minimax/minimax-m3.1-flash (fp8, 1,000,000 ctx, $0.135/M in / $0.54/M out)
• Azure now serves openai/gpt-6.1-terra (unknown, 1,050,000 ctx, $1.2/M in / $6/M out)
• Azure now serves openai/gpt-6.1-terra-pro (unknown, 1,050,000 ctx, $1.2/M in / $6/M out)
• Io Net now serves z-ai/glm-5.3 (fp8, 262,124 ctx, $0.33/M in / $3.2/M out)

providers removed

• InferenceNet no longer serves stepfun/step-5-preview (was fp4)
• InferenceNet no longer serves stepfun/step-5-preview (was fp4)
• Io Net no longer serves tencent/hy4-preview (was fp8)

openrouter catalog snapshots 2026-10-27 → 2026-10-28 · schema 1 · generated 2026-10-28T11:20:55.161Z